[go: up one dir, main page]

WO2024261001A1 - System and method for detection and prediction of kidney disease events - Google Patents

System and method for detection and prediction of kidney disease events Download PDF

Info

Publication number
WO2024261001A1
WO2024261001A1 PCT/EP2024/066988 EP2024066988W WO2024261001A1 WO 2024261001 A1 WO2024261001 A1 WO 2024261001A1 EP 2024066988 W EP2024066988 W EP 2024066988W WO 2024261001 A1 WO2024261001 A1 WO 2024261001A1
Authority
WO
WIPO (PCT)
Prior art keywords
module
data
kidney
aki
intelligence
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/EP2024/066988
Other languages
French (fr)
Inventor
Andrea ANCONA
Francesca ALFIERI
Enrico PERPIGNANO
Simone ZAPPALA
Alessandro Bacci
Valentina Alice CAUDA
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
U Care Medical Srl
Original Assignee
U Care Medical Srl
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by U Care Medical Srl filed Critical U Care Medical Srl
Publication of WO2024261001A1 publication Critical patent/WO2024261001A1/en
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the invention lies in the field of monitoring health status and particularly in the field of monitoring renal health status of humans.
  • the goal of the present invention is to provide a system and method for monitoring the renal health status of humans. More particularly, the present invention relates to a system, a method performed in such a system and corresponding use of a system for detection and prediction of kidney disease events.
  • a sudden loss of kidney function is known as Acute Kidney Injury (AKI) and it is a major worldwide concern due to the associated high in-hospital incidence, mortality, social costs and disability. Timely intervention in diagnosis and treatment may therefore be beneficial.
  • Acute Kidney Injury Acute Kidney Injury (AKI) and it is a major worldwide concern due to the associated high in-hospital incidence, mortality, social costs and disability. Timely intervention in diagnosis and treatment may therefore be beneficial.
  • ICU Intensive Care Units
  • Intensive Care Units consists mainly in the prevention of the disease, by adopting measures able to guarantee appropriate volume control, kidney perfusion, sepsis prevention and nephrotoxic drug tailoring. Early identification of patients who may benefit from such preventive measures is key to enable effective prevention of AKI onset.
  • One approach consists of the use of chemical in-vitro biomarkers. Biomarkers have the limitation of being time-consuming, not specific and discrete in time. These limitations have slowed wide adoption in the clinic.
  • a different approach consists of the use of algorithms that can predict AKI onset.
  • CN 110 914 915 A relates to a medical treatment machine, such as a home dialysis machine, which may receive prescription parameters that define parameters of a medical treatment to be administered to a patient.
  • the clinician enters the medical prescription into a Clinical Information System (CIS) that invokes a system to evaluate the compatibility of the entered prescription by transmitting the prescription parameters to a server that has access to a database of medical devices and their operating parameters.
  • CIS Clinical Information System
  • US 2022 038 3998 A1 relates to a computer implemented method comprises monitoring live feedback received over a course of care of a patient, wherein the live feedback comprises physiological information regarding a physiological state of the patient. The method further comprises employing AI to identify, based on the live feedback information, an event or condition associated with the course of care of the patient that warrants clinical attention or a clinical response.
  • US 2022 040 6437 A1 relates to a method and a system for determining and providing renal therapy, wherein the method may include a modality analysis.
  • the method may include, via a processor of a computing device: determining a modality analysis model configured to determine a modality status of a patient, the modality status configured to indicate a probability of a transition from a first modality to a second modality, and generating the modality status via the modality analysis model using patient information associated with the patient.
  • determining a modality analysis model configured to determine a modality status of a patient, the modality status configured to indicate a probability of a transition from a first modality to a second modality
  • generating the modality status via the modality analysis model using patient information associated with the patient Other embodiments are described
  • EP 3918610 A1 relates to a monitoring system, and the related monitoring and predicting methods of diuresis for the calculation of the risk of onset of renal failure of a patient, including a device comprising a first algorithm for recording, storing, comparing and processing the measurements of the urine container and a second algorithm for predicting the future measurements of the urine container and the level of kidney failure risk associated with
  • US 20200057076 A1 relates to the use of p21 biomarker in the evaluation of whether a patient is suffering from kidney injury or failure, and can be used in methods of treating kidney injury or failure by determining the appropriateness of one or more of initiating renal replacement therapy, withdrawing delivery of compounds that are known to be damaging to the kidney, delaying or avoiding procedures that are known to be damaging to the kidney, and modifying diuretic administration.
  • US 2018 011 0455 A1 relates to a system and urine sensing devices for and method of monitoring kidney function, and in particular, a kidney function monitoring system provides a portable urine monitor system that can provide real-time and continuous feedback about urine output and/or level of at least one urinary component, wherein the portable monitoring device comprises an adaptive and modular self-learning algorithm for the real- time assessment of AKI risk.
  • US 20220390467 A1 relates to a method for determining whether a sepsis patient is likely to develop severe sepsis associated acute kidney injury (SA-AKI) using a combination of clinical data and biomarker data obtained during the first 24 hours following the subject's diagnosis with sepsis.
  • SA-AKI severe sepsis associated acute kidney injury
  • the invention relates to a method for monitoring kidney function, the method comprising: acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status; and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module may be based on the at least one kidney functioning status.
  • the preprocessing step may comprise performing at least one unit of measure conversion.
  • the preprocessing step may comprise discarding at least one out-of-range value.
  • the preprocessing step may comprise processing at least one diuresis data.
  • the preprocessing step may comprise processing at least one blood chemistry data. Moreover, the preprocessing step may comprise processing at least one physiological data. Moreover, the at least one artificial-intelligence assisted module may comprise at least one of: a first module, a second module, and a third module.
  • the first module may also be referred to as AKI predicting module or simply as AKI module.
  • the second module may also be referred to as persistent AKI predicting module or simply as persistent AKI module.
  • the third module may also be referred to continuous renal replacement therapy monitoring module or simply as CRRT module.
  • the classifying step may comprise performing the classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage.
  • KDIGO Kidney Disease Improving Global Outcomes
  • the method may comprise determining which of the at least one artificial- intelligence-assisted module to trigger.
  • the method may comprise determining which at least one artificial-intelligence-assisted module to trigger precedes the step of triggering the at least one artificial-intelligence-assisted module.
  • determining which at least one artificial-intelligence-assisted module to trigger may be based on the KDIGO stage.
  • the at least one kidney functioning status may comprise the KDIGO stage. When the least one kidney functioning status may comprise data indicating a non-applicable stage, no artificial-intelligence-assisted module may be triggered. When the least one kidney functioning status may comprise data indicating a KDIGO stage 0 or 1, the first module may be triggered.
  • the method may comprise performing the classifying stage comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine.
  • the classifying step may comprise determining an acute kidney injury (AKI).
  • the method may comprise determining a persistency of the AKI. Further, the method may comprise determining a final KDIGO stage.
  • the method may comprise predicting at least one kidney disease event. The predicting of the least one kidney disease event may be based on the at least one kidney functioning status.
  • the predicting of the at least one kidney disease event may be performed by the at least one artificial-intelligence assisted module.
  • the method may comprise predicting a risk of a patient of developing AKI.
  • the predicting steps may be performed hourly.
  • the method may comprise predicting the risk for onset AKI within next 24 hours at a current time.
  • the Additionally, method may comprise automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status.
  • the AKI risk level may be based on the predicting of the risk for onset AKI.
  • the method may comprise predicting a risk for onset of persistent AKI at a current time.
  • the method may comprise automatically generating a persistent AKI risk level, wherein a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status.
  • the persistent AKI risk level may be based on the predicting of the risk for onset of persistent AKI.
  • the predicting of the risk for onset of AKI may be performed by the first module.
  • the predicting of the risk for onset of persistent AKI may be performed by the second module.
  • the method may comprise predicting a future kidney recovery trajectory.
  • the predicting of the future kidney recovery trajectory may be performed by the third module.
  • the method may comprise outputting at least one decision-supporting-data based on the predicting of the future kidney recovery trajectory.
  • the method may comprise generating a probability for stopping a continuous renal replacement therapy (CRRT) which may also be referred to as CRRT index comprising a CRRT risk level.
  • CRRT continuous renal replacement therapy
  • the generating of the probability CRRT index may be performed by the third module.
  • the probability CRRT index may be based on the predicting of the future recovery trajectory.
  • the third module may calculate the CRRT index, which is a score indicating the likelihood of a current time being the optimal timing to stop the CRRT treatment.
  • the CRRT module may be seen as a proxy of the fact that the kidney has recovered its function.
  • CRRT index trajectory over time can be considered the future kidney recovery trajectory.
  • the method may comprise generating at least one of a probability of risk of death within the next seven days during renal replacement therapy, a probability of risk of death within the next seven days at the end of renal replacement therapy, a probability of risk of restart of renal replacement therapy within the next seven days, and an optimal time to stop the renal replacement therapy.
  • the method may comprise classifying at least one preprocessed data relating to predicting a risk for onset of persistent AKI, or a future recovery trajectory in at least one zone.
  • the at least one zone is delimited according to at least one range of values. These values are defined, with respect to a standardized database, to assess the urgency needed for the start and/or the end of renal replacement therapy.
  • the method comprises displaying these classifications.
  • the method also comprises displaying at least one AKI risk level, at least one persistent AKI risk level and/or at least one probability CRRT index, in function of time.
  • the method may comprise storing and displaying at least one input submitted by an authorized user corresponding to at the least one AKI risk level at, at the least one persistent AKI risk level, and/or the at least one probability CRRT index at least one time. That input may comprise preferably a note, a message... that may be related to the data or the time the input is corresponding to.
  • the method may comprise prompting at least one authorized user to input at least one data point.
  • the at least one data point may comprise computer-readable input data points.
  • the at least one data point may comprise at least one selectable data point comprising at least one predetermined select data point, wherein the method may comprise prompting at least one authorized user to select at least one option.
  • the method may comprise bidirectionally communicating with at least one server.
  • the method may comprise utilizing any data as recited herein to train at least one algorithm.
  • the training step may be performed on the at least one server.
  • the method may comprise performing the method as recited herein in an integrated intensive care unit system.
  • the method may comprise performing the method as recited herein by using at least one of the: first module, the second module, and third module.
  • at least one of the at least one server may comprise a local server.
  • at least one of the at least one server may comprise a cloud server.
  • the probability CRRT index may comprise a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A.
  • the invention in a second aspect, relates to a system for monitoring kidney function, the system comprising: an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence-assisted module, wherein the triggering component may be configured to trigger the at least one artificial-intelligence-assisted module based on the at least one kidney functioning status.
  • the processing component may be configured to perform at least one unit of measure conversion. In another embodiment, the processing component may be configured to discard at least one out-of-range value. Further, the processing component may be configured to process at least one diuresis data. Moreover, the processing component may be configured to process at least one blood chemistry data. In a further embodiment, the processing component may be configured to process at least one physiological data.
  • the at least one artificial-intelligence assisted module may comprise to at least one of: first module, the second module, and third module.
  • the classifying component may be configured to perform a classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage.
  • KDIGO Kidney Disease Improving Global Outcomes
  • the system may be configured to determine which of the at least one artificial-intelligence- assisted module to trigger. Further, the system may be configured to determine which at least one artificial-intelligence-assisted module to trigger before prompting the triggering component to trigger the at least one artificial-intelligence-assisted module. Moreover, the system may be configured to determine which at least one artificial-intelligence-assisted module to trigger based on the KDIGO stage. The at least one kidney functioning status may comprise the KDIGO stage. The system may be configured to trigger the at least one artificial-intelligence-assisted module based on a value of the KDIGO stage.
  • the system may be configured to trigger none artificial-intelligence- assisted module.
  • the system may be configured to trigger the first module.
  • the least one kidney functioning status may comprise data indicating the value of the KDIGO stage as 2 or 3
  • the system may be configured to trigger the second module.
  • the least one kidney functioning status may comprise data indicating the value of the KDIGO stage as indicating that a currently started dialysis treatment, the system may be configured to trigger the third module.
  • the system may be configured to perform the classifying step comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine.
  • the classifying component may be configured to determine an acute kidney injury (AKI).
  • the system may be configured to determine a persistency of the AKI.
  • the system may be configured to determine a final KDIGO stage.
  • the system may be configured to predict at least one kidney disease event. Additionally or alternatively, the system may be configured to predict the at least one kidney disease event based on the at least one kidney functioning status.
  • the system may be configured to predict the at least one kidney disease event by means of the at least one artificial-intelligence assisted module.
  • the first module may be configured to predict a risk of a patient of developing AKI.
  • the first module may be configured to predict the risk of a patient of developing AKI on an hourly basis.
  • the system may be configured to predict a risk for onset AKI within next 24 hours at a current time. Further, the system may be configured to automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status.
  • the AKI risk level may be based on the prediction of the risk for onset AKI.
  • the system may be configured to predict a risk for onset of persistent AKI at a current time.
  • the system may be configured to automatically generate a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status.
  • the persistent AKI risk level may be based on the prediction of the risk for onset of persistent AKI.
  • the first module may be configured to predict the risk for onset of AKI.
  • the second module may be configured to predict the risk for onset of persistent AKI.
  • the system may be configured to predict a future kidney recovery trajectory.
  • the third module may be configured to predict the future kidney recovery trajectory.
  • the system may be configured to output at least one decision-supporting-data based on the prediction of the future kidney recovery trajectory.
  • the system may be configured to generate a probability CRRT index comprising a risk level.
  • the third module may be configured to generate of the probability CRRT index.
  • the probability CRRT index may be based on the prediction of the future recovery trajectory.
  • the system may be configured to prompt at least one authorized user to input at least one data point.
  • the at least one data point may comprise computer-readable input data points.
  • the at least one data point may comprise at least one selectable data point comprising at least one predetermined selected data point, wherein the system may be configured to prompt the at least one authorized user to select at least one option.
  • the system may be configured to bidirectionally communicate with at least one server.
  • the system may be configured to utilize any data of any of the preceding method embodiments to train at least one algorithm.
  • the training step may be performed on the at least one server.
  • the system may be configured to perform the method as recited herein.
  • the system may be integrated into an intensive care unit system.
  • the system may be configured to perform as recited herein by using at least one of the: first module, the second module, and third module.
  • At least one of the at least one server may comprise a local server.
  • At least one of the at least one server may comprise a cloud server.
  • the persistent AKI risk level may comprise a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A.
  • the invention may relate to another method for monitoring kidney function, which will be referred to as the “KDIGO Bundle” method, comprising, acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, comparing the information contained in the at least one raw/preprocessed data with a standardized database and, outputting at least one output data indicative of the result of the comparison step.
  • the preprocessing step may comprise performing at least one unit of measure conversion.
  • the preprocessing step may comprise discarding at least one out-of-range value.
  • the preprocessing step may comprise processing at least one diuresis data.
  • the preprocessing step may comprise processing at least one blood chemistry data. Moreover, the preprocessing step may comprise processing at least one physiological data. In one embodiment, the acquiring step may comprise acquiring at least one arterial pressure data. In another embodiment, the acquiring step may comprise acquiring at least one blood glucose data. Additionally or alternatively, the acquiring step may comprise acquiring at least one drug identification data. Moreover, the acquiring step may comprise acquiring at least one serum creatinine data. Furthermore, the acquiring step may comprise acquiring at least one drug dosage data. In a further embodiment, the acquiring step may comprise acquiring at least one body surface area data. Additionally or alternatively, the acquiring step may comprise acquiring at least one stroke volume data.
  • the acquiring step may comprise acquiring at least one heart rate data.
  • the comparing step comprises detecting at least one hypotension event. Additionally or alternatively, the comparing step comprises detecting at least one nephrotoxic drug.
  • the comparing step comprises calculating at least one Glomerular Ultrafiltration Rate (GFR) value.
  • the comparing step comprises comparing the at least one GFR value with the standardized database.
  • the comparing step comprises outputting at least one drug intake instruction corresponding to the result of the comparison of the at least one GFR value with the standardized database.
  • the “KDIGO Bundle” method comprises diagnosing a hypotension event.
  • the “KDIGO Bundle” method may also make use any of the previously cited method’s results.
  • the “KDIGO Bundle” method may comprise determining the appropriate at least one drug dosage to the corresponding risk for onset persistent AKI at a current time.
  • the “KDIGO Bundle” method may comprise determining the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy.
  • the invention may relate to a method for conducting the furosemide test, which will be referred to as the assessment method, comprising, acquiring at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, preprocessing the at least one urine output data to automatically generate at least one urine output processed data, calculating a cumulative urine output after every hour since the acquiring step, and comparing the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database.
  • the assessment method may comprise displaying the result of the comparison step.
  • the preprocessing step may comprise performing at least one unit of measure conversion.
  • the comparison result may comprise a probability of risk of worsening kidney function.
  • the acquiring step may comprise acquiring at least one data indicating a currently ended renal replacement therapy treatment and at least one corresponding time data from at least one data source.
  • the comparison may comprise evaluating the cumulative urine output 24 hours after the at least one corresponding date and time data, when the acquiring step is performed several hours after the at least one time data from at least one data source corresponding to the at least one data indicating a currently ended renal replacement therapy treatment.
  • the comparison result may comprise a probability of risk of unsuccessful weaning from renal replacement therapy.
  • the assessment method may comprise diagnosing a risk of worsening kidney condition.
  • the assessment method may also comprise diagnosing a risk of unsuccessful weaning from renal replacement therapy.
  • the invention relates to a method, which will be referred to as a composite method, comprising any of and any combination of the previously cited method, the previously cited “KDIGO Bundle” method and the previously cited assessment method.
  • the system may be configured to carry out the method as recited herein.
  • the system may be configured to carry out the “KDIGO Bundle” method as recited herein.
  • the system may be configured to carry out the assessment method as recited herein.
  • the system may be configured to carry out the composite method as cited herein.
  • the method may comprise utilizing the system as recited herein to carry out the method as recited herein.
  • the method may comprise utilizing components of the system as recited herein to carry out given steps of the method as recited herein.
  • the “KDIGO Bundle” method may comprise utilizing the system as recited herein to carry out the “KDIGO Bundle” method as recited herein.
  • the “KDIGO Bundle” method may comprise utilizing components of the system as recited herein to carry out given steps of “KDIGO Bundle” method as recited herein.
  • the assessment method may comprise utilizing the system as recited herein to carry out the assessment method as recited herein.
  • the assessment method may comprise utilizing components of the system as recited herein to carry out given steps of assessment method as recited herein.
  • the composite method may comprise utilizing the system as recited herein to carry out the composite method as recited herein.
  • the composite method may comprise utilizing components of the system as recited herein to carry out given steps of composite method as recited herein.
  • the invention relates to a computer program comprising instructions which, when the program may be executed by a computer, cause the computer to carry out any of the methods and any combination of the methods as recited herein.
  • the invention relates to a non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out any of the methods and any combination of the methods as recited herein.
  • the invention relates to use of the system as recited herein.
  • the approach of the present invention comprises a plurality of advantages of the state of the art.
  • the approach of the present invention is advantageous when compared with typical in-vitro diagnostic biomarkers, as the present invention is particularly beneficial in terms of timing of AKI prediction.
  • the present invention is capable of predicting continuously AKI future states during the entire permanence of a patient in the intensive care area.
  • the present invention does not require specialized laboratory devices nor overly complex combination of devices.
  • the present invention provides a real-time prediction updated every hour, which allows lifting physician from the responsibility of timely executing a diagnostic test.
  • the approach of the present invention is automated, and no additional human intervention, in particular, medical professional is required, as the present invention uses only routinely collected data.
  • a further advantage of the present invention is that the approach is capable of being executing in background and trigger an alarm when AKI-related events are identified.
  • the approach of the present invention is also advantageous over other artificial intelligence-based approaches.
  • the first module of the present overcomes several limitations of the state of the art that hindered other available approaches to enter the routine clinical practice.
  • the first module comprises a plurality of improved predictive performances in both internal and external validation for AKI stages 2 and 3.
  • the first module employs only a small number of routinely-collected predictive parameters, which is crucial to enable the implementation of module.
  • the first module further comprises other variables, in addition to those known in the art, such as platelets, Blood Urea Nitrogen/sCr ratio, White Blood Cell, Haemoglobin, Albumin, Heart Rate.
  • the first module is also more robust than similar approaches known in the art, in particular, over different types of Intensive Care Unit, either medical or post cardiac-surgery ICUs.
  • the first module is not affected by other parameters such use of diuretics in patients, that for other known approaches may be detrimental, as these could introduce a bias in the predictive performance.
  • An even further advantage of the approach of the first module of the present invention is that the module does not exhibit any bias when faced with different patient populations data.
  • the first module is, moreover, capable of predicting both AKI defined with Urine Output-based criteria and Creatinine-based criteria, which is particularly advantageous over the state of the art which only focused on one of the two diagnostic criteria and AKI phenotypes. This is also particularly beneficial, as it is known that Creatinine-based AKI represent only a fraction of the total AKI episodes acquired in ICU, which make the first module capable of also addressing the remaining fraction.
  • the approach of the second module is also advantageous, as it focuses on a novel set of features based on time-series trends. Additionally, the second module comprises an improved performance than the typical approach of the few machine-learning based inventions which also only focused on specific cohorts of patients, such as septic patients.
  • the approach of the third module of the present invention is also beneficial, as it allows to predict optimal timing to stop CRRT treatments. Furthermore, the method can be performed for the assembling, testing and/or calibrating the system without the presence of a patient. Moreover, the training of the at least one AI module can be performed without the presence of a patient.
  • the present technology is also described by the following numbered embodiments. Below, method embodiments will be discussed. These embodiments are abbreviated by the letter “M” followed by a number. When reference is herein made to a method embodiment, those embodiments are meant. M1.
  • a method for monitoring kidney function comprising acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status, and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module is based on the at least one kidney functioning status.
  • the preprocessing step comprises performing at least one unit of measure conversion.
  • M3 The method according to any of the preceding embodiments, wherein the preprocessing step comprises discarding at least one out-of-range value.
  • the preprocessing step comprises processing at least one diuresis data. M5.
  • the method according to any of the preceding embodiments, wherein the preprocessing step comprises processing at least one blood chemistry data.
  • M6 The method according to any of the preceding embodiments, wherein the preprocessing step comprises processing at least one physiological data.
  • the at least one artificial-intelligence assisted module comprises at least one of: first module, second module, and third module.
  • the classifying step comprises performing the classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage.
  • KDIGO Kidney Disease Improving Global Outcomes
  • the method comprises determining which of the at least one artificial-intelligence-assisted module to trigger.
  • M10 The method according to the preceding embodiment, wherein the method comprises determining which at least one artificial-intelligence-assisted module to trigger precedes the step of triggering the at least one artificial-intelligence-assisted module.
  • M11 The method according to any of the two preceding embodiments and with the features of embodiment M8, wherein determining which at least one artificial-intelligence- assisted module to trigger is based on the KDIGO stage.
  • M12 The method according to any of the preceding embodiments and with the features of embodiment M8 or M10, wherein the at least one kidney functioning status comprises the KDIGO stage. M13.
  • M17 The method according to embodiment M8, wherein the method comprises performing the classifying stage comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine. M18.
  • M20 The method according to any of the three preceding embodiments or to embodiment M8, wherein the method comprises determining a final KDIGO stage.
  • M21 The method according to any of the preceding embodiments, wherein the method comprises predicting at least one kidney disease event. M22.
  • the predicting of the least one kidney disease event is based on the at least one kidney functioning status.
  • M23 The method according to any of the two preceding embodiments, wherein the predicting of the at least one kidney disease event is performed by the at least one artificial-intelligence assisted module.
  • M24 The method according to any of the preceding embodiments, wherein the first module comprises predicting a risk of a patient of developing AKI. M25. The method according to the preceding embodiment, wherein the predicting steps is performed hourly.
  • M26 The method according to any of the preceding embodiments, wherein the method comprises predicting the risk for onset AKI within next 24 hours at a current time. M27.
  • the method comprises automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status.
  • M28 The method according to the two preceding embodiments, wherein the AKI risk level is based on the predicting of the risk for onset AKI.
  • M29 The method according to any of the preceding embodiments, wherein the method comprises predicting a risk for onset of persistent AKI at a current time.
  • the method comprises automatically generating a persistent AKI risk level, wherein a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status.
  • M31 The method according to any of the three preceding embodiments, wherein the method comprises automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status.
  • the persistent AKI risk level is based on the predicting of the risk for onset of persistent AKI.
  • M32 The method according to any of the preceding embodiments and with the features of embodiments M7 and M26, wherein the predicting of the risk for onset of AKI is performed by the first module.
  • M33 The method according to any of the preceding embodiments and with the features of embodiments M7 and M26, wherein the predicting of the risk for onset of persistent AKI is performed by the second module.
  • M34 The method according to any of the preceding embodiments, wherein the method comprises predicting a future kidney recovery trajectory. M35.
  • the probability CRRT index is based on the predicting of the future recovery trajectory.
  • M40 The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of death within the next seven days during renal replacement therapy.
  • M41 The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of death within the next seven days at the end of renal replacement therapy.
  • M42 The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of restart of renal replacement therapy within the next seven days.
  • M43 The method according to the preceding embodiment and with the features of embodiment M34, wherein the probability CRRT index is based on the predicting of the future recovery trajectory.
  • the method comprises displaying at least one input submitted by an authorized user corresponding to at the least one persistent AKI risk level at at least one time.
  • M55 The method according to any of the preceding embodiments with the features according to embodiment M49 wherein the method comprises displaying at least one input submitted by an authorized user corresponding to at the least one probability CRRT index at at least one time.
  • M56 The method according to any of the preceding embodiments, wherein the method comprises prompting at least one authorized user to input at least one data point.
  • the at least one data point comprises computer-readable input data points.
  • the at least one data point comprises at least one selectable data point comprising at least one predetermined select data point, wherein the method comprises prompting at least one authorized user to select at least one option.
  • the method comprises bidirectionally communicating with at least one server.
  • the method comprises utilizing any data of any of the preceding embodiments to train at least one algorithm.
  • the training step is performed on the at least one server.
  • the method comprises performing any of the steps of the method according to any of the preceding embodiments in an integrated intensive care unit system.
  • M63 The method according to any of the preceding method embodiments and with the features of embodiment M7, wherein the method comprises performing any of the steps of the method according to any of the preceding method embodiments by using at least one of the: first module, second module, and third module.
  • M64 The method according to any of the preceding embodiments and with the features of embodiment M59, wherein at least one of the at least one server comprises a local server.
  • M65 The method according to any of the preceding embodiments and with the features of embodiment M59, wherein at least one of the at least one server comprises a cloud server.
  • M66 The method according to any of the preceding embodiments and with the features of embodiment M59, wherein at least one of the at least one server comprises a cloud server.
  • the persistent AKI risk level comprises a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A.
  • An automation method for monitoring kidney function comprising acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, comparing the information contained in the at least one raw/preprocessed data with a standardized database and, outputting at least one output data indicative of the result of the comparison step.
  • the preprocessing step comprises performing at least one unit of measure conversion.
  • the preprocessing step comprises discarding at least one out-of-range value.
  • the preprocessing step comprises processing at least one diuresis data.
  • GFR Glomerular Ultrafiltration Rate
  • the comparing step comprises comparing the at least one GFR value with the standardized database.
  • the outputting step comprises outputting at least one drug intake instruction corresponding to the result of the comparison of the at least one GFR value with the standardized database.
  • An assessment method for conducting the furosemide stress test comprising acquiring at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, preprocessing the at least one urine output data to automatically generate at least one urine output processed data, calculating a cumulative urine output after every hour since the acquiring step, and comparing the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database.
  • D2 The assessment method according to the preceding assessment method embodiment, wherein the assessment method comprises further comprising displaying the result of the comparison step.
  • D3 The assessment method according to any of the preceding assessment method embodiments, wherein the preprocessing step comprises performing at least one unit of measure conversion.
  • D4 The assessment method according to any of the preceding assessment method embodiments wherein the comparison result comprises a probability of risk of worsening kidney function.
  • D5. The assessment method according to any of the preceding assessment method embodiments wherein the acquiring step comprises acquiring at least one data indicating a currently ended renal replacement therapy treatment and at least one corresponding time data from at least one data source.
  • D6. The assessment method according to the preceding assessment method embodiment wherein the comparison comprises evaluating the cumulative urine output 24 hours after the at least one corresponding date and time data, when the acquiring step is performed several hours after the at least one time data from at least one data source corresponding to the at least one data indicating a currently ended renal replacement therapy treatment.
  • the assessment method according to the preceding assessment method embodiment wherein the comparison result comprises a probability of risk of unsuccessful weaning from renal replacement therapy.
  • D8. The assessment method according to any of the preceding assessment method embodiments with the features of assessment method embodiments D4 wherein the assessment method comprises diagnosing a risk of worsening kidney condition.
  • D9. The assessment method according to any of the preceding assessment method embodiments with the features of assessment method embodiments D7 wherein the assessment method comprises diagnosing a risk of unsuccessful weaning from renal replacement therapy.
  • composite method embodiments will be discussed. These embodiments are abbreviated with the letter E followed by a number. Whenever reference is herein made to compound method embodiments, these embodiments are meant. E1.
  • a composite method wherein the composite method comprises the method according to any of the preceding method embodiments, the automation method according to any of the preceding automation method embodiments, the compound method according to any of the preceding compound method embodiments, the assessment method according to any of the preceding assessment method embodiments.
  • system embodiments will be discussed. These embodiments are abbreviated by the letter “S” followed by a number. When reference is herein made to a system embodiment, those embodiments are meant. S1.
  • a system for monitoring kidney function comprising an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence- assisted module, wherein the triggering component is configured to trigger the at least one artificial- intelligence-assisted module based on the at least one kidney functioning status.
  • the processing component is configured to perform at least one unit of measure conversion.
  • S3 The system according to any of the preceding system embodiments, wherein the processing component is configured to discard at least one out-of-range value.
  • the processing component is configured to process at least one diuresis data.
  • S5. The system according to any of the preceding system embodiments, wherein the processing component is configured to process at least one blood chemistry data.
  • S6. The system according to any of the preceding system embodiments, wherein the processing component is configured to process at least one physiological data.
  • S7. The system according to any of the preceding system embodiments, wherein the at least one artificial-intelligence assisted module comprises to at least one of: first module, second module, and third module. S8.
  • the classifying component is configured to perform a classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage.
  • KDIGO Kidney Disease Improving Global Outcomes
  • the system is configured to determine which of the at least one artificial-intelligence-assisted module to trigger.
  • the system is configured to determine which at least one artificial-intelligence-assisted module to trigger before prompting the triggering component to trigger the at least one artificial-intelligence- assisted module.
  • the system according to any of the preceding system embodiments wherein the system is configured to predict a risk for onset of persistent AKI at a current time.
  • S31 The system according to the preceding embodiment, wherein the system is configured to automatically generate a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status.
  • S32 The system according to the two preceding embodiments, wherein the persistent AKI risk level is based on the prediction of the risk for onset of persistent AKI.
  • S33 The system according to any of the preceding system embodiments and with the features of embodiments S7 and S27, wherein the first module is configured to predict the risk for onset of AKI.
  • S34 The system according to any of the preceding system embodiments and with the features of embodiments S7 and S27, wherein the first module is configured to predict the risk for onset of AKI.
  • system configured to classify at least one preprocessed data in at least one zone wherein further the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the start of renal replacement therapy.
  • the system is configured to classify at least one preprocessed data in at least one zone wherein the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the end of renal replacement therapy.
  • the system comprises a display device.
  • the display device is configured to display the at least one preprocessed data with respect to the at least one zone it is classified in.
  • the at least one data point comprises at least one selectable data point comprising at least one predetermined selected data point, wherein the system is configured to prompt the at least one authorized user to select at least one option.
  • S61 The system according to any of the preceding system embodiments, wherein the system is configured to bidirectionally communicate with at least one server.
  • S62. The system according to any of the preceding system embodiments, wherein the system is configured to utilize any data of any of the preceding method embodiments to train at least one algorithm.
  • S63 The system according to the preceding embodiment, wherein the training step is performed on the at least one server.
  • the probability CRRT index comprises a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A.
  • a system for monitoring kidney function comprising an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a comparing component configured to compare the information contained in the at least one raw/preprocessed data with a standardized database and, an outputting component configured to output at least one output data indicative of the result of the comparison step.
  • S78 The system according to the preceding embodiment, wherein the processing component is configured to perform at least one unit of measure conversion.
  • S79. The system according to any of preceding system embodiments S77-S78, wherein the processing component is configured to discard at least one out-of-range value.
  • S80. The system according to any of preceding system embodiments S77-S79, wherein the processing component is configured to process at least one diuresis data.
  • S81. The system according to any of preceding system embodiments S77-S80, wherein the processing component is configured to process at least one blood chemistry data.
  • S82. The system according to any of preceding system embodiments S77-S81, wherein the processing component is configured to process at least one physiological data.
  • S86. The system according to any of preceding system embodiments S77-S85, wherein the acquiring component is configured to acquire at least one serum creatinine data.
  • a system wherein the system comprises the system according to any of preceding embodiments S1-S76 and the system according to any of preceding embodiments S77-S97.
  • S99 The system according to the preceding system embodiment with the features of embodiments S30, S85 and S87 wherein the system is configured to determine the appropriate at least one drug dosage to the corresponding risk for onset persistent AKI at a current time.
  • S100 The system according to the any of the preceding compound method embodiments with the features of embodiments S35, S85, S87 and S94 wherein the system is configured to determine the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy.
  • S101 The system according to the any of the preceding compound method embodiments with the features of embodiments S35, S85, S87 and S94 wherein the system is configured to determine the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy.
  • a system for conducting the furosemide stress test comprising an acquiring component configured to acquire at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, a processing component configured to preprocess the at least one urine output data to automatically generate at least one urine output processed data, a calculating component configured to calculate a cumulative urine output after every hour, and a comparing component configured to compare the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database.
  • S102 The system according to the preceding system embodiment, wherein the system comprises a display component.
  • S108. The system according to the preceding system embodiment wherein the comparing component is configured to output at least one result comprising a probability of risk of unsuccessful weaning from renal replacement therapy.
  • S109 The system according to any of preceding system embodiments S101-S108, with the features of system embodiment S105 wherein the system is configured to diagnose a risk of worsening kidney condition. S110.
  • system embodiment S101-S109 with the features of system embodiment S108 wherein the system is configured to diagnose a risk of unsuccessful weaning from renal replacement therapy.
  • S111. A system wherein the system comprises any of or any combination of, the system according to any of preceding embodiments S1-S76, the system according to any of preceding embodiments S77-S97, the system according to any of preceding embodiments S98-S100, and the system according to any of preceding embodiments S101-S110.
  • M73 The method according to any of the preceding method embodiments, wherein the method comprises utilizing the system according to any of the preceding system embodiments to carry out the method according to any of the preceding method embodiments.
  • the method according to any of the preceding method embodiments wherein the method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the method according to any of the preceding method embodiments.
  • A22. The automation method according to any of the preceding automation method embodiments, wherein the automation method comprises utilizing the system according to any of the preceding system embodiments to carry out the automation method according to any of the preceding automation method embodiments.
  • A23. The automation method according to any of the preceding automation method embodiments, wherein the automation method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the automation method according to any of the preceding automation method embodiments.
  • the compound method according to any of the preceding compound method embodiments wherein the compound method comprises utilizing the system according to any of the preceding system embodiments to carry out the compound method according to any of the preceding compound method embodiments.
  • B5. The compound method according to any of the preceding compound method embodiments, wherein the compound method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the compound method according to any of the preceding compound method embodiments.
  • D8. The assessment method according to any of the preceding assessment method embodiments, wherein the assessment method comprises utilizing the system according to any of the preceding system embodiments to carry out the assessment method according to any of the preceding assessment method embodiments. D9.
  • the assessment method according to any of the preceding assessment method embodiments wherein the assessment method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the assessment method according to any of the preceding assessment method embodiments.
  • E2. The composite method according to any of the preceding composite method embodiments, wherein the composite method comprises utilizing the system according to any of the preceding system embodiments to carry out the composite method according to any of the preceding composite method embodiments.
  • E3. The composite method according to any of the preceding composite method embodiments, wherein the composite method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the composite method according to any of the preceding composite method embodiments. Below is a list of computer program embodiments.
  • C1 A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding method embodiments.
  • C2. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding automation method embodiments.
  • C3. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding compound method embodiments.
  • a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding assessment method embodiments.
  • C5. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding composite method embodiments.
  • T1. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding method embodiments. T2.
  • a non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding automation method embodiments.
  • T3. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding compound method embodiments.
  • T4. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding assessment method embodiments.
  • T5. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding composite method embodiments. Below is a list of use embodiments. Those will be indicated with a letter “U”.
  • U Use of the system according to any of the preceding system embodiments.
  • U2. Use according to the preceding embodiment for carrying out the method according to any of the preceding method embodiments.
  • U3. Use according to the preceding embodiment for carrying out the method according to any of the preceding automation method embodiments.
  • U4. Use according to the preceding embodiment for carrying out the method according to any of the preceding compound method embodiments.
  • U5. Use according to the preceding embodiment for carrying out the method according to any of the preceding assessment method embodiments.
  • U6 Use according to the preceding embodiment for carrying out the method according to any of the preceding composite method embodiments.
  • Fig. 1 schematically depicts a system for monitoring kidney function according to embodiments of the present invention
  • Fig. 2 schematically depicts an example of the system according to embodiment of the present invention
  • Fig. 3 schematically depicts an example of the system according to embodiments of the present invention implementing steps of the method according to embodiments of the present invention
  • Fig. 4 schematically depicts a computing device
  • Fig. 5 depicts a chart outputted by the present invention, representing the acquired measurements of clinical parameters with respect to their corresponding urgency level zones
  • Fig. 1 schematically depicts a system for monitoring kidney function according to embodiments of the present invention
  • Fig. 2 schematically depicts an example of the system according to embodiment of the present invention
  • Fig. 3 schematically depicts an example of the system according to embodiments of the present invention implementing steps of the method according to embodiments of the present invention
  • Fig. 4 schematically depicts a computing device
  • Fig. 5 depicts a chart outputted by the present invention, representing the acquired measurements of clinical parameters with
  • Fig. 1 schematically depicts a system 100 for monitoring kidney function according to embodiments of the present invention.
  • the system 100 comprises an acquiring component 150, a processing component 190, a classifying component 170, and a triggering component 180.
  • the system 100 comprises at least one artificial- intelligence-assisted module 200, such as a first module 210, a second module 220 and a third module 230.
  • Fig. 1 also depicts a “KDIGO bundle” system 300 for monitoring kidney function, comprising an acquiring component 150, a processing component 190, a comparing component 360, and an outputting component (not shown in this figure).
  • Fig. 1 furthermore depicts a system for conducting the furosemide stress test comprising an acquiring component 150, a processing component 410, a calculating component 430, and a comparing component 460.
  • acquiring component 150 may be configured to acquire at least one raw data from at least one data source (not shown).
  • the processing component 190 may be configured to at least preprocess the at least one raw data to automatically generate at least one processed data
  • the classifying component 170 may be configured to classify the at least one processed data into at least one kidney functioning status
  • the triggering component 180 may be configured to trigger at least one artificial-intelligence-assisted module 200 such at least one of the first module 210, the second module 220 and the third module 230. Additionally or alternatively, the triggering component 180 may be configured to trigger the at least one artificial- intelligence-assisted module 200 based on the at least one kidney functioning status.
  • the classifying component and the triggering component may also bidirectionally communicate between each as depicted in Fig. 1.
  • the comparing component 360 may be configured to compare the information contained in the at least one preprocessed data with a standardized database.
  • the processing component 410 may be configured to at least preprocess the at least one raw data to automatically generate at least one processed data.
  • the calculating component 430 may be configured to calculate a cumulative urine output after every hour, and the comparing component 460 may be configured to compare the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database.
  • the preprocessing component may be shared between any combination of systems presented in the invention, for example, the preprocessing component 190 is shared between system 100 and system 300.
  • a preprocessing component may also be independent from other systems such as preprocessing component 410 in system 400.
  • the system 100 is configured to perform the steps of the method as recited herein.
  • the system 300 is configured to perform the steps of the automation method as recited herein.
  • the systems 100 and 300 are configured to perform the compound method as recited herein.
  • the system 400 is configured to perform the steps if the assessment method as recited herein.
  • the systems 100, 300 and 400 are configured to perform the steps of the composite method as recited herein. It should be understood that in some embodiment, any of the component 150, 190, 170, and 180 may be at least be partially integrated in a single component. For instance, the acquiring component 150 and the processing component 190 may be integrated into a single component.
  • any of the component 150, 190, and 360 may be at least be partially integrated in a single component. It should be further be understood that in some embodiment, any of the component 150, 410, 430, and 460 may be at least be partially integrated in a single component. Moreover, it should be understood that in some embodiment, any of the any components of any of the systems cited herein may be at least be partially integrated in a single component.
  • the system 100 may perform steps of the method as exemplified in Fig. 2 Fig. 2 schematically depicts an example of the system 100 according to embodiments of the present invention. In Fig. 2, the example is depicted in relation to one artificial- intelligence-assisted module 200, in particular to the first module 210.
  • the system 100 is also configured to operate with any the at least one artificial-intelligence-assisted modules 200 according to embodiments of the present invention.
  • the system 100 may be configured as a medical software system 100.
  • the medical software system 100 may comprise a plurality of components, wherein the system 100 is configured to be deployed both on-premises in hospital servers or in the cloud for instance via a commercial cloud provider.
  • the system 100 may be configured to deploy at least one model. The deployment view may focus on aspects of the system that are important for the system to go into live operation and defines the physical environment in which the system 100 is intended to run. For instance, Fig. 2 depicts the system 100 configured as a renal platform system 100.
  • the dashed lines represent internal components of the system 100, and the arrows represent the communication direction between two items. It should be understood that the communication direction as depicted in Fig. 2 is only exemplary, and that in other embodiments the communication direction may be the opposite as depicted in Fig.2 and/or it may be bidirectional. Moreover, the system may also be deployed in two different modalities, for example, on-premise such as in locally in hospital; and on-cloud such as a cloud application running in a commercially available environment, e.g., running in Microsoft Azure environment. In one embodiment, the system may be encapsulated in a virtual machine, e.g., in a single virtual machine. In the on-premise deployment, the system may be deployed as docker container.
  • on-premise such as in locally in hospital
  • on-cloud such as a cloud application running in a commercially available environment, e.g., running in Microsoft Azure environment.
  • the system may be encapsulated in a virtual machine, e.g., in
  • Fig. 3 schematically depicts an example of the system implementing steps of method for monitoring kidney function, according to embodiments of the present invention.
  • the method for monitoring kidney function comprises four main steps, which may also be referred to as main sections, comprising: data acquisition S150, data preprocessing S190, KDIGO classification S170, and invocation of artificial-intelligence-assisted modules as needed S180.
  • the method for monitoring kidney function according to embodiments of the present invention is a computer-implemented method, which may further be executed in the medical software system.
  • the invocation S180 of the artificial-intelligence-assisted modules comprises triggering of at least one artificial-intelligence-assisted module 200, which may also be referred to as invoking of the at least one artificial-intelligence-assisted module, that is, invoking the needed artificial-intelligence pending on a kidney disease detection output.
  • the data acquisition S150 comprises the process in which the medical software system receives data from a plurality of sources, i.e., it is the step of the method for monitoring kidney function that prompts the medical software system to acquire at least one raw data from at least one source, wherein the at least one raw data comprises data of a user and related to the user’s kidney functioning.
  • the method may prompt the medical software system to receive clinical data related to a patient admitted in an intensive care unit (ICU), wherein the clinical data may be associated with time and day of measurement and/or unit of measurement.
  • the clinical data may be received, for example.
  • a hospital electronic health record system such as from medical devices, laboratory information system, data manually input by medical care personal such as nurses and/or physicians.
  • Clinical data may be received from the Hospital Electronic Health Record system, from medical devices, from laboratory information system, manually inserted by the nurses, clinicians and/or physicians.
  • the clinical data may comprise, inter alia, but not limited to: blood chemistry measurements such as albumin, blood urea nitrogen (BUN), hematocrit, hemoglobin, platelets’ count, serum creatinine, white blood cells count; physiological data such as diastolic pressure, systolic pressure, medium pressure, heart rate, urine output; patient information such as patient ID, height, weight, age, gender ethnicity, comorbidities, reason of admission to ICU; therapy data such as initial and final information of dialysis treatments.
  • the preprocessing S190 comprises transforming the at least one raw data acquired from the at least one data source into well-defined hourly-time-series data suitable to be used in subsequent steps of the method. Moreover, the processing comprises generating at least one processed data.
  • the preprocessing step may comprises applying four distinct sequential phases.
  • the preprocessing may be executed every hour taking as input all the measurements collected until a present hour. It should be understood that this step is stateless, which means that it processes every time all the data acquired by the medical software system since a patient’s admission in ICU.
  • the preprocessing may comprise tabulating input for each parameter collected, from all a plurality of preprocessing phases such as diuresis, blood chemistry, and physiological. As an example, the following table is given, wherein the first timestamp corresponds to the admission hour of the patient, while the last timestamp is the current hour when the computation started.
  • the process may be carried forward for about 12, on the other hand, for creatine value this may be performed for a longer period such as for about 96 hours.
  • the method may further be concerned with a plurality of other factors. For instance, given raw input data may potentially be subject to various problems such as insertion errors or different units of measurement.
  • the method may also be concerned with data quality analysis which may comprise analyzing input data and performing, for instance, the following steps: A first step comprising unifying the unit of measurements S192 received to the ones used by the system by performing unit of measure conversion where needed. E.g.: transforming volumetric units such liter into milliliter.
  • a second step comprising discarding out-of-range values S194 according to a pre-defined list compiled by the system yielding an output comprising cleaned data which may be used in subsequent steps of the preprocessing.
  • the preprocessing step may comprise urine output data preprocessing, comprising urine output data received by the medical software system which is assigned to a specific timestamp and within a specific hour and which may comprise different values.
  • the preprocessing step yields a transformed value, for instance, millilitres values of urine transformed into milliliters/hour/kilograms values assigned to a specific hour.
  • Such preprocessing of urine output data may be exemplified as follows: S1-1 TABLE: INPUT PARAMETERS EXAMPLE Parameter Value (ml) Timestamp Diuresis 100 YYYY-MM-DD 11:12:04 Diuresis 300 YYYY-MM-DD 11:32:04 Diuresis 0
  • Step 4 Repeat Step 1 S1-1 ALGORITHM: URINE OUTPUT MISSING VALUES Input: S1-Algorithm input and Step 2 of S1-Algorithm Output: Assign to the row of S1-2 Table where Timestamp is equal to current_hour_X a value Step 1: Take the previous value assigned to the current_hour_X-1 in S1-2 Step 2: T Ifa cboluenter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S1-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S1-2 Table.
  • Step 3 Go to Step 1 of S1 Algorithm S1-2 ALGORITHM: URINE OUTPUT CALCULATE HOURLY VALUE Input: S1-Algorithm input and Step 2 of S1-Algorithm Output: Assign to the row of S1-2 Table where Timestamp is equal to current_hour_X a value
  • Step 1 Insert in the result of Step 2 of S1-Algorithm the first measure preceding the (current_hour_X-1):00:00 from the S1-1 Table.
  • Step 2 Calculates the time-gap between the values selected in Step 1.
  • Step 3 For each gap obtained in Step 2 multiply the value of ml to the gap expressed in minutes and sum all these values.
  • the preprocessing S190 may also comprise preprocessing the at least one raw data comprising blood chemistry data which are assigned to a specific timestamp and within a specific hour, which may comprise several different values.
  • the preprocessing step yields a selected singular value for each blood chemistry parameter collected, to a well-defined hour.
  • the preprocessing of blood chemistry S196B data may be exemplified as follows: S2-2 TABLE: OUTPUT PARAMETERS EXAMPLE Parameter Value Timestamp Creatinine XX YYYY-MM-DD 11:00:00 Creatinine XX YYYY-MM-DD 12:00:00
  • Step 3 If the result of Step 2 is empty go for S2-1 Algorithm. Otherwise go for S2-2 Algorithm
  • Step 4 Repeat Step 2 for each parameter grouped S2 –1 ALGORITHM: BLOOD CHEMISTRY MISSING VALUES Input: Input of Step 2 of the S2 Algorithm and current_hour_X Output: Assign to the row of S2-2 Table where Timestamp is equal to current_hour_X a value
  • Step 1 Select the previous value of current_hour_X-1 from the S2-2 Table.
  • Step 2 If counter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S2-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S2-2 Table.
  • Step 3 Go to Step 2 of S2-Algorithm S2 –2 ALGORITHM: BLOOD CHEMISTRY HOURLY VALUE Input: Input of Step 2 of the S2 Algorithm and current_hour_X Output: Assign to the row of S2-2 Table where Timestamp is equal to current_hour_X a value
  • Step 1 From the input of Step 2 of the S2 Algorihtm, the last value (meaning the one with maximum timestamp) will be selected and assigned to current_hour_X hour. Reset counter variable.
  • the preprocessing S190 may also comprise preprocessing the at least one raw data comprising physiological data from an Electronic Health Record system such as from a database of clinical data of a hospital, which are assigned a specific timestamp and within a specific hour, which may comprise several different values.
  • the preprocessing step S190 yields a selected singular value for each physiological parameter collected to a well-defined hour.
  • the preprocessing S190 of physiological data may be exemplified as follows: S3-1 TABLE: INPUT PARAMETERS EXAMPLE Parameter Value Timestamp Heart Rate 80 YYYY-MM-DD 11:12:04 Heart Rate 120 YYYY-MM-DD 11:32:04 Heart Rate 110 YYYY-MM-DD 11:52:04 Heart Rate 70 YYYY-MM-DD 12:12:04 S3-2 TABLE: OUTPUT PARAMETERS EXAMPLE Parameter Value Timestamp Heart Rate XX YYYY-MM-DD 11:00:00 Heart Rate XX YYYY-MM-DD 12:00:00 S3 ALGORITHM: PHYSIOLOGICAL PROCESSING MAIN ROUTINE Input: List of raw physiological measurements as S3-1 Table ordered by Timestamp key Output: Uniform time series of the physiological parameters as S3-2 Table Step 1: Group the S3-1 Table using Parameter column as key Step 2: For each timestamp T as current_hour_X in
  • Step 3 If the result of Step 2 is empty go for S3-1 Algorithm. Otherwise go for S3-2 Algorithm.
  • Step 4 Repeat Step 2 for each parameter grouped S3 –1 ALGORITHM: PHYSIOLOGICAL MISSING VALUES Input: Input of Step 2 of the S3 Algorithm and current_hour_X Output: Assign to the row of S3-2 Table where Timestamp is equal to current_hour_X a value
  • Step 1 Select the previous value of current_hour_X-1 from the S3-2 Table.
  • Step 2 If counter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S3-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S3-2 Table.
  • Step 3 Go to Step 2 of S3-Algorithm S3 –2 ALGORITHM: PHYSIOLOGICAL HOURLY VALUE Input: Input of Step 2 of the S3 Algorithm and current_hour_X Output: Assign to the row of S3-2 Table where Timestamp is equal to current_hour_X a value
  • Step 1 From the input of Step 2 of the S3 Algorithm, calculate the average value. The result will be assigned to current_hour_X hour. Reset counter variable.
  • Step 2 Go to Step 2 of S3 Algorithm
  • the KDIGO classification comprises classifying the processed data into a plurality of status of kidney diseases of a user based on KDIGO guidelines.
  • the Kidney Disease Detection process calculates the AKI staging of the patient by applying the KDIGO guidelines or the reason for admission information of the patient at the present hour of the patient.
  • the outcome of the preprocessing step S190 serves as input of KDIGO classification.
  • the Kidney Disease Detection process is to assign only for the current hour the KIDGO Stage that can have the following values: 0; 1; 2; 3; 4 (Persistent AKI). If the reason for admission to the Intensive Care Unit of the patient includes an Acute Kidney Injury disease, then the Final KDIGO Stage will be 2.
  • the final AKI Stage for the patient is calculated following this table: KDIGO Diuresis KDIGO Creatinine Stage Final KDIGO Stage* S Nt.Aa.ge N.A. N.A. N.A. Creatinine Stage Creatinine Stage Urine Output Stage N.A Urine Output Stage Urine Output Stage Creatinine Stage Max(Urine Output Stage, Creatinine Stage) S4 ALGORITHM: KIDNEY DISEASE DETECTION Input: Output from Preprocessing phase Output: Determine the kidney disease status of the patient Step 1: Calculate KDIGO Stage for diuresis by applying the guidelines.
  • Step 2 Calculate KDIGO Stage for creatinine by applying the guidelines
  • Step 3 Determine the persistency of the KDIGO
  • Step 4 Determine the final KDIGO Stage
  • Fig. 3 also depicts a kidney disease event prediction performed by the method for monitoring kidney disease according to embodiments of the present invention.
  • the method comprises triggering at least one artificial-intelligence-assisted module which may comprises at least one of: First module, the second module, and Third module.
  • First module may output a risk for onset of AKI (stage 2/3 as defined by KDIGO guidelines) within the next 24 hours, at the current time.
  • the first module may also generate a risk level that indicates a severity of a patient’s status (that is, how bad the status of the patient is), and an explanation of the outcome.
  • such an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome.
  • the first module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190.
  • the first module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/ FiO2); lactates; age; gender; weight.
  • clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of
  • the first module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time
  • the first module may also comprise at least one artificial-intelligence- assisted module, which also be referred to as AKI module.
  • AKI module calculates features are sent in input to a machine-learning model trained to predict the risk for onset of AKI (stage 2/3 as defined by KDIGO guidelines) within the next 24 hours.
  • the AKIRA AI module may be applied to the input feature, for example, only if urine output and creatinine values are present.
  • the AKI module may be based on a XGBoost algorithm which is based on a set of decision tree learning algorithms that uses a gradient boosting framework.
  • the output of the model may be a number between 0 and 1, wherein said output may be multiplied by 100 to represent the probability of developing AKI stage 2 or 3 in the following 24 hours.
  • the AKI module may be based on a plurality of different algorithm architectures, such as: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network.
  • the first module may also generate a risk level which may also be referred to as AKIRA risk level.
  • AKI module may compare its output with a specified threshold, wherein the method may comprise assigning and defining a new risk level variable according to these rules: Score Risk level N.A. N.A.
  • the first module may also automatically generate a list of features, variables, with their weights (expressed in terms of %), that most influenced the output of the AKI module.
  • the first module may execute at least one computer- implemented method comprising at least one of: SHapley Additive exPlanations; Impurity- based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation.
  • the second module may automatically output a risk for onset of Persistent AKI (as defined by KDIGO guidelines).
  • the second module may also generate a risk level that a severity of a patient’s status indicates (that is, how bad the status of the patient is) and an explanation of the outcome.
  • an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome.
  • the second module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190 calculated.
  • the second module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/FiO2); lactates; age; gender; weight.
  • clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of
  • the second module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time windows of variable length such as from 3 h to 72 h preceding the current hour.
  • the second module may also comprise at least one artificial-intelligence-assisted module, which also be referred to as Persistent AKI module. Calculated features are sent in input to a machine-learning model trained to predict the risk for onset of Persistent AKI. Persistent AKI module may be applied to the input feature, for example, only if urine output and creatinine values are present.
  • Persistent AKI module may be based on a XGBoost algorithm that is based on a set of decision tree learning algorithms that uses a gradient boosting framework. Model. The output of the model is a number between 0 and 1, and it is multiplied by 100 to represent the probability of developing a Persistent form of AKI during the Intensive Care Unit stay.
  • Persistent AKI module may be based on different algorithm architectures, inter alia, but not limited to: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network; Generate PERSEA Risk level.
  • the second module may execute at least one computer-implemented method comprising at least one of: SHapley Additive exPlanations; Impurity-based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation.
  • the third module may automatically output a readiness level of a patient to stop a treatment of continuous renal replacement therapy in intensive care units expressed with values between 0 and 100.
  • the third module may also generate a weaning- readiness level that indicates how high is the weaning- readiness of the patient and the explanations of the result.
  • such an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome.
  • the third module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190 calculated.
  • the second module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/ FiO2); lactates; age; gender; weight.
  • BUN blood urea nitrogen
  • MAP median arterial pressure
  • PaO2/ FiO2 fraction inspired oxygen and arterial oxygen partial pressure
  • the third module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time windows of variable length such as from 3 h to 240 h.
  • the third module may also comprise at least one artificial-intelligence- assisted module, which also be referred to as CRRT module.
  • CRRT module Calculated features are sent in input to a machine-learning model trained to predict the risk for onset of Persistent AKI (stage 2/3 as defined by KDIGO guidelines).
  • CRRT module may be applied to the input feature, for example, only if urine output and creatinine values are present.
  • CRRT model may be based on a XGBoost algorithm that is based on a set of decision tree learning algorithms that uses a gradient boosting framework. Model. The output of the model is a number between 0 and 1, and it is multiplied by 100 to represent the readiness of a patient to stop a treatment of continuous renal replacement therapy in intensive care units.
  • CRRT module may be based on different algorithm architectures, inter alia, but not limited to: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network; Generate CRRT Risk level.
  • the third module may execute at least one computer- implemented method comprising at least one of: SHapley Additive exPlanations; Impurity- based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation.
  • Fig. 4 depicts a schematic of a computing device 1000.
  • the computing device 1000 may comprise a computing unit 35, a first data storage unit 30A, a second data storage unit 30B and a third data storage unit 30C.
  • the computing device 1000 can be a single computing device or an assembly of computing devices.
  • the computing device 1000 can be locally arranged or remotely, such as a cloud solution.
  • different data can be stored, such as the AKI related data on the first data storage 30A, the time stamped data and/or event code data and/or phenotypic data on the second data storage 30B and privacy sensitive data, such as the connection of the before-mentioned data to an individual, on the thirds data storage 30C.
  • Additional data storage can be also provided and/or the ones mentioned before can be combined at least in part.
  • Another data storage (not shown) can comprise data specifying for instance, clinical parameter data. This data can also be provided on one or more of the before-mentioned data storages.
  • the computing unit 35 can access the first data storage unit 30A, the second data storage unit 30B and the third data storage unit 30C through the internal communication channel 160, which can comprise a bus connection 160.
  • the computing unit 30 may be single processor or a plurality of processors, and may be, but not limited to, a CPU (central processing unit), GPU (graphical processing unit), DSP (digital signal processor), APU (accelerator processing unit), ASIC (application-specific integrated circuit), ASIP (application-specific instruction-set processor) or FPGA (field programable gate array).
  • the first data storage unit 30A may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM Parameter RAM
  • the second data storage unit 30B may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • MRAM Magneto-resistive RAM
  • F-RAM Ferroelectric RAM
  • P-RAM Parameter RAM
  • the third data storage unit 30C may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM) can also be part of the same memory.
  • the third data storage unit 30C can be a secure memory device 30C, such as, a self-encrypted memory, hardware-based full disk encryption memory and the like which can automatically encrypt all of the stored data.
  • the data can be decrypted from the memory component only upon successful authentication of the party requiring to access the third data storage unit 30C, wherein the party can be a user, computing device, processing unit and the like.
  • the third data storage unit 30C can only be connected to the computing unit 35 and the computing unit 35 can be configured to never output the data received from the third data storage unit 30C. This can ensure a secure storing and handling of the encryption key (i.e., private key) stored in the third data storage unit 30C.
  • the second data storage unit 30B may not be provided but instead the computing device 1000 can be configured to receive a corresponding encrypted share from the database 60.
  • the computing device 1000 may comprise the second data storage unit 30B and can be configured to receive a corresponding encrypted share from the database 60.
  • the computing device 1000 may comprise a further memory component 140 which may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • the memory component 140 may also be connected with the other components of the computing device 1000 (such as the computing component 35) through the internal communication channel 160. Further the computing device 1000 may comprise an external communication component 130.
  • the external communication component 130 can be configured to facilitate sending and/or receiving data to/from an external device (e.g., backup device 10, recovery device 20, database 60).
  • the external communication component 130 may comprise an antenna (e.g., WIFI antenna, NFC antenna, 2G/3G/4G/5G antenna and the like), USB port/plug, LAN port/plug, contact pads offering electrical connectivity and the like.
  • the external communication component 130 can send and/or receive data based on a communication protocol which can comprise instructions for sending and/or receiving data. Said instructions can be stored in the memory component 140 and can be executed by the computing unit 35 and/or external communication component 130.
  • the external communication component 130 can be connected to the internal communication component 160.
  • data received by the external communication component 130 can be provided to the memory component 140, computing unit 35, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C.
  • data stored on the memory component 140, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C and/or data generated by the commuting unit 35 can be provided to the external communication component 130 for being transmitted to an external device.
  • the computing device 1000 may comprise an input user interface 110 which can allow the user of the computing device 1000 to provide at least one input (e.g., instruction) to the computing device 100.
  • the input user interface 110 may comprise a button, keyboard, trackpad, mouse, touchscreen, joystick and the like.
  • the computing device 1000 may comprise an output user interface 120 which can allow the computing device 1000 to provide indications to the user.
  • the output user interface 110 may be a LED, a display, a speaker and the like.
  • the output and the input user interface 100 may also be connected through the internal communication component 160 with the internal component of the device 100.
  • the processor may be singular or plural, and may be, but not limited to, a CPU, GPU, DSP, APU, or FPGA.
  • the memory may be singular or plural, and may be, but not limited to, being volatile or non-volatile, such an SDRAM, DRAM, SRAM, Flash Memory, MRAM, F-RAM, or P-RAM.
  • the data processing device can comprise means of data processing, such as, processor units, hardware accelerators and/or microcontrollers.
  • the data processing device 20 can comprise memory components, such as, main memory (e.g., RAM), cache memory (e.g., SRAM) and/or secondary memory (e.g., HDD, SDD).
  • the data processing device can comprise busses configured to facilitate data exchange between components of the data processing device, such as, the communication between the memory components and the processing components.
  • the data processing device can comprise network interface cards that can be configured to connect the data processing device to a network, such as, to the Internet.
  • the data processing device can comprise user interfaces, such as: - output user interface, such as: o screens or monitors configured to display visual data (e.g., displaying graphical user interfaces of railway network status),
  • Fig. 4 depicts a schematic of a computing device 1000.
  • the computing device 1000 may comprise a computing unit 35, a first data storage unit 30A, a second data storage unit 30B and a third data storage unit 30C.
  • the computing device 1000 can be a single computing device or an assembly of computing devices.
  • the computing device 1000 can be locally arranged or remotely, such as a cloud solution.
  • the different data can be stored, such as the genetic data on the first data storage 30A, the time stamped data and/or event code data and/or phenotypic data on the second data storage 30B and privacy sensitive data, such as the connection of the before-mentioned data to an individual, on the thirds data storage 30C.
  • Additional data storage can be also provided and/or the ones mentioned before can be combined at least in part.
  • Another data storage (not shown) can comprise data specifying for instance, air temperature, rail temperature, position of blades, model of point machine, position of point machine and/or further railway network related information. This data can also be provided on one or more of the before-mentioned data storages.
  • the computing unit 35 can access the first data storage unit 30A, the second data storage unit 30B and the third data storage unit 30C through the internal communication channel 160, which can comprise a bus connection 160.
  • the computing unit 30 may be single processor or a plurality of processors, and may be, but not limited to, a CPU (central processing unit), GPU (graphical processing unit), DSP (digital signal processor), APU (accelerator processing unit), ASIC (application-specific integrated circuit), ASIP (application-specific instruction-set processor) or FPGA (field programable gate array).
  • the first data storage unit 30A may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM Parameter RAM
  • the second data storage unit 30B may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • MRAM Magneto-resistive RAM
  • F-RAM Ferroelectric RAM
  • P-RAM Parameter RAM
  • the third data storage unit 30C may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • RAM random-access memory
  • DRAM Dynamic RAM
  • SDRAM Synchronous Dynamic RAM
  • SRAM static RAM
  • Flash Memory Flash Memory
  • Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM) can also be part of the same memory.
  • the third data storage unit 30C can be a secure memory device 30C, such as, a self-encrypted memory, hardware-based full disk encryption memory and the like which can automatically encrypt all of the stored data.
  • the data can be decrypted from the memory component only upon successful authentication of the party requiring to access the third data storage unit 30C, wherein the party can be a user, computing device, processing unit and the like.
  • the third data storage unit 30C can only be connected to the computing unit 35 and the computing unit 35 can be configured to never output the data received from the third data storage unit 30C. This can ensure a secure storing and handling of the encryption key (i.e., private key) stored in the third data storage unit 30C.
  • the second data storage unit 30B may not be provided but instead the computing device 1000 can be configured to receive a corresponding encrypted share from the database 60.
  • the computing device 1000 may comprise the second data storage unit 30B and can be configured to receive a corresponding encrypted share from the database 60.
  • the computing device 1000 may comprise a further memory component 140 which may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM).
  • the memory component 140 may also be connected with the other components of the computing device 1000 (such as the computing component 35) through the internal communication channel 160. Further the computing device 1000 may comprise an external communication component 130.
  • the external communication component 130 can be configured to facilitate sending and/or receiving data to/from an external device (e.g., backup device 10, recovery device 20, database 60).
  • the external communication component 130 may comprise an antenna (e.g., WIFI antenna, NFC antenna, 2G/3G/4G/5G antenna and the like), USB port/plug, LAN port/plug, contact pads offering electrical connectivity and the like.
  • the external communication component 130 can send and/or receive data based on a communication protocol which can comprise instructions for sending and/or receiving data. Said instructions can be stored in the memory component 140 and can be executed by the computing unit 35 and/or external communication component 130.
  • the external communication component 130 can be connected to the internal communication component 160.
  • data received by the external communication component 130 can be provided to the memory component 140, computing unit 35, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C.
  • data stored on the memory component 140, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C and/or data generated by the commuting unit 35 can be provided to the external communication component 130 for being transmitted to an external device.
  • the computing device 1000 may comprise an input user interface 110 which can allow the user of the computing device 1000 to provide at least one input (e.g., instruction) to the computing device 100.
  • the input user interface 110 may comprise a button, keyboard, trackpad, mouse, touchscreen, joystick and the like.
  • the computing device 1000 may comprise an output user interface 120 which can allow the computing device 1000 to provide indications to the user.
  • the output user interface 110 may be a LED, a display, a speaker and the like.
  • the output and the input user interface 100 may also be connected through the internal communication component 160 with the internal component of the device 100.
  • the processor may be singular or plural, and may be, but not limited to, a CPU, GPU, DSP, APU, or FPGA.
  • the memory may be singular or plural, and may be, but not limited to, being volatile or non-volatile, such an SDRAM, DRAM, SRAM, Flash Memory, MRAM, F-RAM, or P-RAM.
  • the data processing device can comprise means of data processing, such as, processor units, hardware accelerators and/or microcontrollers.
  • the data processing device 20 can comprise memory components, such as, main memory (e.g., RAM), cache memory (e.g., SRAM) and/or secondary memory (e.g., HDD, SDD).
  • the data processing device can comprise busses configured to facilitate data exchange between components of the data processing device, such as, the communication between the memory components and the processing components.
  • the data processing device can comprise network interface cards that can be configured to connect the data processing device to a network, such as, to the Internet.
  • the data processing device can comprise user interfaces, such as: ⁇ output user interface, such as: o screens or monitors configured to display visual data (e.g., displaying graphical user interfaces of railway network status), o speakers configured to communicate audio data (e.g., playing audio data to the user), ⁇ input user interface, such as: o camera configured to capture visual data (e.g., capturing images and/or videos of the user), o microphone configured to capture audio data (e.g., recording audio from the user), o keyboard configured to allow the insertion of text and/or other keyboard commands (e.g., allowing the user to enter text data and/or other keyboard commands by having the user type on the keyboard) and/or trackpad, mouse, touchscreen, joystick – configured to facilitate the navigation through different graphical user interfaces of the questionnaire.
  • ⁇ output user interface such as: o screens or monitors configured to display visual data (e.g., displaying graphical user interfaces of railway network status), o speakers configured to communicate audio data (e.g.
  • the data processing device can be a processing unit configured to carry out instructions of a program.
  • the data processing device can be a system-on-chip comprising processing units, memory components and busses.
  • the data processing device can be a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer.
  • the data processing device can be a server, either local and/or remote.
  • the data processing device can be a processing unit or a system-on-chip that can be interfaced with a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer and/or user interface (such as the upper-mentioned user interfaces).
  • the data processing device can be a processing unit configured to carry out instructions of a program.
  • the data processing device can be a system-on-chip comprising processing units, memory components and busses.
  • the data processing device can be a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer.
  • the data processing device can be a server, either local and/or remote.
  • the data processing device can be a processing unit or a system-on-chip that can be interfaced with a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer and/or user interface (such as the upper-mentioned user interfaces).
  • Fig. 5 depicts a chart outputted by the present invention, representing the acquired measurements of clinical parameters with respect to their corresponding urgency level zones. In simple words, the measurements acquired by the invention is presented in a chart wherein the measurements are also presented in tandem with the “zone” in which it is categorized.
  • these zones can represent the urgency level of Renal Replacement Therapy (RRT in Figure. 5) such as No RRT indication, RRT indication and Urgent RRT indication. It should be understood that in certain embodiments, these zones are not related to an RRT urgency level, but any urgency level that can correspond to the measurements taken by the invention, wherein said urgency levels may be traced back to the standardized database.
  • Fig. 6 depicts chart outputted by the present invention, representing the scores calculated by the system as well as a note 500 inputted into the system by an authorized user, with respect to time. In simple terms, an authorized user may input at least one note 500 at a certain time and date relative to the score calculated by the system at said time and date. Said note may be displayed with the scores calculated with respect to time to at least one authorized user.
  • step (A) precedes step (B)
  • step (A) is performed (at least partly) simultaneously with step (B) or that step (B) precedes step (A).
  • step (X) is said to precede another step (Z)
  • this does not imply that there is no step between steps (X) and (Z).
  • step (X) preceding step (Z) encompasses the situation that step (X) is performed directly before step (Z), but also the situation that (X) is performed before one or more steps (Y1), ..., followed by step (Z).
  • step (X) is performed directly before step (Z)
  • step (Y1) is performed before one or more steps (Y1), ..., followed by step (Z).
  • step (Z) is performed before one or more steps (Y1), ..., followed by step (Z).
  • Corresponding considerations apply when terms like “after” or “before” are used.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Surgery (AREA)
  • Urology & Nephrology (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The present invention relates to a method for monitoring kidney function, the method comprising: acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status, and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module is based on the at least one kidney functioning status Furthermore, the present invention relates to a system for monitoring kidney function, the method comprising: an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence-assisted module, wherein the triggering component is configured to trigger the at least one artificial-intelligence-assisted module based on the at least one kidney functioning status.

Description

System and method for detection and prediction of kidney disease events Field The invention lies in the field of monitoring health status and particularly in the field of monitoring renal health status of humans. The goal of the present invention is to provide a system and method for monitoring the renal health status of humans. More particularly, the present invention relates to a system, a method performed in such a system and corresponding use of a system for detection and prediction of kidney disease events. Introduction A sudden loss of kidney function is known as Acute Kidney Injury (AKI) and it is a major worldwide concern due to the associated high in-hospital incidence, mortality, social costs and disability. Timely intervention in diagnosis and treatment may therefore be beneficial. Currently, clinical approach adopted by physicians to limit the AKI onset in Intensive Care Units (ICU) consists mainly in the prevention of the disease, by adopting measures able to guarantee appropriate volume control, kidney perfusion, sepsis prevention and nephrotoxic drug tailoring. Early identification of patients who may benefit from such preventive measures is key to enable effective prevention of AKI onset. One approach consists of the use of chemical in-vitro biomarkers. Biomarkers have the limitation of being time-consuming, not specific and discrete in time. These limitations have slowed wide adoption in the clinic. A different approach consists of the use of algorithms that can predict AKI onset. Several researches developed algorithms by the use of big data analysis and Artificial Intelligence (AI) instruments, but until now the presented studies are heterogeneous and many of them are not externally validated or contain several biases. CN 110 914 915 A relates to a medical treatment machine, such as a home dialysis machine, which may receive prescription parameters that define parameters of a medical treatment to be administered to a patient. The clinician enters the medical prescription into a Clinical Information System (CIS) that invokes a system to evaluate the compatibility of the entered prescription by transmitting the prescription parameters to a server that has access to a database of medical devices and their operating parameters. US 2022 038 3998 A1 relates to a computer implemented method comprises monitoring live feedback received over a course of care of a patient, wherein the live feedback comprises physiological information regarding a physiological state of the patient. The method further comprises employing AI to identify, based on the live feedback information, an event or condition associated with the course of care of the patient that warrants clinical attention or a clinical response. US 2022 040 6437 A1 relates to a method and a system for determining and providing renal therapy, wherein the method may include a modality analysis. The method may include, via a processor of a computing device: determining a modality analysis model configured to determine a modality status of a patient, the modality status configured to indicate a probability of a transition from a first modality to a second modality, and generating the modality status via the modality analysis model using patient information associated with the patient. Other embodiments are described EP 3918610 A1 relates to a monitoring system, and the related monitoring and predicting methods of diuresis for the calculation of the risk of onset of renal failure of a patient, including a device comprising a first algorithm for recording, storing, comparing and processing the measurements of the urine container and a second algorithm for predicting the future measurements of the urine container and the level of kidney failure risk associated with them. US 20200057076 A1 relates to the use of p21 biomarker in the evaluation of whether a patient is suffering from kidney injury or failure, and can be used in methods of treating kidney injury or failure by determining the appropriateness of one or more of initiating renal replacement therapy, withdrawing delivery of compounds that are known to be damaging to the kidney, delaying or avoiding procedures that are known to be damaging to the kidney, and modifying diuretic administration. US 2018 011 0455 A1 relates to a system and urine sensing devices for and method of monitoring kidney function, and in particular, a kidney function monitoring system provides a portable urine monitor system that can provide real-time and continuous feedback about urine output and/or level of at least one urinary component, wherein the portable monitoring device comprises an adaptive and modular self-learning algorithm for the real- time assessment of AKI risk. US 20220390467 A1 relates to a method for determining whether a sepsis patient is likely to develop severe sepsis associated acute kidney injury (SA-AKI) using a combination of clinical data and biomarker data obtained during the first 24 hours following the subject's diagnosis with sepsis. Summary In light of the above, it is therefore an object of the present invention to overcome or at least to alleviate the shortcomings and disadvantages of the prior art. More particularly, it is an object of the present invention to provide a more accurate and less prone to failure method and a corresponding system for detection and prediction of kidney disease events. These objects are met by the present invention. In a first aspect, the invention relates to a method for monitoring kidney function, the method comprising: acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status; and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module may be based on the at least one kidney functioning status. In one embodiment, the preprocessing step may comprise performing at least one unit of measure conversion. In another embodiment, the preprocessing step may comprise discarding at least one out-of-range value. In a further embodiment, the preprocessing step may comprise processing at least one diuresis data. Additionally or alternatively, the preprocessing step may comprise processing at least one blood chemistry data. Moreover, the preprocessing step may comprise processing at least one physiological data. Moreover, the at least one artificial-intelligence assisted module may comprise at least one of: a first module, a second module, and a third module. The first module may also be referred to as AKI predicting module or simply as AKI module. The second module may also be referred to as persistent AKI predicting module or simply as persistent AKI module. The third module may also be referred to continuous renal replacement therapy monitoring module or simply as CRRT module. In one embodiment, the classifying step may comprise performing the classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage. Further, the method may comprise determining which of the at least one artificial- intelligence-assisted module to trigger. The method may comprise determining which at least one artificial-intelligence-assisted module to trigger precedes the step of triggering the at least one artificial-intelligence-assisted module. In one embodiment, determining which at least one artificial-intelligence-assisted module to trigger may be based on the KDIGO stage. Moreover, the at least one kidney functioning status may comprise the KDIGO stage. When the least one kidney functioning status may comprise data indicating a non-applicable stage, no artificial-intelligence-assisted module may be triggered. When the least one kidney functioning status may comprise data indicating a KDIGO stage 0 or 1, the first module may be triggered. When the least one kidney functioning status may comprise data indicating a KDIGO stage 2 or 3, the second module may be triggered. When the least one kidney functioning status may comprise data indicating a currently started dialysis treatment, the third module may be triggered. Furthermore, the method may comprise performing the classifying stage comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine. The classifying step may comprise determining an acute kidney injury (AKI). The method may comprise determining a persistency of the AKI. Further, the method may comprise determining a final KDIGO stage. Moreover, the method may comprise predicting at least one kidney disease event. The predicting of the least one kidney disease event may be based on the at least one kidney functioning status. The predicting of the at least one kidney disease event may be performed by the at least one artificial-intelligence assisted module. In a further embodiment, the method may comprise predicting a risk of a patient of developing AKI. The predicting steps may be performed hourly. The method may comprise predicting the risk for onset AKI within next 24 hours at a current time. The Additionally, method may comprise automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status. The AKI risk level may be based on the predicting of the risk for onset AKI. The method may comprise predicting a risk for onset of persistent AKI at a current time. In another embodiment, the method may comprise automatically generating a persistent AKI risk level, wherein a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status. The persistent AKI risk level may be based on the predicting of the risk for onset of persistent AKI. Moreover, the predicting of the risk for onset of AKI may be performed by the first module. The predicting of the risk for onset of persistent AKI may be performed by the second module. Further, the method may comprise predicting a future kidney recovery trajectory. The predicting of the future kidney recovery trajectory may be performed by the third module. The method may comprise outputting at least one decision-supporting-data based on the predicting of the future kidney recovery trajectory. The method may comprise generating a probability for stopping a continuous renal replacement therapy (CRRT) which may also be referred to as CRRT index comprising a CRRT risk level. The generating of the probability CRRT index may be performed by the third module. The probability CRRT index may be based on the predicting of the future recovery trajectory. In simple terms, the third module may calculate the CRRT index, which is a score indicating the likelihood of a current time being the optimal timing to stop the CRRT treatment. Hence, the CRRT module may be seen as a proxy of the fact that the kidney has recovered its function. Moreover, CRRT index trajectory over time can be considered the future kidney recovery trajectory. In a further embodiment, the method may comprise generating at least one of a probability of risk of death within the next seven days during renal replacement therapy, a probability of risk of death within the next seven days at the end of renal replacement therapy, a probability of risk of restart of renal replacement therapy within the next seven days, and an optimal time to stop the renal replacement therapy. Moreover, the method may comprise classifying at least one preprocessed data relating to predicting a risk for onset of persistent AKI, or a future recovery trajectory in at least one zone. The at least one zone is delimited according to at least one range of values. These values are defined, with respect to a standardized database, to assess the urgency needed for the start and/or the end of renal replacement therapy. Furthermore, the method comprises displaying these classifications. The method also comprises displaying at least one AKI risk level, at least one persistent AKI risk level and/or at least one probability CRRT index, in function of time. In one embodiment, the method may comprise storing and displaying at least one input submitted by an authorized user corresponding to at the least one AKI risk level at, at the least one persistent AKI risk level, and/or the at least one probability CRRT index at least one time. That input may comprise preferably a note, a message… that may be related to the data or the time the input is corresponding to. In one embodiment, the method may comprise prompting at least one authorized user to input at least one data point. The at least one data point may comprise computer-readable input data points. The at least one data point may comprise at least one selectable data point comprising at least one predetermined select data point, wherein the method may comprise prompting at least one authorized user to select at least one option. The method may comprise bidirectionally communicating with at least one server. The method may comprise utilizing any data as recited herein to train at least one algorithm. The training step may be performed on the at least one server. Further, the method may comprise performing the method as recited herein in an integrated intensive care unit system. Moreover, the method may comprise performing the method as recited herein by using at least one of the: first module, the second module, and third module. In one embodiment, at least one of the at least one server may comprise a local server. In another embodiment, at least one of the at least one server may comprise a cloud server. The Additionally, AKI risk level may comprise a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) Additionally, persistent AKI risk level may comprise a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) The probability CRRT index may comprise a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) In a second aspect, the invention relates to a system for monitoring kidney function, the system comprising: an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence-assisted module, wherein the triggering component may be configured to trigger the at least one artificial-intelligence-assisted module based on the at least one kidney functioning status. In one embodiment, the processing component may be configured to perform at least one unit of measure conversion. In another embodiment, the processing component may be configured to discard at least one out-of-range value. Further, the processing component may be configured to process at least one diuresis data. Moreover, the processing component may be configured to process at least one blood chemistry data. In a further embodiment, the processing component may be configured to process at least one physiological data. The at least one artificial-intelligence assisted module may comprise to at least one of: first module, the second module, and third module. In one embodiment, the classifying component may be configured to perform a classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage. The system may be configured to determine which of the at least one artificial-intelligence- assisted module to trigger. Further, the system may be configured to determine which at least one artificial-intelligence-assisted module to trigger before prompting the triggering component to trigger the at least one artificial-intelligence-assisted module. Moreover, the system may be configured to determine which at least one artificial-intelligence-assisted module to trigger based on the KDIGO stage. The at least one kidney functioning status may comprise the KDIGO stage. The system may be configured to trigger the at least one artificial-intelligence-assisted module based on a value of the KDIGO stage. When the least one kidney functioning status may comprise data indicating a value of the KDIGO stage as a non-applicable stage, the system may be configured to trigger none artificial-intelligence- assisted module. When the least one kidney functioning status may comprise data indicating the value of the KDIGO stage as 0 or 1, the system may be configured to trigger the first module. When the least one kidney functioning status may comprise data indicating the value of the KDIGO stage as 2 or 3, the system may be configured to trigger the second module. When the least one kidney functioning status may comprise data indicating the value of the KDIGO stage as indicating that a currently started dialysis treatment, the system may be configured to trigger the third module. The system may be configured to perform the classifying step comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine. Moreover, the classifying component may be configured to determine an acute kidney injury (AKI). The system may be configured to determine a persistency of the AKI. The system may be configured to determine a final KDIGO stage. Further, the system may be configured to predict at least one kidney disease event. Additionally or alternatively, the system may be configured to predict the at least one kidney disease event based on the at least one kidney functioning status. The system may be configured to predict the at least one kidney disease event by means of the at least one artificial-intelligence assisted module. The first module may be configured to predict a risk of a patient of developing AKI. The first module may be configured to predict the risk of a patient of developing AKI on an hourly basis. The system may be configured to predict a risk for onset AKI within next 24 hours at a current time. Further, the system may be configured to automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status. The AKI risk level may be based on the prediction of the risk for onset AKI. In a further embodiment, the system may be configured to predict a risk for onset of persistent AKI at a current time. The system may be configured to automatically generate a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status. The persistent AKI risk level may be based on the prediction of the risk for onset of persistent AKI. The first module may be configured to predict the risk for onset of AKI. The second module may be configured to predict the risk for onset of persistent AKI. The system may be configured to predict a future kidney recovery trajectory. The third module may be configured to predict the future kidney recovery trajectory. The system may be configured to output at least one decision-supporting-data based on the prediction of the future kidney recovery trajectory. The system may be configured to generate a probability CRRT index comprising a risk level. The third module may be configured to generate of the probability CRRT index. The probability CRRT index may be based on the prediction of the future recovery trajectory. Moreover, the system may be configured to prompt at least one authorized user to input at least one data point. The at least one data point may comprise computer-readable input data points. The at least one data point may comprise at least one selectable data point comprising at least one predetermined selected data point, wherein the system may be configured to prompt the at least one authorized user to select at least one option. The system may be configured to bidirectionally communicate with at least one server. The system may be configured to utilize any data of any of the preceding method embodiments to train at least one algorithm. The training step may be performed on the at least one server. The system may be configured to perform the method as recited herein. Moreover, the system may be integrated into an intensive care unit system. The system may be configured to perform as recited herein by using at least one of the: first module, the second module, and third module. At least one of the at least one server may comprise a local server. At least one of the at least one server may comprise a cloud server. The AKI risk level may comprise a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) The persistent AKI risk level may comprise a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) The probability CRRT index may comprise a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) Furthermore, the method comprises diagnosing a KDIGO stage, a risk for onset AKI, a risk for onset persistent AKI, and /or the probability of successful weaning probability CRRT. In another regard, the invention may relate to another method for monitoring kidney function, which will be referred to as the “KDIGO Bundle” method, comprising, acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, comparing the information contained in the at least one raw/preprocessed data with a standardized database and, outputting at least one output data indicative of the result of the comparison step. In one embodiment, the preprocessing step may comprise performing at least one unit of measure conversion. In another embodiment, the preprocessing step may comprise discarding at least one out-of-range value. In a further embodiment, the preprocessing step may comprise processing at least one diuresis data. Additionally or alternatively, the preprocessing step may comprise processing at least one blood chemistry data. Moreover, the preprocessing step may comprise processing at least one physiological data. In one embodiment, the acquiring step may comprise acquiring at least one arterial pressure data. In another embodiment, the acquiring step may comprise acquiring at least one blood glucose data. Additionally or alternatively, the acquiring step may comprise acquiring at least one drug identification data. Moreover, the acquiring step may comprise acquiring at least one serum creatinine data. Furthermore, the acquiring step may comprise acquiring at least one drug dosage data. In a further embodiment, the acquiring step may comprise acquiring at least one body surface area data. Additionally or alternatively, the acquiring step may comprise acquiring at least one stroke volume data. Moreover, the acquiring step may comprise acquiring at least one heart rate data. In one embodiment, the comparing step comprises calculating at least one Cardiac Index value, which may be defined as: Cardiac Index = (Stroke Volume ×Heart Rate)/(Body Surface Area) In another embodiment, the comparing step comprises detecting at least one hypotension event. Additionally or alternatively, the comparing step comprises detecting at least one nephrotoxic drug. In a further embodiment, the comparing step comprises calculating at least one Glomerular Ultrafiltration Rate (GFR) value. Moreover, the comparing step comprises comparing the at least one GFR value with the standardized database. Furthermore, the comparing step comprises outputting at least one drug intake instruction corresponding to the result of the comparison of the at least one GFR value with the standardized database. In another embodiment, the “KDIGO Bundle” method comprises diagnosing a hypotension event. In an additional regard, the “KDIGO Bundle” method may also make use any of the previously cited method’s results. In one embodiment, the “KDIGO Bundle” method may comprise determining the appropriate at least one drug dosage to the corresponding risk for onset persistent AKI at a current time. In a further embodiment, the “KDIGO Bundle” method may comprise determining the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy. In a further regard, the invention may relate to a method for conducting the furosemide test, which will be referred to as the assessment method, comprising, acquiring at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, preprocessing the at least one urine output data to automatically generate at least one urine output processed data, calculating a cumulative urine output after every hour since the acquiring step, and comparing the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database. In another embodiment, the assessment method may comprise displaying the result of the comparison step. In one embodiment, the preprocessing step may comprise performing at least one unit of measure conversion. In a further embodiment, the comparison result may comprise a probability of risk of worsening kidney function. Furthermore, the acquiring step may comprise acquiring at least one data indicating a currently ended renal replacement therapy treatment and at least one corresponding time data from at least one data source. In another embodiment, the comparison may comprise evaluating the cumulative urine output 24 hours after the at least one corresponding date and time data, when the acquiring step is performed several hours after the at least one time data from at least one data source corresponding to the at least one data indicating a currently ended renal replacement therapy treatment. Additionally and alternatively, the comparison result may comprise a probability of risk of unsuccessful weaning from renal replacement therapy. In a further embodiment, the assessment method may comprise diagnosing a risk of worsening kidney condition. The assessment method may also comprise diagnosing a risk of unsuccessful weaning from renal replacement therapy. In a further regard, the invention relates to a method, which will be referred to as a composite method, comprising any of and any combination of the previously cited method, the previously cited “KDIGO Bundle” method and the previously cited assessment method. The system may be configured to carry out the method as recited herein. The system may be configured to carry out the “KDIGO Bundle” method as recited herein. The system may be configured to carry out the assessment method as recited herein. The system may be configured to carry out the composite method as cited herein. The method may comprise utilizing the system as recited herein to carry out the method as recited herein. The method may comprise utilizing components of the system as recited herein to carry out given steps of the method as recited herein. The “KDIGO Bundle” method may comprise utilizing the system as recited herein to carry out the “KDIGO Bundle” method as recited herein. The “KDIGO Bundle” method may comprise utilizing components of the system as recited herein to carry out given steps of “KDIGO Bundle” method as recited herein. The assessment method may comprise utilizing the system as recited herein to carry out the assessment method as recited herein. The assessment method may comprise utilizing components of the system as recited herein to carry out given steps of assessment method as recited herein. The composite method may comprise utilizing the system as recited herein to carry out the composite method as recited herein. The composite method may comprise utilizing components of the system as recited herein to carry out given steps of composite method as recited herein. In a third aspect, the invention relates to a computer program comprising instructions which, when the program may be executed by a computer, cause the computer to carry out any of the methods and any combination of the methods as recited herein. In a fourth aspect, the invention relates to a non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out any of the methods and any combination of the methods as recited herein. Moreover, the invention relates to use of the system as recited herein. Additionally or alternatively, use as recited herein for carrying out any of the methods and any combination of the methods recited herein. The approach of the present invention comprises a plurality of advantages of the state of the art. In particular, the approach of the present invention is advantageous when compared with typical in-vitro diagnostic biomarkers, as the present invention is particularly beneficial in terms of timing of AKI prediction. The present invention is capable of predicting continuously AKI future states during the entire permanence of a patient in the intensive care area. Moreover, the present invention does not require specialized laboratory devices nor overly complex combination of devices. Additionally, the present invention provides a real-time prediction updated every hour, which allows lifting physician from the responsibility of timely executing a diagnostic test. Furthermore, the approach of the present invention is automated, and no additional human intervention, in particular, medical professional is required, as the present invention uses only routinely collected data. A further advantage of the present invention, is that the approach is capable of being executing in background and trigger an alarm when AKI-related events are identified. The approach of the present invention is also advantageous over other artificial intelligence-based approaches. For instance, the first module of the present overcomes several limitations of the state of the art that hindered other available approaches to enter the routine clinical practice. In this regard, the first module comprises a plurality of improved predictive performances in both internal and external validation for AKI stages 2 and 3. Moreover, the first module employs only a small number of routinely-collected predictive parameters, which is crucial to enable the implementation of module. Additionally or alternatively, the first module further comprises other variables, in addition to those known in the art, such as platelets, Blood Urea Nitrogen/sCr ratio, White Blood Cell, Haemoglobin, Albumin, Heart Rate. The first module is also more robust than similar approaches known in the art, in particular, over different types of Intensive Care Unit, either medical or post cardiac-surgery ICUs. The first module is not affected by other parameters such use of diuretics in patients, that for other known approaches may be detrimental, as these could introduce a bias in the predictive performance. An even further advantage of the approach of the first module of the present invention is that the module does not exhibit any bias when faced with different patient populations data. The first module is, moreover, capable of predicting both AKI defined with Urine Output-based criteria and Creatinine-based criteria, which is particularly advantageous over the state of the art which only focused on one of the two diagnostic criteria and AKI phenotypes. This is also particularly beneficial, as it is known that Creatinine-based AKI represent only a fraction of the total AKI episodes acquired in ICU, which make the first module capable of also addressing the remaining fraction. Moreover, the approach of the second module is also advantageous, as it focuses on a novel set of features based on time-series trends. Additionally, the second module comprises an improved performance than the typical approach of the few machine-learning based inventions which also only focused on specific cohorts of patients, such as septic patients. The approach of the third module of the present invention is also beneficial, as it allows to predict optimal timing to stop CRRT treatments. Furthermore, the method can be performed for the assembling, testing and/or calibrating the system without the presence of a patient. Moreover, the training of the at least one AI module can be performed without the presence of a patient. The present technology is also described by the following numbered embodiments. Below, method embodiments will be discussed. These embodiments are abbreviated by the letter “M” followed by a number. When reference is herein made to a method embodiment, those embodiments are meant. M1. A method for monitoring kidney function, the method comprising acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status, and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module is based on the at least one kidney functioning status. M2. The method according to the preceding embodiment, wherein the preprocessing step comprises performing at least one unit of measure conversion. M3. The method according to any of the preceding embodiments, wherein the preprocessing step comprises discarding at least one out-of-range value. M4. The method according to any of the preceding embodiments, wherein the preprocessing step comprises processing at least one diuresis data. M5. The method according to any of the preceding embodiments, wherein the preprocessing step comprises processing at least one blood chemistry data. M6. The method according to any of the preceding embodiments, wherein the preprocessing step comprises processing at least one physiological data. M7. The method according to any of the preceding embodiments, wherein the at least one artificial-intelligence assisted module comprises at least one of: first module, second module, and third module. M8. The method according to any of the preceding embodiments, wherein the classifying step comprises performing the classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage. M9. The method according to any of the preceding embodiments, wherein the method comprises determining which of the at least one artificial-intelligence-assisted module to trigger. M10. The method according to the preceding embodiment, wherein the method comprises determining which at least one artificial-intelligence-assisted module to trigger precedes the step of triggering the at least one artificial-intelligence-assisted module. M11. The method according to any of the two preceding embodiments and with the features of embodiment M8, wherein determining which at least one artificial-intelligence- assisted module to trigger is based on the KDIGO stage. M12. The method according to any of the preceding embodiments and with the features of embodiment M8 or M10, wherein the at least one kidney functioning status comprises the KDIGO stage. M13. The method according to the preceding embodiment, wherein when the least one kidney functioning status comprises data indicating a non-applicable stage, no artificial- intelligence-assisted module is triggered. M14. The method according to embodiment M11 and with the features of embodiment M7, wherein when the least one kidney functioning status comprises data indicating a KDIGO stage 0 or 1, the first module is triggered. M15. The method according to embodiment M11 and with the features of embodiment M7, wherein when the least one kidney functioning status comprises data indicating a KDIGO stage 2 or 3, the second module is triggered. M16. The method according to embodiment M11 and with the features of embodiment M7, wherein when the least one kidney functioning status comprises data indicating that a currently started dialysis treatment, the third module is triggered. M17. The method according to embodiment M8, wherein the method comprises performing the classifying stage comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine. M18. The method according to the preceding embodiment or to embodiment M8, wherein the classifying step comprises determining an acute kidney injury (AKI). M19. The method according to the preceding embodiments, wherein the method comprises determining a persistency of the AKI. M20. The method according to any of the three preceding embodiments or to embodiment M8, wherein the method comprises determining a final KDIGO stage. M21. The method according to any of the preceding embodiments, wherein the method comprises predicting at least one kidney disease event. M22. The method according to the preceding embodiment, wherein the predicting of the least one kidney disease event is based on the at least one kidney functioning status. M23. The method according to any of the two preceding embodiments, wherein the predicting of the at least one kidney disease event is performed by the at least one artificial-intelligence assisted module. M24. The method according to any of the preceding embodiments, wherein the first module comprises predicting a risk of a patient of developing AKI. M25. The method according to the preceding embodiment, wherein the predicting steps is performed hourly. M26. The method according to any of the preceding embodiments, wherein the method comprises predicting the risk for onset AKI within next 24 hours at a current time. M27. The method according to any of the three preceding embodiments, wherein the method comprises automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status. M28. The method according to the two preceding embodiments, wherein the AKI risk level is based on the predicting of the risk for onset AKI. M29. The method according to any of the preceding embodiments, wherein the method comprises predicting a risk for onset of persistent AKI at a current time. M30. The method according to the preceding embodiment, wherein the method comprises automatically generating a persistent AKI risk level, wherein a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status. M31. The method according to the two preceding embodiments, wherein the persistent AKI risk level is based on the predicting of the risk for onset of persistent AKI. M32. The method according to any of the preceding embodiments and with the features of embodiments M7 and M26, wherein the predicting of the risk for onset of AKI is performed by the first module. M33. The method according to any of the preceding embodiments and with the features of embodiments M7 and M26, wherein the predicting of the risk for onset of persistent AKI is performed by the second module. M34. The method according to any of the preceding embodiments, wherein the method comprises predicting a future kidney recovery trajectory. M35. The method according to the preceding embodiment and with the features of embodiment M7, wherein the predicting of the future kidney recovery trajectory is performed by the third module. M36. The method according to any of the preceding embodiments and with the features of embodiment M34, wherein the method comprises outputting at least one decision- supporting-data based on the predicting of the future kidney recovery trajectory. M37. The method according to any of the preceding embodiments, wherein the method comprises generating a probability CRRT index comprising a CRRT successful weaning probability. M38. The method according to any of the preceding embodiments and with the features of embodiment M7, wherein the generating of the probability CRRT index is performed by the third module. M39. The method according to the preceding embodiment and with the features of embodiment M34, wherein the probability CRRT index is based on the predicting of the future recovery trajectory. M40. The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of death within the next seven days during renal replacement therapy. M41. The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of death within the next seven days at the end of renal replacement therapy. M42. The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating a probability of risk of restart of renal replacement therapy within the next seven days. M43. The method according to any of the preceding embodiments and with the features of embodiment M34 wherein the method comprises generating an optimal time to stop the renal replacement therapy. M44. The method according to any of the preceding method embodiments with the features according to the embodiment M29, wherein the at least one preprocessed data is classified in at least one zone wherein further the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the start of renal replacement therapy. M45. The method according to any of the preceding method embodiments with the features according to the embodiment M34, wherein the at least one preprocessed data is classified in at least one zone wherein the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the end of renal replacement therapy. M46. The method according to any of the two preceding method embodiments, wherein the method comprises displaying the at least one preprocessed data with respect to the at least one zone it is classified in. M47. The method according to any of the preceding method embodiments with the features according to embodiment M28 wherein the method comprises displaying at least one AKI risk level in function of time. M48. The method according to any of the preceding method embodiments with the features according to embodiment M30 wherein the method comprises displaying at least one persistent AKI risk level in function of time. M49. The method according to any of the preceding method embodiments with the features according to embodiment M37 wherein the method comprises displaying at least one probability CRRT index, in function of time. M50. The method according to any of the preceding embodiments with the features according to embodiment M47 wherein the method comprises storing at least one input submitted by an authorized user corresponding to at the least one AKI risk level at at least one time. M51. The method according to any of the preceding embodiments with the features according to embodiment M48 wherein the method comprises storing at least one input submitted by an authorized user corresponding to at the least one persistent AKI risk level at at least one time. M52. The method according to any of the preceding embodiments with the features according to embodiment M49 wherein the method comprises storing at least one input submitted by an authorized user corresponding to at the least one probability CRRT index at at least one time. M53. The method according to any of the preceding embodiments with the features according to embodiment M50 wherein the method comprises displaying at least one input submitted by an authorized user corresponding to at the least one AKI risk level at at least one time. M54. The method according to any of the preceding embodiments with the features according to embodiment M48 wherein the method comprises displaying at least one input submitted by an authorized user corresponding to at the least one persistent AKI risk level at at least one time. M55. The method according to any of the preceding embodiments with the features according to embodiment M49 wherein the method comprises displaying at least one input submitted by an authorized user corresponding to at the least one probability CRRT index at at least one time. M56. The method according to any of the preceding embodiments, wherein the method comprises prompting at least one authorized user to input at least one data point. M57. The method according to the preceding embodiment, wherein the at least one data point comprises computer-readable input data points. M58. The method according to any of the two preceding embodiments, wherein the at least one data point comprises at least one selectable data point comprising at least one predetermined select data point, wherein the method comprises prompting at least one authorized user to select at least one option. M59. The method according to any of the preceding embodiments, wherein the method comprises bidirectionally communicating with at least one server. M60. The method according to any of the preceding embodiments, wherein the method comprises utilizing any data of any of the preceding embodiments to train at least one algorithm. M61. The method according to the preceding embodiment, wherein the training step is performed on the at least one server. M62. The method according to any of the preceding embodiment, wherein the method comprises performing any of the steps of the method according to any of the preceding embodiments in an integrated intensive care unit system. M63. The method according to any of the preceding method embodiments and with the features of embodiment M7, wherein the method comprises performing any of the steps of the method according to any of the preceding method embodiments by using at least one of the: first module, second module, and third module. M64. The method according to any of the preceding embodiments and with the features of embodiment M59, wherein at least one of the at least one server comprises a local server. M65. The method according to any of the preceding embodiments and with the features of embodiment M59, wherein at least one of the at least one server comprises a cloud server. M66. The method according to any of the preceding embodiments and with the features of embodiments M24, wherein the AKI risk level comprises a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) M67. The method according to any of the preceding embodiments and with the features of embodiments M30, wherein the persistent AKI risk level comprises a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) M68. The method according to any of the preceding embodiments and with the features of embodiments M37, wherein the probability CRRT index comprises a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) M69. The method according to any of the previous method embodiments with the features of embodiments M8, wherein the method comprises diagnosing a KDIGO stage. M.70 The method according to any of the previous method embodiments with the features of embodiments M26, wherein the method comprises diagnosing the risk for onset AKI. M71. The method according to any of the previous method embodiments with the features of embodiments M29, wherein the method comprises diagnosing the risk for onset persistent AKI. M72. The method according to any of the previous method embodiments with the features of embodiments M37, wherein the method comprises diagnosing the probability of successful weaning probability CRRT. Below, automation method embodiments will be discussed. These embodiments are abbreviated with the letter “A” followed by a number. Whenever reference is herein made to automation method embodiments, these embodiments are meant. A1. An automation method for monitoring kidney function, the automation method comprising acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, comparing the information contained in the at least one raw/preprocessed data with a standardized database and, outputting at least one output data indicative of the result of the comparison step. A2. The automation method according to the preceding embodiment, wherein the preprocessing step comprises performing at least one unit of measure conversion. A3. The automation method according to any of the preceding automation embodiments, wherein the preprocessing step comprises discarding at least one out-of-range value. A4. The automation method according to any of the three preceding embodiments, wherein the preprocessing step comprises processing at least one diuresis data. A5. The automation method according to any of the four preceding embodiments, wherein the preprocessing step comprises processing at least one blood chemistry data. A6. The automation method according to any of the five preceding embodiments, wherein the preprocessing step comprises processing at least one physiological data. A7. The automation method according to any of preceding automation method embodiments A1 to A6, wherein the acquiring step comprises acquiring at least one arterial pressure data. A8. The automation method according to any of preceding automation method embodiments A1 to A7, wherein the acquiring step comprises acquiring at least one blood glucose data. A9. The automation method according to any of preceding automation method embodiments A1 to A8, wherein the acquiring step comprises acquiring at least one drug identification data. A10. The automation method according to any of preceding automation method embodiments A1 to A9, wherein the acquiring step comprises acquiring at least one serum creatinine data. A11. The automation method according to any of preceding automation method embodiments A1 to A10, wherein the acquiring step comprises acquiring at least one drug dosage data. A12. The automation method according to any of preceding automation method embodiments A1 to A11, wherein the acquiring step comprises acquiring at least one body surface area data. A13. The automation method according to any of preceding automation method embodiments A1 to A12, wherein the acquiring step comprises acquiring at least one stroke volume data. A14. The automation method according to any of preceding automation method embodiments A1 to A13, wherein the acquiring step comprises acquiring at least one heart rate data. A15. The automation method according to any of the preceding automation method embodiments with the features of embodiments A12, A13 and A14, wherein the comparing step comprises calculating at least one Cardiac Index value. A16. The automation method according to any of the preceding automation method embodiments with the features of any of automation method embodiments A7, A8 and A15, wherein the comparing step comprises detecting at least one hypotension event. A17. The automation method according to any of the preceding automation method embodiments with the features of embodiment A9, wherein the comparing step comprises detecting at least one nephrotoxic drug. A18. The automation method according to any of the preceding automation method embodiments with the features of embodiment A10, wherein the comparing step comprises calculating at least one Glomerular Ultrafiltration Rate (GFR) value. A19. The automation method according to any of the preceding automation method embodiments with the features of embodiments A9, A11 and A18, wherein the comparing step comprises comparing the at least one GFR value with the standardized database. A20. The automation method according to any of the preceding automation method embodiments with the features of embodiment A19, wherein the outputting step comprises outputting at least one drug intake instruction corresponding to the result of the comparison of the at least one GFR value with the standardized database. A21. The automation method according to any of the preceding automation method embodiments with the features of embodiment A16, wherein the method comprises diagnosing a hypotension event. Below, compound method embodiments will be discussed. These embodiments are abbreviated with the letter “B” followed by a number. Whenever reference is herein made to compound method embodiments, these embodiments are meant. B1. A compound method, wherein the compound method comprises the method according to any of the preceding method embodiments and the automation method according to any of the preceding automation method embodiments. B2. The compound method according to the preceding compound method embodiment with the features of embodiments M29, A9 and A11 wherein the compound method comprises determining the appropriate at least one drug dosage to the corresponding risk for onset persistent AKI at a current time. B3. The compound method according to the any of the preceding compound method embodiments with the features of embodiments M34, A9, A11 and A18 wherein the compound method comprises determining the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy. Below, assessment method embodiments will be discussed. These embodiments are abbreviated with the letter “D” followed by a number. Whenever reference is herein made to assessment method embodiments, these embodiments are meant. D1. An assessment method for conducting the furosemide stress test, the assessment method comprising acquiring at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, preprocessing the at least one urine output data to automatically generate at least one urine output processed data, calculating a cumulative urine output after every hour since the acquiring step, and comparing the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database. D2. The assessment method according to the preceding assessment method embodiment, wherein the assessment method comprises further comprising displaying the result of the comparison step. D3. The assessment method according to any of the preceding assessment method embodiments, wherein the preprocessing step comprises performing at least one unit of measure conversion. D4. The assessment method according to any of the preceding assessment method embodiments wherein the comparison result comprises a probability of risk of worsening kidney function. D5. The assessment method according to any of the preceding assessment method embodiments wherein the acquiring step comprises acquiring at least one data indicating a currently ended renal replacement therapy treatment and at least one corresponding time data from at least one data source. D6. The assessment method according to the preceding assessment method embodiment wherein the comparison comprises evaluating the cumulative urine output 24 hours after the at least one corresponding date and time data, when the acquiring step is performed several hours after the at least one time data from at least one data source corresponding to the at least one data indicating a currently ended renal replacement therapy treatment. D7. The assessment method according to the preceding assessment method embodiment wherein the comparison result comprises a probability of risk of unsuccessful weaning from renal replacement therapy. D8. The assessment method according to any of the preceding assessment method embodiments with the features of assessment method embodiments D4 wherein the assessment method comprises diagnosing a risk of worsening kidney condition. D9. The assessment method according to any of the preceding assessment method embodiments with the features of assessment method embodiments D7 wherein the assessment method comprises diagnosing a risk of unsuccessful weaning from renal replacement therapy. Below, composite method embodiments will be discussed. These embodiments are abbreviated with the letter E followed by a number. Whenever reference is herein made to compound method embodiments, these embodiments are meant. E1. A composite method, wherein the composite method comprises the method according to any of the preceding method embodiments, the automation method according to any of the preceding automation method embodiments, the compound method according to any of the preceding compound method embodiments, the assessment method according to any of the preceding assessment method embodiments. Below, system embodiments will be discussed. These embodiments are abbreviated by the letter “S” followed by a number. When reference is herein made to a system embodiment, those embodiments are meant. S1. A system for monitoring kidney function, the system comprising an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence- assisted module, wherein the triggering component is configured to trigger the at least one artificial- intelligence-assisted module based on the at least one kidney functioning status. S2. The system according to the preceding embodiment, wherein the processing component is configured to perform at least one unit of measure conversion. S3. The system according to any of the preceding system embodiments, wherein the processing component is configured to discard at least one out-of-range value. S4. The system according to any of the preceding system embodiments, wherein the processing component is configured to process at least one diuresis data. S5. The system according to any of the preceding system embodiments, wherein the processing component is configured to process at least one blood chemistry data. S6. The system according to any of the preceding system embodiments, wherein the processing component is configured to process at least one physiological data. S7. The system according to any of the preceding system embodiments, wherein the at least one artificial-intelligence assisted module comprises to at least one of: first module, second module, and third module. S8. The system according to any of the preceding system embodiments, wherein the classifying component is configured to perform a classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage. S9. The system according to any of the preceding system embodiments, wherein the system is configured to determine which of the at least one artificial-intelligence-assisted module to trigger. S10. The system according to the preceding embodiment, wherein the system is configured to determine which at least one artificial-intelligence-assisted module to trigger before prompting the triggering component to trigger the at least one artificial-intelligence- assisted module. S11. The system according to any of the two preceding embodiments and with the features of embodiment S8, wherein the system is configured to determine which at least one artificial-intelligence-assisted module to trigger based on the KDIGO stage. S12. The system according to any of the preceding system embodiments and with the features of embodiment S8 or S10, wherein the at least one kidney functioning status comprises the KDIGO stage. S13. The system according to the preceding embodiment, wherein the system is configured to triggering the at least one artificial-intelligence-assisted module based on a value of the KDIGO stage. S14. The system according to any of the two preceding embodiments, wherein when the least one kidney functioning status comprises data indicating a value of the KDIGO stage as a non-applicable stage, the system is configured to trigger none artificial-intelligence- assisted module. S15. The system according to embodiment S12 or S13 and with the features of embodiment S7, wherein when the least one kidney functioning status comprises data indicating the value of the KDIGO stage as 0 or 1, the system is configured to trigger First module. S16. The system according to embodiment S12 or S13 and with the features of embodiment S7, wherein when the least one kidney functioning status comprises data indicating the value of the KDIGO stage as 2 or 3, the system is configured to trigger the second module. S17. The system according to embodiment S12 or S13 and with the features of embodiment S7, wherein when the least one kidney functioning status comprises data indicating the value of the KDIGO stage as indicating that a currently started dialysis treatment, the system is configured to trigger the third module. S18. The system according to embodiment S8, wherein the system is configured to perform the classifying step comprising at least one of: KDIGO stage for diuresis, and KDIGO stage for creatinine. S19. The system according to the preceding embodiment or to embodiment S8, wherein the classifying component is configured to determine an acute kidney injury (AKI). S20. The system according to the preceding embodiments, wherein the system is configured to determine a persistency of the AKI. S21. The system according to any of the three preceding embodiments or to embodiment S8, wherein the system is configured to determine a final KDIGO stage. S22. The system according to any of the preceding system embodiments, wherein the system is configured to predict at least one kidney disease event. S23. The system according to the preceding embodiment, wherein the system is configured to predict the at least one kidney disease event based on the at least one kidney functioning status. S24. The system according to any of the two preceding embodiments, wherein the system is configured to predict the at least one kidney disease event by means of the at least one artificial-intelligence assisted module. S25. The system according to any of the preceding system embodiments and with the features of embodiment S7, wherein the first module is configured to predict a risk of a patient of developing AKI. S26. The system according to the preceding embodiment, wherein the first module is configured to predict the risk of a patient of developing AKI on an hourly basis. S27. The system according to any of the preceding system embodiments, wherein the system is configured to predict a risk for onset AKI within next 24 hours at a current time. S28. The system according to the preceding embodiment, wherein the system is configured to automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status. S29. The system according to the two preceding embodiments, wherein the AKI risk level is based on the prediction of the risk for onset AKI. S30. The system according to any of the preceding system embodiments, wherein the system is configured to predict a risk for onset of persistent AKI at a current time. S31. The system according to the preceding embodiment, wherein the system is configured to automatically generate a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status. S32. The system according to the two preceding embodiments, wherein the persistent AKI risk level is based on the prediction of the risk for onset of persistent AKI. S33. The system according to any of the preceding system embodiments and with the features of embodiments S7 and S27, wherein the first module is configured to predict the risk for onset of AKI. S34. The system according to any of the preceding system embodiments and with the features of embodiments S7 and S27, wherein the second module is configured to predict the risk for onset of persistent AKI. S35. The system according to any of the preceding system embodiments, wherein the system is configured to predict a future kidney recovery trajectory. S36. The system according to the preceding embodiment and with the features of embodiment S7, wherein the third module is configured to predict the future kidney recovery trajectory. S37. The system according to any of the preceding system embodiments and with the features of embodiment S34, wherein the system is configured to output at least one decision-supporting-data based on the prediction of the future kidney recovery trajectory. S38. The system according to any of the preceding system embodiments, wherein the system is configured to generate a probability CRRT index comprising a successful weaning probability. S39. The system according to any of the preceding system embodiments and with the features of embodiment S7, wherein the third module is configured to generate of the probability CRRT index. S40. The system according to the preceding embodiment and with the features of embodiment S35, wherein the probability CRRT index is based on the prediction of the future recovery trajectory. S41. The system according to any of the preceding embodiments and with the features of embodiment S35 wherein the system is configured to generate a probability of risk of death within the next seven days during renal replacement therapy. S42. The system according to any of the preceding embodiments and with the features of embodiment S35 wherein the system is configured to generate a probability of risk of death within the next seven days at the end of renal replacement therapy. S43. The system according to any of the preceding embodiments and with the features of embodiment S35 wherein the system is configured to generate a probability of risk of restart of renal replacement therapy within the next seven days. S44. The system according to any of the preceding embodiments and with the features of embodiment S35 wherein the system is configured to generate an optimal time to stop the renal replacement therapy. S45. The system according to any of the preceding system embodiments with the features according to the embodiment S30, wherein the system is configured to classify at least one preprocessed data in at least one zone wherein further the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the start of renal replacement therapy. S46. The system according to any of the preceding system embodiments with the features according to the embodiment S35, wherein the system is configured to classify at least one preprocessed data in at least one zone wherein the at least one zone is delimited according to at least one range of values, wherein the at least one range of values is defined, with respect to a standardized database, to assess the urgency needed for the end of renal replacement therapy. S47. The system according to any of the preceding system embodiments wherein the system comprises a display device. S48. The system according to any of the two preceding system embodiments, wherein the display device is configured to display the at least one preprocessed data with respect to the at least one zone it is classified in. S49. The system according to any of the preceding system embodiments with the features according to embodiment S29 wherein the display device is configured to display at least one AKI risk level in function of time. S50. The system according to any of the preceding system embodiments with the features according to embodiment S41 wherein the display device is configured to display at least one persistent AKI risk level in function of time. S51. The system according to any of the preceding system embodiments with the features according to embodiment S38 wherein the display device is configured to display at least one probability CRRT index, in function of time. S52. The system according to any of the preceding embodiments with the features according to embodiment S49 wherein the system is configured to store at least one input submitted by an authorized user corresponding to at the least one AKI risk level at at least one time. S53. The system according to any of the preceding embodiments with the features according to embodiment S50 wherein the system is configured to store at least one input submitted by an authorized user corresponding to at the least one persistent AKI risk level at at least one time. S54. The system according to any of the preceding embodiments with the features according to embodiment S51 wherein the system is configured to store at least one input submitted by an authorized user corresponding to at the least one probability CRRT index at at least one time. S55. The system according to any of the preceding embodiments with the features according to embodiment S52 wherein the display device is configured to display at least one input submitted by an authorized user corresponding to at the least one AKI risk level at at least one time. S56. The system according to any of the preceding embodiments with the features according to embodiment S50 wherein the display device is configured to display at least one input submitted by an authorized user corresponding to at the least one persistent AKI risk level at at least one time. S57. The system according to any of the preceding embodiments with the features according to embodiment S51 wherein the display device is configured to display at least one input submitted by an authorized user corresponding to at the least one probability CRRT index at at least one time. S58. The system according to any of the preceding system embodiments, wherein the system is configured to prompt at least one authorized user to input at least one data point. S59. The system according to the preceding embodiment, wherein the at least one data point comprises computer-readable input data points. S60. The system according to any of the two preceding embodiments, wherein the at least one data point comprises at least one selectable data point comprising at least one predetermined selected data point, wherein the system is configured to prompt the at least one authorized user to select at least one option. S61. The system according to any of the preceding system embodiments, wherein the system is configured to bidirectionally communicate with at least one server. S62. The system according to any of the preceding system embodiments, wherein the system is configured to utilize any data of any of the preceding method embodiments to train at least one algorithm. S63. The system according to the preceding embodiment, wherein the training step is performed on the at least one server. S64. The system according to any of the preceding embodiment, wherein the system is configured to perform any of the steps of the method according to any of the preceding method embodiments. S65. The system according to the preceding embodiment, wherein the system is integrated into an intensive care unit system. S66. The system according to any of the preceding system embodiments and with the features of embodiment S7, wherein the system is configured to perform any of the steps of the method according to any of the preceding method embodiments by using at least one of the: first module, second module, and third module. S67. The system according to any of the preceding system embodiments and with the features of embodiment S61, wherein at least one of the at least one server comprises a local server. S68. The system according to any of the preceding system embodiments and with the features of embodiment S61, wherein at least one of the at least one server comprises a cloud server. S69. The system according to any of the preceding system embodiments and with the features of embodiments S26, wherein the AKI risk level comprises a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) S70. The system according to any of the preceding system embodiments and with the features of embodiments S30, wherein the persistent AKI risk level comprises a risk threshold comprising a risk score defining the risk level as Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) S71. The system according to any of the preceding system embodiments and with the features of embodiments S38, wherein the probability CRRT index comprises a threshold comprising a risk score defining the successful weaning probability as Score Successful weaning probability N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) S72. The system according to any of the preceding system embodiments, wherein the system is configured to carry out the method according to any of the preceding method embodiments. S73. The system according to any of the previous system embodiments with the features of embodiments S8, wherein the system is configured to diagnose a KDIGO stage. S74. The system according to any of the previous system embodiments with the features of embodiments S26, wherein the system is configured to diagnose the risk for onset AKI. S75. The system according to any of the previous system embodiments with the features of embodiments S29, wherein the system is configured to diagnose the risk for onset persistent AKI. S76. The system according to any of the previous system embodiments with the features of embodiments S37, wherein the system is configured to diagnose the probability of successful weaning probability CRRT. S77. A system for monitoring kidney function, the system comprising an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a comparing component configured to compare the information contained in the at least one raw/preprocessed data with a standardized database and, an outputting component configured to output at least one output data indicative of the result of the comparison step. S78. The system according to the preceding embodiment, wherein the processing component is configured to perform at least one unit of measure conversion. S79. The system according to any of preceding system embodiments S77-S78, wherein the processing component is configured to discard at least one out-of-range value. S80. The system according to any of preceding system embodiments S77-S79, wherein the processing component is configured to process at least one diuresis data. S81. The system according to any of preceding system embodiments S77-S80, wherein the processing component is configured to process at least one blood chemistry data. S82. The system according to any of preceding system embodiments S77-S81, wherein the processing component is configured to process at least one physiological data. S83. The system according to any of preceding system embodiments S77-S82, wherein the acquiring component is configured to acquire at least one arterial pressure data. S84. The system according to any of preceding system embodiments S77-S83, wherein the acquiring component is configured to acquire at least one blood glucose data. S85. The system according to any of preceding system embodiments S77-S84, wherein the acquiring component is configured to acquire at least one drug identification data. S86. The system according to any of preceding system embodiments S77-S85, wherein the acquiring component is configured to acquire at least one serum creatinine data. S87. The system according to any of preceding system embodiments S77-S86, wherein the acquiring component is configured to acquire at least one drug dosage data. S88. The system according to any of preceding system embodiments S77-S87, wherein the acquiring component is configured to acquire at least one body surface area data. S89. The system according to any of preceding system embodiments S77-S88, wherein the acquiring component is configured to acquire at least one stroke volume data. S90. The system according to any of preceding system embodiments S77-S89, wherein the acquiring component is configured to acquire at least one heart rate data. S91. The system according to any of preceding system embodiments S77-S90 with the features of embodiments S88, S89, and S90, wherein the comparing component is configured to calculate at least one Cardiac Index value. S92. The system according to any of preceding system embodiments S77-S91 with the features of embodiments S83, S84, and S91, wherein the comparing component is configured to detect at least one hypotension event. S93. The system according to any of preceding system embodiments S77-S92 with the features of embodiment S85, wherein the comparing component is configured to detect at least one nephrotoxic drug. S94. The system according to any of preceding system embodiments S77-S93 with the features of embodiment S86, wherein the comparing component is configured to calculate at least one Glomerular Ultrafiltration Rate (GFR) value. S95. The system according to any of preceding system embodiments S77-S94 with the features of embodiments S85, S87 and S94, wherein the comparing component is configured to compare the at least one GFR value with the standardized database. S96. The system according to any of preceding system embodiments S77-S95 with the features of embodiment S95, wherein the outputting component is configured to output at least one drug intake instruction corresponding to the result of the comparison of the at least one GFR value with the standardized database. S97. The system according to any of preceding system embodiments S77-S96 with the features of embodiment S92, wherein the system is configured to diagnose a hypotension event. S98. A system, wherein the system comprises the system according to any of preceding embodiments S1-S76 and the system according to any of preceding embodiments S77-S97. S99. The system according to the preceding system embodiment with the features of embodiments S30, S85 and S87 wherein the system is configured to determine the appropriate at least one drug dosage to the corresponding risk for onset persistent AKI at a current time. S100. The system according to the any of the preceding compound method embodiments with the features of embodiments S35, S85, S87 and S94 wherein the system is configured to determine the appropriate at least one drug dosage to the corresponding GFR and corresponding type of renal replacement therapy. S101. A system for conducting the furosemide stress test, the system comprising an acquiring component configured to acquire at least one urine output data, at least one corresponding date and time data, and at least one data indicating a currently started renal replacement therapy treatment from at least one data source, a processing component configured to preprocess the at least one urine output data to automatically generate at least one urine output processed data, a calculating component configured to calculate a cumulative urine output after every hour, and a comparing component configured to compare the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database. S102. The system according to the preceding system embodiment, wherein the system comprises a display component. S103. The system according to the preceding system embodiment, wherein the display component is configured to display the result of the comparison step. S104. The system according any of preceding system embodiments S101-S103, wherein the processing component is configured to perform at least one unit of measure conversion. S105. The system according any of preceding system embodiments S101-S104, wherein the output of the comparing component comprises a probability of risk of worsening kidney function. S106. The system according any of preceding system embodiments S101-S105, wherein the acquiring component is configured to acquire at least one data indicating a currently ended renal replacement therapy treatment and at least one corresponding time data from at least one data source. S107. The system according to any of preceding system embodiments S101-S106, wherein the comparing component is configured to evaluate the cumulative urine output 24 hours after the at least one corresponding date and time data, several hours after when the acquiring component is configured to acquire at least one time data from at least one data source corresponding to the at least one data indicating a currently ended renal replacement therapy treatment. S108. The system according to the preceding system embodiment wherein the comparing component is configured to output at least one result comprising a probability of risk of unsuccessful weaning from renal replacement therapy. S109. The system according to any of preceding system embodiments S101-S108, with the features of system embodiment S105 wherein the system is configured to diagnose a risk of worsening kidney condition. S110. The system according to any of preceding system embodiments S101-S109, with the features of system embodiment S108 wherein the system is configured to diagnose a risk of unsuccessful weaning from renal replacement therapy. S111. A system wherein the system comprises any of or any combination of, the system according to any of preceding embodiments S1-S76, the system according to any of preceding embodiments S77-S97, the system according to any of preceding embodiments S98-S100, and the system according to any of preceding embodiments S101-S110. M73. The method according to any of the preceding method embodiments, wherein the method comprises utilizing the system according to any of the preceding system embodiments to carry out the method according to any of the preceding method embodiments. M74. The method according to any of the preceding method embodiments, wherein the method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the method according to any of the preceding method embodiments. A22. The automation method according to any of the preceding automation method embodiments, wherein the automation method comprises utilizing the system according to any of the preceding system embodiments to carry out the automation method according to any of the preceding automation method embodiments. A23. The automation method according to any of the preceding automation method embodiments, wherein the automation method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the automation method according to any of the preceding automation method embodiments. B4. The compound method according to any of the preceding compound method embodiments, wherein the compound method comprises utilizing the system according to any of the preceding system embodiments to carry out the compound method according to any of the preceding compound method embodiments. B5. The compound method according to any of the preceding compound method embodiments, wherein the compound method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the compound method according to any of the preceding compound method embodiments. D8. The assessment method according to any of the preceding assessment method embodiments, wherein the assessment method comprises utilizing the system according to any of the preceding system embodiments to carry out the assessment method according to any of the preceding assessment method embodiments. D9. The assessment method according to any of the preceding assessment method embodiments, wherein the assessment method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the assessment method according to any of the preceding assessment method embodiments. E2. The composite method according to any of the preceding composite method embodiments, wherein the composite method comprises utilizing the system according to any of the preceding system embodiments to carry out the composite method according to any of the preceding composite method embodiments. E3. The composite method according to any of the preceding composite method embodiments, wherein the composite method comprises utilizing components of the system according to any of the preceding system embodiments to carry out given steps of the composite method according to any of the preceding composite method embodiments. Below is a list of computer program embodiments. Those will be indicated with a letter “C”. Whenever such embodiments are referred to, this will be done by referring to “C” embodiments. C1. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding method embodiments. C2. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding automation method embodiments. C3. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding compound method embodiments. C4. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding assessment method embodiments. C5. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any of the preceding composite method embodiments. Below is a list of computer storage embodiments. Those will be indicated with a letter “T”. Whenever such embodiments are referred to, this will be done by referring to “T” embodiments. T1. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding method embodiments. T2. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding automation method embodiments. T3. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding compound method embodiments. T4. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding assessment method embodiments. T5. A non-transient computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any of the preceding composite method embodiments. Below is a list of use embodiments. Those will be indicated with a letter “U”. Whenever such embodiments are referred to, this will be done by referring to “U” embodiments. U1. Use of the system according to any of the preceding system embodiments. U2. Use according to the preceding embodiment for carrying out the method according to any of the preceding method embodiments. U3. Use according to the preceding embodiment for carrying out the method according to any of the preceding automation method embodiments. U4. Use according to the preceding embodiment for carrying out the method according to any of the preceding compound method embodiments. U5. Use according to the preceding embodiment for carrying out the method according to any of the preceding assessment method embodiments. U6. Use according to the preceding embodiment for carrying out the method according to any of the preceding composite method embodiments.
The present invention will now be described with reference to the accompanying drawings which illustrate embodiments of the invention. These embodiments should only exemplify, but not limit, the present invention. Fig. 1 schematically depicts a system for monitoring kidney function according to embodiments of the present invention; Fig. 2 schematically depicts an example of the system according to embodiment of the present invention; Fig. 3 schematically depicts an example of the system according to embodiments of the present invention implementing steps of the method according to embodiments of the present invention; Fig. 4 schematically depicts a computing device; Fig. 5 depicts a chart outputted by the present invention, representing the acquired measurements of clinical parameters with respect to their corresponding urgency level zones; Fig. 6 depicts chart outputted by the present invention, representing the scores calculated by the system as well as a note inputted into the system by an authorized user, with respect to time. It is noted that not all the drawings carry all the reference signs. Instead, in some of the drawings, some of the reference signs have been omitted for sake of brevity and simplicity of illustration. Embodiments of the present invention will now be described with reference to the accompanying drawings. Fig. 1 schematically depicts a system 100 for monitoring kidney function according to embodiments of the present invention. In simple terms, the system 100 comprises an acquiring component 150, a processing component 190, a classifying component 170, and a triggering component 180. Moreover, the system 100 comprises at least one artificial- intelligence-assisted module 200, such as a first module 210, a second module 220 and a third module 230. Fig. 1 also depicts a “KDIGO bundle” system 300 for monitoring kidney function, comprising an acquiring component 150, a processing component 190, a comparing component 360, and an outputting component (not shown in this figure). Fig. 1 furthermore depicts a system for conducting the furosemide stress test comprising an acquiring component 150, a processing component 410, a calculating component 430, and a comparing component 460. In one embodiment, acquiring component 150 may be configured to acquire at least one raw data from at least one data source (not shown). Moreover, the processing component 190 may be configured to at least preprocess the at least one raw data to automatically generate at least one processed data, and the classifying component 170 may be configured to classify the at least one processed data into at least one kidney functioning status. In a further embodiment, the triggering component 180 may be configured to trigger at least one artificial-intelligence-assisted module 200 such at least one of the first module 210, the second module 220 and the third module 230. Additionally or alternatively, the triggering component 180 may be configured to trigger the at least one artificial- intelligence-assisted module 200 based on the at least one kidney functioning status. Furthermore, in some embodiments, the classifying component and the triggering component may also bidirectionally communicate between each as depicted in Fig. 1. However, it should be understood that also other component of the system 100 may be in bidirectional communication (not shown). In one embodiment, the comparing component 360 may be configured to compare the information contained in the at least one preprocessed data with a standardized database. In another embodiment, the processing component 410 may be configured to at least preprocess the at least one raw data to automatically generate at least one processed data. The calculating component 430 may be configured to calculate a cumulative urine output after every hour, and the comparing component 460 may be configured to compare the cumulative urine output and the at least one data indicating a currently started renal replacement therapy treatment with a standardized database. The preprocessing component may be shared between any combination of systems presented in the invention, for example, the preprocessing component 190 is shared between system 100 and system 300. A preprocessing component may also be independent from other systems such as preprocessing component 410 in system 400. Moreover, the system 100 is configured to perform the steps of the method as recited herein. The system 300 is configured to perform the steps of the automation method as recited herein. The systems 100 and 300 are configured to perform the compound method as recited herein. The system 400 is configured to perform the steps if the assessment method as recited herein. The systems 100, 300 and 400 are configured to perform the steps of the composite method as recited herein. It should be understood that in some embodiment, any of the component 150, 190, 170, and 180 may be at least be partially integrated in a single component. For instance, the acquiring component 150 and the processing component 190 may be integrated into a single component. It should also be understood that in some embodiment, any of the component 150, 190, and 360 may be at least be partially integrated in a single component. It should be further be understood that in some embodiment, any of the component 150, 410, 430, and 460 may be at least be partially integrated in a single component. Moreover, it should be understood that in some embodiment, any of the any components of any of the systems cited herein may be at least be partially integrated in a single component. The system 100 may perform steps of the method as exemplified in Fig. 2 Fig. 2 schematically depicts an example of the system 100 according to embodiments of the present invention. In Fig. 2, the example is depicted in relation to one artificial- intelligence-assisted module 200, in particular to the first module 210. However, it should be understood that the system 100 according to the present invention is also configured to operate with any the at least one artificial-intelligence-assisted modules 200 according to embodiments of the present invention. In one embodiment, the system 100 may be configured as a medical software system 100. The medical software system 100 may comprise a plurality of components, wherein the system 100 is configured to be deployed both on-premises in hospital servers or in the cloud for instance via a commercial cloud provider. In a further embodiment, the system 100 may be configured to deploy at least one model. The deployment view may focus on aspects of the system that are important for the system to go into live operation and defines the physical environment in which the system 100 is intended to run. For instance, Fig. 2 depicts the system 100 configured as a renal platform system 100. The dashed lines represent internal components of the system 100, and the arrows represent the communication direction between two items. It should be understood that the communication direction as depicted in Fig. 2 is only exemplary, and that in other embodiments the communication direction may be the opposite as depicted in Fig.2 and/or it may be bidirectional. Moreover, the system may also be deployed in two different modalities, for example, on-premise such as in locally in hospital; and on-cloud such as a cloud application running in a commercially available environment, e.g., running in Microsoft Azure environment. In one embodiment, the system may be encapsulated in a virtual machine, e.g., in a single virtual machine. In the on-premise deployment, the system may be deployed as docker container. The system may implement the steps of the method according to embodiments of the present invention and may also prompt the modules as defined herein.). Fig. 3 schematically depicts an example of the system implementing steps of method for monitoring kidney function, according to embodiments of the present invention. In simple terms, the method for monitoring kidney function comprises four main steps, which may also be referred to as main sections, comprising: data acquisition S150, data preprocessing S190, KDIGO classification S170, and invocation of artificial-intelligence-assisted modules as needed S180. It should be understood that the method for monitoring kidney function according to embodiments of the present invention is a computer-implemented method, which may further be executed in the medical software system. It should also be understood that the invocation S180 of the artificial-intelligence-assisted modules comprises triggering of at least one artificial-intelligence-assisted module 200, which may also be referred to as invoking of the at least one artificial-intelligence-assisted module, that is, invoking the needed artificial-intelligence pending on a kidney disease detection output. The data acquisition S150 comprises the process in which the medical software system receives data from a plurality of sources, i.e., it is the step of the method for monitoring kidney function that prompts the medical software system to acquire at least one raw data from at least one source, wherein the at least one raw data comprises data of a user and related to the user’s kidney functioning. For instance, the method may prompt the medical software system to receive clinical data related to a patient admitted in an intensive care unit (ICU), wherein the clinical data may be associated with time and day of measurement and/or unit of measurement. Moreover, the clinical data may be received, for example. From a hospital electronic health record system such as from medical devices, laboratory information system, data manually input by medical care personal such as nurses and/or physicians. Clinical data may be received from the Hospital Electronic Health Record system, from medical devices, from laboratory information system, manually inserted by the nurses, clinicians and/or physicians. The clinical data may comprise, inter alia, but not limited to: blood chemistry measurements such as albumin, blood urea nitrogen (BUN), hematocrit, hemoglobin, platelets’ count, serum creatinine, white blood cells count; physiological data such as diastolic pressure, systolic pressure, medium pressure, heart rate, urine output; patient information such as patient ID, height, weight, age, gender ethnicity, comorbidities, reason of admission to ICU; therapy data such as initial and final information of dialysis treatments. The preprocessing S190 comprises transforming the at least one raw data acquired from the at least one data source into well-defined hourly-time-series data suitable to be used in subsequent steps of the method. Moreover, the processing comprises generating at least one processed data. For transforming the at least one raw data the preprocessing step may comprises applying four distinct sequential phases. The preprocessing may be executed every hour taking as input all the measurements collected until a present hour. It should be understood that this step is stateless, which means that it processes every time all the data acquired by the medical software system since a patient’s admission in ICU. In one embodiment, the preprocessing may comprise tabulating input for each parameter collected, from all a plurality of preprocessing phases such as diuresis, blood chemistry, and physiological. As an example, the following table is given, wherein the first timestamp corresponds to the admission hour of the patient, while the last timestamp is the current hour when the computation started. S0 TABLE: FINAL PROCESSING RESULTS Parameter Value Timestamp YYYY-MM-DD HH:00:00 YYYY-MM-DD (…H.H+1):00:00 YYYY-MM-DD (HH+n):00:00 Each phase of the preprocessing can handle missing values by carrying forward the value assigned to the preceding hour. This process runs at most max_gap times in a row, and this variable may assume different values depending on the type of treated parameter, e.g., blood chemistry, physiological, urine output from 1 up to 96 hours. Put differently, a value parameter may be carried out for a specific number of hours, depending on a given parameter. For instance, for urine output values the process may be carried forward for about 12, on the other hand, for creatine value this may be performed for a longer period such as for about 96 hours. The method may further be concerned with a plurality of other factors. For instance, given raw input data may potentially be subject to various problems such as insertion errors or different units of measurement. Hence, the method may also be concerned with data quality analysis which may comprise analyzing input data and performing, for instance, the following steps: A first step comprising unifying the unit of measurements S192 received to the ones used by the system by performing unit of measure conversion where needed. E.g.: transforming volumetric units such liter into milliliter. A second step comprising discarding out-of-range values S194 according to a pre-defined list compiled by the system yielding an output comprising cleaned data which may be used in subsequent steps of the preprocessing. In one embodiment, the preprocessing step may comprise urine output data preprocessing, comprising urine output data received by the medical software system which is assigned to a specific timestamp and within a specific hour and which may comprise different values. The preprocessing step yields a transformed value, for instance, millilitres values of urine transformed into milliliters/hour/kilograms values assigned to a specific hour. For this purpose, diuresis values are first converted to ml/h and then normalized by the adjusted ideal body weight (AIBW) of the patient obtained with the following formulas: ^^^^^ ^^^^ ^^^^ℎ^ (^^^)(^) =   50  +  (0.91  ×  [ℎ  −  152.4]) ^^^^^ ^^^^ ^^^^ℎ^ (^^^)(^) =   45.5  +  (0.91  ×  [ℎ  −  152.4])  [18] (m = male, f = female, h = height in centimeters) ^^^^^^^^ ^^^^^ ^^^^ ^^^^ℎ^ (^^^^) = ^^^+ 0.4 ∗ (^^^− ^^^)[18] (ABW = actual body weight at the ICU admission) Such preprocessing of urine output data may be exemplified as follows: S1-1 TABLE: INPUT PARAMETERS EXAMPLE Parameter Value (ml) Timestamp Diuresis 100 YYYY-MM-DD 11:12:04 Diuresis 300 YYYY-MM-DD 11:32:04 Diuresis 0 YYYY-MM-DD 11:52:04 Diuresis 200 YYYY-MM-DD 12:12:04 S1-2 TABLE: OUTPUT PARAMETERS EXAMPLE Parameter Value (ml/hr/kg) Timestamp Diuresis XX YYYY-MM-DD 11:00:00 Diuresis XX YYYY-MM-DD 12:00:00 S1 ALGORITHM: URINE OUTPUT MAIN ROUTINE Input: List of diuresis measurements as S1-1 Table ordered by Timestamp key Output: Uniform time series of diuresis (ml/hr/kg) as S1-2 Table Step 1: For each timestamp T as current_hour_X in S1-2 Table: Step 2: Select all values between current_hour_X and current_hour_X-1 from S1-1 Table Step 3: If the result of Step 2 is empty, then proceed with S1-1 Algorithm. Otherwise go for S1-2 Algorithm Step 4: Repeat Step 1 S1-1 ALGORITHM: URINE OUTPUT MISSING VALUES Input: S1-Algorithm input and Step 2 of S1-Algorithm Output: Assign to the row of S1-2 Table where Timestamp is equal to current_hour_X a value Step 1: Take the previous value assigned to the current_hour_X-1 in S1-2 Step 2: T Ifa cboluenter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S1-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S1-2 Table. Step 3: Go to Step 1 of S1 Algorithm S1-2 ALGORITHM: URINE OUTPUT CALCULATE HOURLY VALUE Input: S1-Algorithm input and Step 2 of S1-Algorithm Output: Assign to the row of S1-2 Table where Timestamp is equal to current_hour_X a value Step 1: Insert in the result of Step 2 of S1-Algorithm the first measure preceding the (current_hour_X-1):00:00 from the S1-1 Table. Step 2: Calculates the time-gap between the values selected in Step 1. Step 3: For each gap obtained in Step 2 multiply the value of ml to the gap expressed in minutes and sum all these values. The result is the urine output expressed in ml/hr. Step 4: Assign to the current_hour_X in S1-2 Table the result obtained in Step 3 divided by the AIBW obtained with the formula. The result will be expressed as ml/hr/kg. Step 5: G Re o s t e o t S co te u p nte 1 r o v f a S ri 1 ab A le lg . orithm In a further embodiment, the preprocessing S190 may also comprise preprocessing the at least one raw data comprising blood chemistry data which are assigned to a specific timestamp and within a specific hour, which may comprise several different values. The preprocessing step yields a selected singular value for each blood chemistry parameter collected, to a well-defined hour. S2-1 TABLE: INPUT PARAMETERS EXAMPLE Parameter Value Timestamp Creatinine 0.3 YYYY-MM-DD 11:12:04 Creatinine 0.5 YYYY-MM-DD 11:32:04 Creatinine 1.3 YYYY-MM-DD 11:52:04 Creatinine 1.1 YYYY-MM-DD 12:12:04 The preprocessing of blood chemistry S196B data may be exemplified as follows: S2-2 TABLE: OUTPUT PARAMETERS EXAMPLE Parameter Value Timestamp Creatinine XX YYYY-MM-DD 11:00:00 Creatinine XX YYYY-MM-DD 12:00:00 S2 ALGORITHM: BLOOD CHEMISTRY MAIN ROUTINE Input: List of raw blood chemistry measurements as S2-1 Table ordered by Timestamp key Output: Uniform time series of the blood chemistry parameters as S2-2 Table Step 1: Group the S2-1 Table using Parameter column as key Step 2: For each timestamp T as current_hour_X in S2-2 Table, select all values between current_hour_X-1 and current_hour_X. Step 3: If the result of Step 2 is empty go for S2-1 Algorithm. Otherwise go for S2-2 Algorithm Step 4: Repeat Step 2 for each parameter grouped S2 –1 ALGORITHM: BLOOD CHEMISTRY MISSING VALUES Input: Input of Step 2 of the S2 Algorithm and current_hour_X Output: Assign to the row of S2-2 Table where Timestamp is equal to current_hour_X a value Step 1: Select the previous value of current_hour_X-1 from the S2-2 Table. Step 2: If counter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S2-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S2-2 Table. Step 3: Go to Step 2 of S2-Algorithm S2 –2 ALGORITHM: BLOOD CHEMISTRY HOURLY VALUE Input: Input of Step 2 of the S2 Algorithm and current_hour_X Output: Assign to the row of S2-2 Table where Timestamp is equal to current_hour_X a value Step 1: From the input of Step 2 of the S2 Algorihtm, the last value (meaning the one with maximum timestamp) will be selected and assigned to current_hour_X hour. Reset counter variable. Step 2: Go to Step 2 of S2 Algorithm In another embodiment, the preprocessing S190 may also comprise preprocessing the at least one raw data comprising physiological data from an Electronic Health Record system such as from a database of clinical data of a hospital, which are assigned a specific timestamp and within a specific hour, which may comprise several different values. The preprocessing step S190 yields a selected singular value for each physiological parameter collected to a well-defined hour. The preprocessing S190 of physiological data may be exemplified as follows: S3-1 TABLE: INPUT PARAMETERS EXAMPLE Parameter Value Timestamp Heart Rate 80 YYYY-MM-DD 11:12:04 Heart Rate 120 YYYY-MM-DD 11:32:04 Heart Rate 110 YYYY-MM-DD 11:52:04 Heart Rate 70 YYYY-MM-DD 12:12:04 S3-2 TABLE: OUTPUT PARAMETERS EXAMPLE Parameter Value Timestamp Heart Rate XX YYYY-MM-DD 11:00:00 Heart Rate XX YYYY-MM-DD 12:00:00 S3 ALGORITHM: PHYSIOLOGICAL PROCESSING MAIN ROUTINE Input: List of raw physiological measurements as S3-1 Table ordered by Timestamp key Output: Uniform time series of the physiological parameters as S3-2 Table Step 1: Group the S3-1 Table using Parameter column as key Step 2: For each timestamp T as current_hour_X in S3-1 Table, select all values between current_hour_X-1 and current_hour_X. Step 3: If the result of Step 2 is empty go for S3-1 Algorithm. Otherwise go for S3-2 Algorithm. Step 4: Repeat Step 2 for each parameter grouped S3 –1 ALGORITHM: PHYSIOLOGICAL MISSING VALUES Input: Input of Step 2 of the S3 Algorithm and current_hour_X Output: Assign to the row of S3-2 Table where Timestamp is equal to current_hour_X a value Step 1: Select the previous value of current_hour_X-1 from the S3-2 Table. Step 2: If counter is less than max_gap then assigned the value selected in Step 1 to the current_hour_X in S3-2 Table. Increment counter; Otherwise, assign Not Available to the current_hour_X in S3-2 Table. Step 3: Go to Step 2 of S3-Algorithm S3 –2 ALGORITHM: PHYSIOLOGICAL HOURLY VALUE Input: Input of Step 2 of the S3 Algorithm and current_hour_X Output: Assign to the row of S3-2 Table where Timestamp is equal to current_hour_X a value Step 1: From the input of Step 2 of the S3 Algorithm, calculate the average value. The result will be assigned to current_hour_X hour. Reset counter variable. Step 2: Go to Step 2 of S3 Algorithm The KDIGO classification comprises classifying the processed data into a plurality of status of kidney diseases of a user based on KDIGO guidelines. The Kidney Disease Detection process calculates the AKI staging of the patient by applying the KDIGO guidelines or the reason for admission information of the patient at the present hour of the patient. The outcome of the preprocessing step S190 serves as input of KDIGO classification. The Kidney Disease Detection process is to assign only for the current hour the KIDGO Stage that can have the following values: 0; 1; 2; 3; 4 (Persistent AKI). If the reason for admission to the Intensive Care Unit of the patient includes an Acute Kidney Injury disease, then the Final KDIGO Stage will be 2. The final AKI Stage for the patient is calculated following this table: KDIGO Diuresis KDIGO Creatinine Stage Final KDIGO Stage* S Nt.Aa.ge N.A. N.A. N.A. Creatinine Stage Creatinine Stage Urine Output Stage N.A Urine Output Stage Urine Output Stage Creatinine Stage Max(Urine Output Stage, Creatinine Stage) S4 ALGORITHM: KIDNEY DISEASE DETECTION Input: Output from Preprocessing phase Output: Determine the kidney disease status of the patient Step 1: Calculate KDIGO Stage for diuresis by applying the guidelines. Step 2: Calculate KDIGO Stage for creatinine by applying the guidelines Step 3: Determine the persistency of the KDIGO Step 4: Determine the final KDIGO Stage Fig. 3 also depicts a kidney disease event prediction performed by the method for monitoring kidney disease according to embodiments of the present invention. For this the method comprises triggering at least one artificial-intelligence-assisted module which may comprises at least one of: First module, the second module, and Third module. First module may output a risk for onset of AKI (stage 2/3 as defined by KDIGO guidelines) within the next 24 hours, at the current time. The first module may also generate a risk level that indicates a severity of a patient’s status (that is, how bad the status of the patient is), and an explanation of the outcome. In one embodiment, such an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome. For this purpose, the first module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190. The first module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/ FiO2); lactates; age; gender; weight. The first module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time In one embodiment, the first module may also comprise at least one artificial-intelligence- assisted module, which also be referred to as AKI module. Calculated features are sent in input to a machine-learning model trained to predict the risk for onset of AKI (stage 2/3 as defined by KDIGO guidelines) within the next 24 hours. The AKIRA AI module may be applied to the input feature, for example, only if urine output and creatinine values are present. The AKI module may be based on a XGBoost algorithm which is based on a set of decision tree learning algorithms that uses a gradient boosting framework. The output of the model may be a number between 0 and 1, wherein said output may be multiplied by 100 to represent the probability of developing AKI stage 2 or 3 in the following 24 hours. However, it should be understood that the AKI module may be based on a plurality of different algorithm architectures, such as: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network. In a further embodiment, the first module may also generate a risk level which may also be referred to as AKIRA risk level. AKI module may compare its output with a specified threshold, wherein the method may comprise assigning and defining a new risk level variable according to these rules: Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) Moreover, the first module may also automatically generate a list of features, variables, with their weights (expressed in terms of %), that most influenced the output of the AKI module. For this purpose, the first module may execute at least one computer- implemented method comprising at least one of: SHapley Additive exPlanations; Impurity- based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation. The second module may automatically output a risk for onset of Persistent AKI (as defined by KDIGO guidelines). Moreover, the second module may also generate a risk level that a severity of a patient’s status indicates (that is, how bad the status of the patient is) and an explanation of the outcome. In one embodiment, such an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome. For this purpose, the second module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190 calculated. The second module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/FiO2); lactates; age; gender; weight. The second module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time windows of variable length such as from 3 h to 72 h preceding the current hour. In one embodiment, the second module may also comprise at least one artificial-intelligence-assisted module, which also be referred to as Persistent AKI module. Calculated features are sent in input to a machine-learning model trained to predict the risk for onset of Persistent AKI. Persistent AKI module may be applied to the input feature, for example, only if urine output and creatinine values are present. Persistent AKI module may be based on a XGBoost algorithm that is based on a set of decision tree learning algorithms that uses a gradient boosting framework. Model. The output of the model is a number between 0 and 1, and it is multiplied by 100 to represent the probability of developing a Persistent form of AKI during the Intensive Care Unit stay. Persistent AKI module may be based on different algorithm architectures, inter alia, but not limited to: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network; Generate PERSEA Risk level. Persistent AKI module may compare its output with a specified threshold, wherein the method may comprise assigning and defining a new risk level variable according to these rules: Score Risk level N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) Moreover, the second module may also automatically generate a list of features, variables, with their weights (expressed in terms of %), that most influenced the output of the Persistent AKI module. For this purpose, the second module may execute at least one computer-implemented method comprising at least one of: SHapley Additive exPlanations; Impurity-based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation. The third module may automatically output a readiness level of a patient to stop a treatment of continuous renal replacement therapy in intensive care units expressed with values between 0 and 100. Moreover, the third module may also generate a weaning- readiness level that indicates how high is the weaning- readiness of the patient and the explanations of the result. In one embodiment, such an explanation comprises a list of most features to the outcome, i.e., the features that contributed the most or that influenced the most the outcome. For this purpose, the third module receives as input the at least one processed data (comprising a format: hourly time values) obtained from the preprocessing step S190 calculated. The second module may receive processed data comprising clinical parameters comprising at least one of: albumin; blood urea nitrogen (BUN); diastolic pressure, heart rate; hematocrit, hemoglobin; median arterial pressure (MAP); platelets count, serum creatinine; systolic pressure; urine output normalized by adjusted body weight accumulated over preceding hours such over the preceding 6, 12, 24, 48, and/or 96 hours; white blood cells count; total protein; fluid balance; ratio of fraction inspired oxygen and arterial oxygen partial pressure (PaO2/ FiO2); lactates; age; gender; weight. The third module may, for each clinical parameter, extract at least one value of: average, maximum, minimum, difference, and standard deviation, wherein these may be calculated on time windows of variable length such as from 3 h to 240 h. In one embodiment, the third module may also comprise at least one artificial-intelligence- assisted module, which also be referred to as CRRT module. Calculated features are sent in input to a machine-learning model trained to predict the risk for onset of Persistent AKI (stage 2/3 as defined by KDIGO guidelines). CRRT module may be applied to the input feature, for example, only if urine output and creatinine values are present. CRRT model may be based on a XGBoost algorithm that is based on a set of decision tree learning algorithms that uses a gradient boosting framework. Model. The output of the model is a number between 0 and 1, and it is multiplied by 100 to represent the readiness of a patient to stop a treatment of continuous renal replacement therapy in intensive care units. CRRT module may be based on different algorithm architectures, inter alia, but not limited to: Ensemble Decision trees; Random Forest; Gradient boosting decision tree; XGboost; Neural Network; Recurrent Neural Network; Convolutional Neural Network; Generate CRRT Risk level. CRRT module may compare its output with a specified threshold, wherein the method may comprise assigning and defining a new successful weaning probability variable according to these rules: Score Successful weaning probability N.A. N.A. (-1) Score<Threshold/2 Low (0) Score >= Threshold/2 and Score<Threshold Medium (1) Score >= Threshold High (2) Moreover, the third module may also automatically generate a list of features, variables, with their weights (expressed in terms of %), that most influenced the output of the CRRT module. For this purpose, the third module may execute at least one computer- implemented method comprising at least one of: SHapley Additive exPlanations; Impurity- based feature importance; Permutation Importance; Partial dependence plots; Local Interpretable Model-Agnostic Explanations; Individual conditional explanation. Fig. 4 depicts a schematic of a computing device 1000. The computing device 1000 may comprise a computing unit 35, a first data storage unit 30A, a second data storage unit 30B and a third data storage unit 30C. The computing device 1000 can be a single computing device or an assembly of computing devices. The computing device 1000 can be locally arranged or remotely, such as a cloud solution. On the different data storage units 30 different data can be stored, such as the AKI related data on the first data storage 30A, the time stamped data and/or event code data and/or phenotypic data on the second data storage 30B and privacy sensitive data, such as the connection of the before-mentioned data to an individual, on the thirds data storage 30C. Additional data storage can be also provided and/or the ones mentioned before can be combined at least in part. Another data storage (not shown) can comprise data specifying for instance, clinical parameter data. This data can also be provided on one or more of the before-mentioned data storages. The computing unit 35 can access the first data storage unit 30A, the second data storage unit 30B and the third data storage unit 30C through the internal communication channel 160, which can comprise a bus connection 160. The computing unit 30 may be single processor or a plurality of processors, and may be, but not limited to, a CPU (central processing unit), GPU (graphical processing unit), DSP (digital signal processor), APU (accelerator processing unit), ASIC (application-specific integrated circuit), ASIP (application-specific instruction-set processor) or FPGA (field programable gate array). The first data storage unit 30A may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The second data storage unit 30B may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The third data storage unit 30C may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). It should be understood that generally, the first data storage unit 30A (also referred to as encryption key storage unit 30A), the second data storage unit 30B (also referred to as data share storage unit 30B), and the third data storage unit 30C (also referred to as decryption key storage unit 30C) can also be part of the same memory. That is, only one general data storage unit 30 per device may be provided, which may be configured to store the respective encryption key (such that the section of the data storage unit 30 storing the encryption key may be the encryption key storage unit 30A), the respective data element share (such that the section of the data storage unit 30 storing the data element share may be the data share storage unit 30B), and the respective decryption key (such that the section of the data storage unit 30 storing the decryption key may be the decryption key storage unit 30A). In some embodiments, the third data storage unit 30C can be a secure memory device 30C, such as, a self-encrypted memory, hardware-based full disk encryption memory and the like which can automatically encrypt all of the stored data. The data can be decrypted from the memory component only upon successful authentication of the party requiring to access the third data storage unit 30C, wherein the party can be a user, computing device, processing unit and the like. In some embodiments, the third data storage unit 30C can only be connected to the computing unit 35 and the computing unit 35 can be configured to never output the data received from the third data storage unit 30C. This can ensure a secure storing and handling of the encryption key (i.e., private key) stored in the third data storage unit 30C. In some embodiments, the second data storage unit 30B may not be provided but instead the computing device 1000 can be configured to receive a corresponding encrypted share from the database 60. In some embodiments, the computing device 1000 may comprise the second data storage unit 30B and can be configured to receive a corresponding encrypted share from the database 60. The computing device 1000 may comprise a further memory component 140 which may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The memory component 140 may also be connected with the other components of the computing device 1000 (such as the computing component 35) through the internal communication channel 160. Further the computing device 1000 may comprise an external communication component 130. The external communication component 130 can be configured to facilitate sending and/or receiving data to/from an external device (e.g., backup device 10, recovery device 20, database 60). The external communication component 130 may comprise an antenna (e.g., WIFI antenna, NFC antenna, 2G/3G/4G/5G antenna and the like), USB port/plug, LAN port/plug, contact pads offering electrical connectivity and the like. The external communication component 130 can send and/or receive data based on a communication protocol which can comprise instructions for sending and/or receiving data. Said instructions can be stored in the memory component 140 and can be executed by the computing unit 35 and/or external communication component 130. The external communication component 130 can be connected to the internal communication component 160. Thus, data received by the external communication component 130 can be provided to the memory component 140, computing unit 35, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C. Similarly, data stored on the memory component 140, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C and/or data generated by the commuting unit 35 can be provided to the external communication component 130 for being transmitted to an external device. In addition, the computing device 1000 may comprise an input user interface 110 which can allow the user of the computing device 1000 to provide at least one input (e.g., instruction) to the computing device 100. For example, the input user interface 110 may comprise a button, keyboard, trackpad, mouse, touchscreen, joystick and the like. Additionally, still, the computing device 1000 may comprise an output user interface 120 which can allow the computing device 1000 to provide indications to the user. For example, the output user interface 110 may be a LED, a display, a speaker and the like. The output and the input user interface 100 may also be connected through the internal communication component 160 with the internal component of the device 100. The processor may be singular or plural, and may be, but not limited to, a CPU, GPU, DSP, APU, or FPGA. The memory may be singular or plural, and may be, but not limited to, being volatile or non-volatile, such an SDRAM, DRAM, SRAM, Flash Memory, MRAM, F-RAM, or P-RAM. The data processing device can comprise means of data processing, such as, processor units, hardware accelerators and/or microcontrollers. The data processing device 20 can comprise memory components, such as, main memory (e.g., RAM), cache memory (e.g., SRAM) and/or secondary memory (e.g., HDD, SDD). The data processing device can comprise busses configured to facilitate data exchange between components of the data processing device, such as, the communication between the memory components and the processing components. The data processing device can comprise network interface cards that can be configured to connect the data processing device to a network, such as, to the Internet. The data processing device can comprise user interfaces, such as: - output user interface, such as: o screens or monitors configured to display visual data (e.g., displaying graphical user interfaces of railway network status), Fig. 4 depicts a schematic of a computing device 1000. The computing device 1000 may comprise a computing unit 35, a first data storage unit 30A, a second data storage unit 30B and a third data storage unit 30C. The computing device 1000 can be a single computing device or an assembly of computing devices. The computing device 1000 can be locally arranged or remotely, such as a cloud solution. On the different data storage units 30 the different data can be stored, such as the genetic data on the first data storage 30A, the time stamped data and/or event code data and/or phenotypic data on the second data storage 30B and privacy sensitive data, such as the connection of the before-mentioned data to an individual, on the thirds data storage 30C. Additional data storage can be also provided and/or the ones mentioned before can be combined at least in part. Another data storage (not shown) can comprise data specifying for instance, air temperature, rail temperature, position of blades, model of point machine, position of point machine and/or further railway network related information. This data can also be provided on one or more of the before-mentioned data storages. The computing unit 35 can access the first data storage unit 30A, the second data storage unit 30B and the third data storage unit 30C through the internal communication channel 160, which can comprise a bus connection 160. The computing unit 30 may be single processor or a plurality of processors, and may be, but not limited to, a CPU (central processing unit), GPU (graphical processing unit), DSP (digital signal processor), APU (accelerator processing unit), ASIC (application-specific integrated circuit), ASIP (application-specific instruction-set processor) or FPGA (field programable gate array). The first data storage unit 30A may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The second data storage unit 30B may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The third data storage unit 30C may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). It should be understood that generally, the first data storage unit 30A (also referred to as encryption key storage unit 30A), the second data storage unit 30B (also referred to as data share storage unit 30B), and the third data storage unit 30C (also referred to as decryption key storage unit 30C) can also be part of the same memory. That is, only one general data storage unit 30 per device may be provided, which may be configured to store the respective encryption key (such that the section of the data storage unit 30 storing the encryption key may be the encryption key storage unit 30A), the respective data element share (such that the section of the data storage unit 30 storing the data element share may be the data share storage unit 30B), and the respective decryption key (such that the section of the data storage unit 30 storing the decryption key may be the decryption key storage unit 30A). In some embodiments, the third data storage unit 30C can be a secure memory device 30C, such as, a self-encrypted memory, hardware-based full disk encryption memory and the like which can automatically encrypt all of the stored data. The data can be decrypted from the memory component only upon successful authentication of the party requiring to access the third data storage unit 30C, wherein the party can be a user, computing device, processing unit and the like. In some embodiments, the third data storage unit 30C can only be connected to the computing unit 35 and the computing unit 35 can be configured to never output the data received from the third data storage unit 30C. This can ensure a secure storing and handling of the encryption key (i.e., private key) stored in the third data storage unit 30C. In some embodiments, the second data storage unit 30B may not be provided but instead the computing device 1000 can be configured to receive a corresponding encrypted share from the database 60. In some embodiments, the computing device 1000 may comprise the second data storage unit 30B and can be configured to receive a corresponding encrypted share from the database 60. The computing device 1000 may comprise a further memory component 140 which may be singular or plural, and may be, but not limited to, a volatile or non-volatile memory, such as a random-access memory (RAM), Dynamic RAM (DRAM), Synchronous Dynamic RAM (SDRAM), static RAM (SRAM), Flash Memory, Magneto-resistive RAM (MRAM), Ferroelectric RAM (F-RAM), or Parameter RAM (P-RAM). The memory component 140 may also be connected with the other components of the computing device 1000 (such as the computing component 35) through the internal communication channel 160. Further the computing device 1000 may comprise an external communication component 130. The external communication component 130 can be configured to facilitate sending and/or receiving data to/from an external device (e.g., backup device 10, recovery device 20, database 60). The external communication component 130 may comprise an antenna (e.g., WIFI antenna, NFC antenna, 2G/3G/4G/5G antenna and the like), USB port/plug, LAN port/plug, contact pads offering electrical connectivity and the like. The external communication component 130 can send and/or receive data based on a communication protocol which can comprise instructions for sending and/or receiving data. Said instructions can be stored in the memory component 140 and can be executed by the computing unit 35 and/or external communication component 130. The external communication component 130 can be connected to the internal communication component 160. Thus, data received by the external communication component 130 can be provided to the memory component 140, computing unit 35, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C. Similarly, data stored on the memory component 140, first data storage unit 30A and/or second data storage unit 30B and/or third data storage unit 30C and/or data generated by the commuting unit 35 can be provided to the external communication component 130 for being transmitted to an external device. In addition, the computing device 1000 may comprise an input user interface 110 which can allow the user of the computing device 1000 to provide at least one input (e.g., instruction) to the computing device 100. For example, the input user interface 110 may comprise a button, keyboard, trackpad, mouse, touchscreen, joystick and the like. Additionally, still, the computing device 1000 may comprise an output user interface 120 which can allow the computing device 1000 to provide indications to the user. For example, the output user interface 110 may be a LED, a display, a speaker and the like. The output and the input user interface 100 may also be connected through the internal communication component 160 with the internal component of the device 100. The processor may be singular or plural, and may be, but not limited to, a CPU, GPU, DSP, APU, or FPGA. The memory may be singular or plural, and may be, but not limited to, being volatile or non-volatile, such an SDRAM, DRAM, SRAM, Flash Memory, MRAM, F-RAM, or P-RAM. The data processing device can comprise means of data processing, such as, processor units, hardware accelerators and/or microcontrollers. The data processing device 20 can comprise memory components, such as, main memory (e.g., RAM), cache memory (e.g., SRAM) and/or secondary memory (e.g., HDD, SDD). The data processing device can comprise busses configured to facilitate data exchange between components of the data processing device, such as, the communication between the memory components and the processing components. The data processing device can comprise network interface cards that can be configured to connect the data processing device to a network, such as, to the Internet. The data processing device can comprise user interfaces, such as: ▪ output user interface, such as: o screens or monitors configured to display visual data (e.g., displaying graphical user interfaces of railway network status), o speakers configured to communicate audio data (e.g., playing audio data to the user), ▪ input user interface, such as: o camera configured to capture visual data (e.g., capturing images and/or videos of the user), o microphone configured to capture audio data (e.g., recording audio from the user), o keyboard configured to allow the insertion of text and/or other keyboard commands (e.g., allowing the user to enter text data and/or other keyboard commands by having the user type on the keyboard) and/or trackpad, mouse, touchscreen, joystick – configured to facilitate the navigation through different graphical user interfaces of the questionnaire. The data processing device can be a processing unit configured to carry out instructions of a program. The data processing device can be a system-on-chip comprising processing units, memory components and busses. The data processing device can be a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer. The data processing device can be a server, either local and/or remote. The data processing device can be a processing unit or a system-on-chip that can be interfaced with a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer and/or user interface (such as the upper-mentioned user interfaces). - input user interface, such as: o camera configured to capture visual data (e.g., capturing images and/or videos of the user), o microphone configured to capture audio data (e.g., recording audio from the user), o keyboard configured to allow the insertion of text and/or other keyboard commands (e.g., allowing the user to enter text data and/or other keyboard commands by having the user type on the keyboard) and/or trackpad, mouse, touchscreen, joystick – configured to facilitate the navigation through different graphical user interfaces of the questionnaire. The data processing device can be a processing unit configured to carry out instructions of a program. The data processing device can be a system-on-chip comprising processing units, memory components and busses. The data processing device can be a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer. The data processing device can be a server, either local and/or remote. The data processing device can be a processing unit or a system-on-chip that can be interfaced with a personal computer, a laptop, a pocket computer, a smartphone, a tablet computer and/or user interface (such as the upper-mentioned user interfaces). Fig. 5 depicts a chart outputted by the present invention, representing the acquired measurements of clinical parameters with respect to their corresponding urgency level zones. In simple words, the measurements acquired by the invention is presented in a chart wherein the measurements are also presented in tandem with the “zone” in which it is categorized. For instance, these zones can represent the urgency level of Renal Replacement Therapy (RRT in Figure. 5) such as No RRT indication, RRT indication and Urgent RRT indication. It should be understood that in certain embodiments, these zones are not related to an RRT urgency level, but any urgency level that can correspond to the measurements taken by the invention, wherein said urgency levels may be traced back to the standardized database. Fig. 6 depicts chart outputted by the present invention, representing the scores calculated by the system as well as a note 500 inputted into the system by an authorized user, with respect to time. In simple terms, an authorized user may input at least one note 500 at a certain time and date relative to the score calculated by the system at said time and date. Said note may be displayed with the scores calculated with respect to time to at least one authorized user. While in the above, a preferred embodiment has been described with reference to the accompanying drawings, the skilled person will understand that this embodiment was provided for illustrative purpose only and should by no means be construed to limit the scope of the present invention, which is defined by the claims. Whenever a relative term, such as “about”, “substantially” or “approximately” is used in this specification, such a term should also be construed to also include the exact term. That is, e.g., “substantially straight” should be construed to also include “(exactly) straight”. Whenever steps were recited in the above or also in the appended claims, it should be noted that the order in which the steps are recited in this text may be accidental. That is, unless otherwise specified or unless clear to the skilled person, the order in which steps are recited may be accidental. That is, when the present document states, e.g., that a method comprises steps (A) and (B), this does not necessarily mean that step (A) precedes step (B), but it is also possible that step (A) is performed (at least partly) simultaneously with step (B) or that step (B) precedes step (A). Furthermore, when a step (X) is said to precede another step (Z), this does not imply that there is no step between steps (X) and (Z). That is, step (X) preceding step (Z) encompasses the situation that step (X) is performed directly before step (Z), but also the situation that (X) is performed before one or more steps (Y1), …, followed by step (Z). Corresponding considerations apply when terms like “after” or “before” are used.

Claims

Claims 1. A method for monitoring kidney function, the method comprising acquiring at least one raw data from at least one data source, preprocessing the at least one raw data to automatically generate at least one processed data, classifying the at least one processed data into at least one kidney functioning status, and triggering at least one artificial-intelligence-assisted module, wherein the triggering of the at least one artificial-intelligence-assisted module is based on the at least one kidney functioning status.
2. The method according to the preceding claim, wherein the preprocessing step comprises at least one of performing at least one unit of measure conversion; discarding at least one out-of-range value; processing at least one diuresis data; processing at least one blood chemistry data; and processing at least one physiological data.
3. The method according to any of the preceding claims, wherein the at least one artificial-intelligence assisted module comprises at least one of: first module, second module, and third module.
4. The method according to any of the preceding claims, wherein the classifying step comprises performing the classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage, wherein the method comprises determining which of the at least one artificial-intelligence-assisted module to trigger, wherein determining which at least one artificial-intelligence-assisted module to trigger is based on the KDIGO stage, wherein the at least one kidney functioning status comprises the KDIGO stage.
5. The method according to the preceding claim, wherein when the least one kidney functioning status comprises data indicating at least one of a non-applicable stage, no artificial-intelligence-assisted module is triggered; a KDIGO stage 0 or 1, the first module is triggered; a KDIGO stage 2 or 3, the second module is triggered; a currently started dialysis treatment, the third module is triggered.
6. The method according to any of the preceding claims, wherein the method comprises predicting at least one kidney disease event, wherein the predicting of the least one kidney disease event is based on the at least one kidney functioning status, wherein the predicting of the at least one kidney disease event is performed by the at least one artificial-intelligence assisted module.
7. The method according to any of the preceding claims, wherein the method comprises at least one of: predicting a risk of a patient of developing AKI, wherein the method comprises automatically generating an AKI risk level, wherein the AKI risk level expresses a severity of a patient’s renal health status; predicting a risk for onset of persistent AKI, automatically generating a persistent AKI risk level, wherein a persistent AKI risk level, wherein the persistent AKI risk level expresses a severity of the patient’s renal health status; predicting a future kidney recovery trajectory, wherein the method comprises outputting at least one decision-supporting-data based on the predicting of the future kidney recovery trajectory; and generating a probability CRRT index comprising a CRRT risk level, wherein the probability CRRT index is based on the predicting of the future recovery trajectory.
8. The method according to the preceding claim and with the features of claim 3, wherein predicting of the risk for onset of AKI is performed by the first module; predicting of the risk for onset of persistent AKI is performed by the second module; predicting of the future kidney recovery trajectory is performed by the third module; and generating of the probability CRRT index is performed by the third module.
9. A system for monitoring kidney function, the method comprising an acquiring component configured to acquire at least one raw data from at least one data source, a processing component configured to at least preprocess the at least one raw data to automatically generate at least one processed data, a classifying component configured to classify the at least one processed data into at least one kidney functioning status, and a triggering component configured to trigger at least one artificial-intelligence- assisted module, wherein the triggering component is configured to trigger the at least one artificial- intelligence-assisted module based on the at least one kidney functioning status.
10. The system according to the preceding claim, wherein the processing component is configured to perform at least one of at least one unit of measure conversion; discard at least one out-of-range value; process at least one diuresis data; process at least one blood chemistry data; and process at least one physiological data.
11. The system according to any of the preceding system claims, wherein the at least one artificial-intelligence assisted module comprises to at least one of: first module, second module, and third module.
12. The system according to any of the preceding system claims, wherein the classifying component is configured to perform a classifying step based on at least one Kidney Disease Improving Global Outcomes (KDIGO) classification to output a KDIGO stage, wherein the system is configured to determine which of the at least one artificial-intelligence-assisted module to trigger, wherein the system is configured to determine which at least one artificial-intelligence-assisted module to trigger based on the KDIGO stage, wherein the at least one kidney functioning status comprises the KDIGO stage.
13. The system according to the preceding claim, wherein when the least one kidney functioning status comprises data indicating the value of the KDIGO stage is at least one of a non-applicable stage, the system is configured to trigger none artificial- intelligence-assisted module; 0 or 1, the system is configured to trigger the first module; 2 or 3, the system is configured to trigger the second module; and indicating that a currently started dialysis treatment, the system is configured to trigger the third module.
14. The system according to any of the preceding system claims, wherein the system is configured to predict at least one kidney disease event, wherein the system is configured to predict the at least one kidney disease event based on the at least one kidney functioning status, wherein the system is configured to predict the at least one kidney disease event by means of the at least one artificial-intelligence assisted module.
15. The system according to any of the preceding system claims and with the features of claim 11, wherein the first module is configured to predict a risk of a patient of developing AKI; the second module is configured to predict of the risk for onset of persistent AKI; and the third module is configured to predict of the future kidney recovery trajectory and to generate a probability CRRT index comprising a risk level.
PCT/EP2024/066988 2023-06-20 2024-06-18 System and method for detection and prediction of kidney disease events Pending WO2024261001A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP23180428.7 2023-06-20
EP23180428 2023-06-20

Publications (1)

Publication Number Publication Date
WO2024261001A1 true WO2024261001A1 (en) 2024-12-26

Family

ID=86904044

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2024/066988 Pending WO2024261001A1 (en) 2023-06-20 2024-06-18 System and method for detection and prediction of kidney disease events

Country Status (1)

Country Link
WO (1) WO2024261001A1 (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180110455A1 (en) 2015-04-15 2018-04-26 The Johns Hopkins University System and urine sensing devices for and method of monitoring kidney function
US20200057076A1 (en) 2018-05-24 2020-02-20 Renibus Therapeutics, Inc. Methods of treating patients at risk for renal injury and renal failure
CN110914915A (en) 2017-07-14 2020-03-24 费森尤斯医疗保健控股公司 Prescription compatibility check for medical devices
EP3918610A1 (en) 2019-01-30 2021-12-08 Politecnico Di Torino A monitoring and prediction system of diuresis for the calculation of kidney failure risk, and the method thereof
US20220383998A1 (en) 2014-06-13 2022-12-01 University Hospitals Cleveland Medical Center Artificial-intelligence-based facilitation of healthcare delivery
US20220390467A1 (en) 2019-10-28 2022-12-08 Children's Hospital Medical Center Methods relating to sepsis associated acute kidney injury
US20220406437A1 (en) 2021-06-18 2022-12-22 Fresenius Medical Care Holdings, Inc. Methods and systems for determining and providing renal therapy

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220383998A1 (en) 2014-06-13 2022-12-01 University Hospitals Cleveland Medical Center Artificial-intelligence-based facilitation of healthcare delivery
US20180110455A1 (en) 2015-04-15 2018-04-26 The Johns Hopkins University System and urine sensing devices for and method of monitoring kidney function
CN110914915A (en) 2017-07-14 2020-03-24 费森尤斯医疗保健控股公司 Prescription compatibility check for medical devices
US20200057076A1 (en) 2018-05-24 2020-02-20 Renibus Therapeutics, Inc. Methods of treating patients at risk for renal injury and renal failure
EP3918610A1 (en) 2019-01-30 2021-12-08 Politecnico Di Torino A monitoring and prediction system of diuresis for the calculation of kidney failure risk, and the method thereof
US20220095977A1 (en) * 2019-01-30 2022-03-31 Politecnico Di Torino Monitoring and prediction system of diuresis for the calculation of kidney failure risk, and the method thereof
US20220390467A1 (en) 2019-10-28 2022-12-08 Children's Hospital Medical Center Methods relating to sepsis associated acute kidney injury
US20220406437A1 (en) 2021-06-18 2022-12-22 Fresenius Medical Care Holdings, Inc. Methods and systems for determining and providing renal therapy

Similar Documents

Publication Publication Date Title
US8595159B2 (en) Predicting near-term deterioration of hospital patients
Zhao et al. Early prediction of sepsis based on machine learning algorithm
US20240321447A1 (en) Method and System for Personalized Prediction of Infection and Sepsis
US20170249434A1 (en) Multi-format, multi-domain and multi-algorithm metalearner system and method for monitoring human health, and deriving health status and trajectory
US20210153776A1 (en) Method and device for sizing an interatrial aperture
JP7751588B2 (en) Medical machine learning system and method
CN119339930B (en) Information digital management system based on severe medical science
US20190392952A1 (en) Computer-implemented methods, systems, and computer-readable media for diagnosing a condition
TWI796228B (en) Acute kidney injury predicting system and method thereof
US20200113503A1 (en) Method For Predicting Of Mortality Risk Or Sepsis Risk And Device For Predicting Of Mortality Risk Or Sepsis Risk Using The Same
CN117112729B (en) Medical resource docking method and system based on artificial intelligence
US20140372146A1 (en) Determining a physiologic severity of illness score for patients admitted to an acute care facility
CN118765173A (en) Methods and systems for sepsis risk stratification
WO2024261001A1 (en) System and method for detection and prediction of kidney disease events
KR20220005791A (en) Delirium prediction method and apparatus
US20190088369A1 (en) Determining patient status based on measurable medical characteristics
TWI803893B (en) Artificial intelligence assisted medical diagnosis method for sepsis and system thereof
CN117524477A (en) MODS dynamic early warning method and system based on noninvasive parameters
TWM631259U (en) Acute kidney injury predicting system
Agrawal et al. DiabChatbot: A Machine Learning Chatbot for Early Diagnosis of Type II/Mellitus Diabetes and Diet Recommendation in an Indian Scenario
US20250325237A1 (en) Clinical education method and system
US20250372214A1 (en) Systems and methods for maintaining data integrity in a health analysis platform by assessing and modifying physiological measurements based on filtered healthcare data
Mahmoud et al. Short-Term and Long-Term Readmission Prediction in Uncontrolled Diabetic Patients using Machine Learning Techniques.
Ri et al. Simulating a Specialist's Treatment Experience for Hypertension Using Deep Neural Networks
Shirwaikar et al. Design framework for a data mart in the neonatal intensive care unit

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24732707

Country of ref document: EP

Kind code of ref document: A1