[go: up one dir, main page]

WO2024173096A1 - Stratification dynamique des risques basée sur une simulation - Google Patents

Stratification dynamique des risques basée sur une simulation Download PDF

Info

Publication number
WO2024173096A1
WO2024173096A1 PCT/US2024/014572 US2024014572W WO2024173096A1 WO 2024173096 A1 WO2024173096 A1 WO 2024173096A1 US 2024014572 W US2024014572 W US 2024014572W WO 2024173096 A1 WO2024173096 A1 WO 2024173096A1
Authority
WO
WIPO (PCT)
Prior art keywords
patient
time
ingestion
threshold
metric
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.)
Ceased
Application number
PCT/US2024/014572
Other languages
English (en)
Inventor
Gary Marc EICHENBAUM
Brett Alyn HOWELL
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.)
Simulations Plus Inc
Kenvue Brands LLC
Original Assignee
Johnson and Johnson Consumer Inc
Simulations Plus Inc
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 Johnson and Johnson Consumer Inc, Simulations Plus Inc filed Critical Johnson and Johnson Consumer Inc
Publication of WO2024173096A1 publication Critical patent/WO2024173096A1/fr
Anticipated expiration legal-status Critical
Ceased 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G06N7/06—Simulation on general purpose computers
    • 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
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • 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
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • 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
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Definitions

  • over-the-counter pain medications e.g., analgesics
  • acetaminophen overdose is one of the most common poisonings.
  • An overdose occurs when a person takes more than the normal or recommended amount of medication.
  • An overdose may be accidental or intentional.
  • Risk stratification techniques allow health care providers to categorize overdose patients into high- risk and low-risk groups. Risk stratification may help health care providers make treatment decisions. If a patient suffering from acetaminophen overdose is not properly stratified, the patient may not receive appropriate treatment (e.g., the patient may receive inadequate treatment, or may not receive treatment at all).
  • the present disclosure relates to a device and method for determining suitable treatment for patients experiencing acetaminophen overdose.
  • the present disclosure relates to the use of machine learning and/ or statistical techniques to accurately predict a risk level and/ or treatment response of such patients.
  • An example device may include a processor configured to perform one or more actions.
  • the processor may receive patient data indicative of an acetaminophen overdose, a time associated with acetaminophen ingestion, and an aminotransferase (AT) product level.
  • AT aminotransferase
  • a metric indicative of effectiveness of an acetaminophen overdose treatment e.g., N-Acetyl Cysteine (NAC), activated charcoal, and/ or, optionally, other treatment(s)
  • an acetaminophen overdose treatment e.g., N-Acetyl Cysteine (NAC), activated charcoal, and/ or, optionally, other treatment(s)
  • NAC N-Acetyl Cysteine
  • Prognosis information may be output based on the metric.
  • the patient data may further indicate a second time associated with the AT product level.
  • the AT product level may be a first AT product level at a first time.
  • the patient data may further indicate a second AT product level at a second time.
  • the metric may be determined based on a relative difference between the first AT product level at the first time and the second AT product level at the second time.
  • a lookup table may be generated based on the cellular simulation.
  • the lookup table may comprise a plurality of datasets. Each dataset may comprise a relative comparison of the dataset to the metric.
  • the device may determine that the patient data corresponds to a matching dataset in the plurality of datasets.
  • the prognosis information may be determined based on the relative comparison of the matching dataset to the metric.
  • Determining the metric may comprise determining a patient risk.
  • the device may determine a time since ingestion indicative of a span of time between the time associated with acetaminophen ingestion and a time associated with the patient presenting at a medical facility.
  • the patient risk may be categorized as low if: the time since ingestion is equal to or less than a first timc-sincc-ingcstion threshold; the time since ingestion is between the first time-since-ingestion threshold and a second time-since-ingestion threshold, and the AT product level of the patient is less than a first AT product threshold; or the time since ingestion is equal to or greater than the second time-since- ingestion threshold, and the AT product level of the patient is less than a second AT product threshold.
  • the patient risk may be categorized as high if: the time since ingestion is between the first time- since-ingestion threshold and the second time-since-ingestion threshold, and the AT product level of the patient is greater than the first AT product threshold; or the time since ingestion is greater than the second time-since-ingestion threshold, and the AT product level of the patient is greater than the second AT product threshold.
  • FIG. 1 illustrates an example simulation and generation of a lookup table.
  • FIG. 2 is a block diagram of an example acetaminophen (APAP) overdose treatment assistant device.
  • APAP acetaminophen
  • FIGs. 3-9 illustrate user interface (UI) examples for an APAP overdose treatment assistant device.
  • FIG. 10 is a flow diagram illustrating an example computer-implemented method.
  • the Rumack-Matthew nomogram may be used to stratify the risk of acetaminophen (APAP) overdose patients.
  • the Rumack-Matthew nomogram is based on concentration (e.g., amount of APAP ingested) and time since ingestion. Because these values are typically patient-reported, doctors may have difficulty determining an accurate concentration and/or time since ingestion. For example, a patient may misremember or lie about the amount of the drug taken or the time at which the drug was ingested. Performing risk assessment based on measured biomarkers may remove some possible inaccuracies caused by relying on reported data.
  • the Rumack-Matthew nomogram compares a patient to an average of all patients. However, the Rumack-Matthew nomogram does not take into account specific risk factors associated with the patient being treated (e.g., history of alcohol abuse, obesity, etc.). The Rumack-Matthew nomogram may not be applicable if ingestion has occurred less than 4 hours ago, or more than 24 hours ago, which limits its applicability.
  • the Rumack-Matthew nomogram aids clinicians in determining whether a patient should receive N-Acetyl Cysteine (NAC) treatment
  • the nomogram does not address when to stop treatment. Instead, a clinician manually tracks biomarkcr values and performs calculations to determine when to stop the treatment.
  • the Rumack-Matthew nomogram is only applicable to NAC, not other therapies or treatments of APAP overdose.
  • the health risk of patients that are believed to have overdosed on APAP may be dynamically stratified.
  • a simulation device may be used to characterize a patient’s risk based on a simulation of the patient’s liver’s reaction to the overdose (and/or an overdose treatment).
  • the risk stratification by such a device may be more accurate compared to the Rumack-Matthew Nomogram.
  • the device may use an algorithm that takes into account risk factors associated with the patient being treated.
  • the device may use a physiology-based model. For example, the device may consider biometric data such as the gender, age, and/ or weight of the patient. For example, the device may consider the patient’s reduced liver function (e.g., due to alcoholism) and/or other such risk factors.
  • the device may include a simulator, as illustrated in FIG. 1.
  • the simulator may simulate a plurality of cells.
  • the plurality of cells may be a particular type of cell (e.g., liver cells).
  • the simulator may simulate an organ (e.g., a liver) from the plurality of cells.
  • the simulator may simulate a drug (e.g., acetaminophen) contacting a portion of the cells.
  • the simulator may simulate how the cells and/ or organ react to the drug.
  • the simulator may perform a simulation of liver cell damage caused by the acetaminophen overdose.
  • the simulator may be able to determine the number of markers that the cells and/ or organ are expected to release into the blood stream. The number of markers may be dependent on the amount of the drug that contacted the cells. The number of markers may correspond to an injury level of the cells and/ or organ.
  • the simulation may include a cellular-level and/or tissue-level simulation of liver function (e.g., before and/ or after treatment, if any).
  • the simulation may include a computer-based model of cellular dynamics, including elements such as nucleic acids, proteins, carbohydrates, ions, pH, temperature, pressure, electrical signals, and/or the like.
  • the simulation may incorporate a modelling of cellular and/ or tissue pathways and/ or reactions.
  • the simulator may include one or more tools associated with cellular and/ or tissue pathways and/ or reactions, such as PathFinder, BioJAKE, ElecticArc, BioPath, Pathway Browser, and/ or the like.
  • example simulated cellular and/or tissue pathways and/ or reactions may include: liver injury from reactive metabolites generated by APAP, associated biomarker responses indicating various levels of liver injury and/ or loss of tunction and/ or recovery processes, drug concentration predictions associated with various dose levels and/or levels of liver injury, interception of liver injury and/ or recovery pathways by exogenous drug(s) or therapeutic options to improve patient health (e.g., such as to speed up liver cell regeneration, block cell death, or maintain cell function), and/or dose and time information connected to biomarker/ response/ concentration predictions.
  • the simulation may include one or more mathematical representations of cellular and/ or tissue function.
  • the mathematical representations may address functions such as DNA replication and repair, transcription, translation, energy metabolism, cell divisions, chromatin modeling, signaling pathways, membrane transport (including, for example, ion channels, pumps, nutrients, and/or the like), intracellular molecular trafficking, cell membrane dynamics, metabolic pathways, and/or the like.
  • the simulation may include software components suitable for depicting cellular and/ or tissue behavior over time.
  • Example software components may include quantitative system toxicology software such as DIEIsym, RENAsym, Certera’s Cardiac Safety 7 Simulator (CSS), and/or the like.
  • the simulator may be calibrated using a plurality of datasets.
  • the datasets may 7 include biometric data, information about risk factors, and/ or any other relevant information for determining how a patient’s organ (s) will react to a drug overdose.
  • the simulator may generate a lookup table (e.g., based on the cellular simulation).
  • the lookup table may include a plurality of datasets 125.
  • each row in the lookup table may represent a dataset 125.
  • the datasets 125 may 7 each include a different combination of patient health information (e.g., drug dosage, biometric data, risk factors, etc.).
  • Each dataset 125 may include a risk level associated with that combination of patient health information.
  • a dataset may indicate that a patient is 26 years old, male, 200 pounds, has a healthy liver, and ingested a relatively small dose of APAP (e.g., 7.5 grams).
  • the dataset may categorize the patient as low risk (e.g., as having a low risk of permanent injury or death).
  • a dataset may indicate that a patient is 50 years old, male, 120 pounds, has alcohol-related liver disease, and ingested a relatively high dose of APAP (e.g., 20 grams).
  • the dataset may categorize the patient as high risk (e.g., likely to die from the overdose).
  • the datasets in the lookup table may include other patient health information than those mentioned above.
  • the dataset may 7 include other patient health information such as time of presentation after overdose, levels of APAP in the blood stream, blood or blood component levels of alanine aminotransferase (ALT), blood or blood component levels of aspartate aminotransferase (AST), dosage amount, International Normalized Ratio (INR), blood or blood component levels of bilirubin, and/ or other datapoints relevant to determining liver health.
  • the datasets 125 of the lookup table may be fixed (e.g., static).
  • the datasets 125 of the lookup table may be updated over time.
  • the datasets 125 of the lookup table may be updated periodically.
  • the lookup table may be updated with additional datasets whenever new datasets are run through the simulator.
  • the device may determine a metric indicative of effectiveness of an acetaminophen overdose treatment (e.g., NAC, activated charcoal, and/ or other treatment(s)) for the patient based on patient data and the cellular simulation.
  • the metric may indicate liver health risk of the patient. Determining the metric may involve determining a patient risk.
  • the metric may include one or more thresholds (e.g., risk stratification thresholds).
  • patient data may be compared to the threshold to determine whether the patient risk (e.g., for liver failure) is high or low.
  • the device may receive inputs 130.
  • the inputs 130 may include, for example, patient data of a patient who is currently being treated for an APAP overdose.
  • the inputs 130 may indicate, for example, an acetaminophen overdose, a time associated with acetaminophen ingestion, and an aminotransferase (AT) product level.
  • the inputs 130 may indicate a second time associated with the AT product level.
  • the time associated with the acetaminophen overdose may be reported by the patient.
  • the time associated with acetaminophen ingestion may be estimated based on the AT product level and an amount of acetaminophen ingested reported by the patient.
  • the device may adaptively update the risk assessment based on new data.
  • the device may update the risk assessment during and/or after treatment. This is in contrast to the Rumack-Matthew nomogram, which is fixed in time and addresses (e.g., only addresses) the first assessment prior to treatment.
  • the AT product level may be determined based on, for example, a product of the APAP blood concentration level of the patient (e.g., at the time of presentation to a medical facility) times blood or blood component levels of ALT.
  • the device may determine that the APAP blood concentration level of the patient (e.g., indicated by the inputs 130) is below a minimum APAP -bloodconcentration threshold.
  • the minimum APAP-blood-concentration threshold may be (e.g., may be set to) 5 mg/L.
  • the device may set the patient’s APAP blood concentration value to 5 mg/L (e.g., instead of using the APAP blood concentration indicated by the inputs 130).
  • Using a minimum APAP-blood-concentration threshold may allow a health care provider to more accurately determine the risk of a patient (e.g., and properly treat the patient) that has a low APAP blood concentration at the time of presentation at a health care facility.
  • the device may compare the inputs 130 to one or more of the datasets 125. The device may determine that one of the datasets 125 matches the inputs 130. For example, the device may determine that the inputs 130 correspond to datapoints in a matching dataset 140.
  • the AT product level indicated by the inputs 130 may be a first AT product level at a first time. In some examples, the inputs 130 may further indicate a second AT product level at a second time.
  • the device may, for example, determine a relative difference between the first AT product level at the first time and the second AT product level at the second time. The device may determine that the relative difference matches a relative difference indicated by the matching dataset 140.
  • the metric indicative of effectiveness of an acetaminophen overdose treatment e.g., NAC, activated charcoal, and/ or, optionally, other treatment(s)
  • an acetaminophen overdose treatment e.g., NAC, activated charcoal, and/ or, optionally, other treatment(s)
  • the device may output prognosis information associated with the matching dataset 140.
  • the inputs 130 may match the datapoints in a first set of columns of the matching dataset 140.
  • the last column of each dataset 125 may include the prognosis information associated with the corresponding dataset 125.
  • the device may output, at 150, the prognosis information associated with the matching dataset 140.
  • the prognosis information may comprise a risk level that the patient will have acute liver injury or that the patient will die.
  • the prognosis information may include an indication that the patient should receive a treatment other than NAC treatment.
  • the prognosis information may include a risk of the patient (e.g., a risk for liver failure).
  • the risk of the patient may be determined using the determined metric (e.g., risk threshold).
  • a risk of the patient based on the patient data e.g., the inputs 130
  • a time since ingestion e.g., indicative of a span of time between the time associated with acetaminophen ingestion and a time associated with the patient presenting at a medical facility
  • a time since ingestion e.g., indicative of a span of time between the time associated with acetaminophen ingestion and a time associated with the patient presenting at a medical facility
  • the patient risk may be categorized as low (e.g., below the metric) if: the time since ingestion is equal to or less than a first time-since-ingestion threshold; the time since ingestion is between the first time-since-ingestion threshold and a second time-since-ingestion threshold, and the AT product level of the patient is less than a first AT product threshold; or the time since ingestion is equal to or greater than the second time-since-ingestion threshold, and the AT product level of the patient is less than a second AT product threshold.
  • the patient risk may be categorized as high (e.g., above the metric) if: the time since ingestion is between the first time-since- ingestion threshold and the second time-since-ingestion threshold, and the AT product level of the patient is greater than the first AT product threshold; or the time since ingestion is greater than the second time-since-ingestion threshold, and the AT product level of the patient is greater than the second AT product threshold.
  • the device may consider whether additional substances (e.g., alcohol and/or opiates) were ingested by the patient at the time of overdose.
  • the device may consider the form of the drug that was ingested. For example, the device may determine that the drug ingested was in the form of a slow-release capsule. The device may consider whether the patient took a single dose or multiple doses over time.
  • the device may be configured to receive multiple inputs.
  • the inputs may include one or more of: time of presentation after overdose, levels of APAP in blood stream, ALT levels, AST levels, dosage amount, INR, bilirubin levels, and/ or the like.
  • the inputs may include updated information collected during the patient’s treatment.
  • FTG. 2 is a block diagram of an example APAP overdose treatment assistant device 202.
  • the APAP overdose treatment assistant device 202 (also referred to herein as the “device 202”) may include a simulation module 204, a lookup table module 206, a processor 208, a display 210, an interface module 212, and/ or the like.
  • the simulation module 204 may be configured to perform the simulator operations as discussed with respect to FIG. 1.
  • the lookup table module 206 may be configured to generate and/ or store the lookup table with datasets from the simulation module.
  • the simulation module 204 and/ or the lookup table module 206 may be part of the processor 208.
  • the processor 208 may perform functions such as, for example, data retrieval from other modules.
  • the display 210 may be an interactive display (e.g., such that the display 210 includes the interface module 212).
  • the display 210 may display outputs from the simulation module 204 and/ or the lookup table module 206.
  • the display 210 may display prompts to request information from external sources (e.g., from a health care provider).
  • the interface module 212 may be in contact with a human interface device 214, one or more surgical instrument(s) 216, and/ or one or more surgical hubs 218.
  • the interface module 212 may be in communication with an electronic medical records (EMR) system 220.
  • EMR electronic medical records
  • the EMR system 220 may be external from the device 202.
  • the EMR system 220 may include an interface module 222, an authentication and verification module 224, a security module 226, a data removal module, and/ or a data processing module 230.
  • the authentication and verification module 224 may perform various functions such as, for example, authenticating whether a person is allowed to access medical records in the EMR system 220.
  • the security module 226 may perform security functions such as, for example, encrypting and/or password protecting the medical records in the EMR system 220.
  • the data removal module 228 may remove data from the EMR system 220.
  • the data processing module 230 may perform data processing functions such as, for example, data storage and retrieval.
  • the interface module 222 may allow the EMR system 220 to communicate (e.g., exchange data) with external systems.
  • the interface module 222 may interface with an external surgical data storage system 232.
  • the device 202 may obtain the mput(s) from an EAIR system 220 or another system containing the patient’s record. In some examples, the mput(s) may be entered manually.
  • the device 202 may have an interactive display screen (e.g., the display 210).
  • the interactive display screen may prompt a health care provider for information about the patient. For example, the interactive display screen may display questions for a health care provider to answer. For example, one question may ask whether the patient took one dose ot a drug or multiple doses.
  • the health care provider may input patient health information into the device without the device 202 requesting the information.
  • the device 202 may display (e.g., on the interactive display screen) the determined risk level of the patient.
  • the device 202 may give recommendations to the health care provider based on the determined risk level.
  • the device 202 may be configured to identify patients who would benefit from (e.g., further) intervention/treatment(s).
  • the device 202 may determine that the patient would benefit from NAC treatment, activated charcoal, and/ or other/ additional treatment(s) .
  • the device 202 may determine that the patient could benefit from treatment (e.g., using another pharmaceutical).
  • the device 202 may determine that the patient should be transferred to a different treatment facility (e.g., that may be better suited to treat patients at the determined risk level).
  • the device 202 may determine whether the patient would benefit from a liver transplant.
  • the device 202 may predict the dose amount ingested by the patient based on the patient health information.
  • the device 202 may determine that (e.g., further) treatment(s) would benefit the patient.
  • the device 202 may determine how long a patient should receive the (e.g., further) treatment(s) .
  • the determination may be based on a simulation of the effects of the treatment(s) on the organ (e.g., the effects of NAC, activated charcoal, and/or other treatment ⁇ )) .
  • the device 202 may determine how long the patient should remain in the hospital and/or be monitored by a health care provider. For example, the device 202 may estimate an amount of time that the patient should be monitored based on the simulation.
  • the device 202 may request additional information from the health care provider. For example, the device 202 may request that additional biometric measurements be performed. For example, the device 202 may request the additional information to determine (e.g., further) treatment options. The device 202 may analyze the additional information in the context of the initial patient health information. For example, the device 202 may use the additional information to lookup a risk level in the lookup table. The device 202 may then compare the risk level associated with the initial patient health information to the risk level associated with the additional information to determine if the patient’s health is improving or declining. The device 202 may also use the trend in risk level to estimate the time of ingestion and dosage of the drug ingested by the patient.
  • the device may display a guided menu (e.g., via a display screen such as the display screen 210).
  • the guided menu may be used to assist health care providers in diagnosing and/or treating a patient that has overdosed on APAP.
  • the guided menu may allow a health care provider to quickly navigate to different patient data.
  • the guided menu may have clickable icons that navigate to other display screens where the health care provider may enter or review patient presentation data, initial lab data, and/ or treatment data.
  • patient presentation data may include an amount of overdose, a type of overdose, and/ or a time of overdose.
  • the initial lab data may include plasma measurements such as the amount of APAP detected in the plasma, ALT and/ or AST levels, INR, and/ or total bilirubin (TB).
  • Treatment data may, for example, include information regarding whether to begin a treatment (e.g., whether to begin administering NAC, activated charcoal, and/ or other treatment ⁇ )) .
  • the guided menu may allow the health care provider to navigate to pages associateci with prognostic analysis, follow-up lab data, and/or information regarding when to stop a treatment.
  • the guided menu may have quick links.
  • one quick link may be a “new patient” link tied to a page where the health care provider may enter data about a new patient.
  • one quick link may allow the health care provider to navigate to a patient dashboard for an existing patient.
  • one quick link may be a “resources” link.
  • the resources link may, for example, be tied to a medical reference manual.
  • the medical reference manual may include, for example, risk stratification information.
  • FIG. 4 illustrates an example patient dashboard.
  • the patient dashboard may include patient information.
  • the patient dashboard may display the patient’s name, an overdose type of the patient (e.g., an acute or chronic), and/ or lab results associated with the patient.
  • the patient dashboarci may include graphs illustrating the patient’s lab results over a period of time (e.g., since admission to the health care center).
  • the patient dashboard may include a graphical representation of a reported overdose amount and/or an estimated overdose amount.
  • the patient dashboard may include a graphical representation of a reported and/ or an estimated amount of time since the overdose (e.g., a time since ingestion, also sometimes referred to as a post-ingestion time).
  • the patient dashboard may include a treatment recommendation.
  • the treatment recommendation may indicate that NAC treatment, activated charcoal, and/ or a novel therapy is recommended.
  • the treatment recommendation may indicate an approximate amount of time that the patient should receive the treatment.
  • the patient dashboard may indicate a risk stratification of the patient.
  • the risk stratification may indicate whether the patient has a low or high risk of acute liver injury (ALI) and/ or acute liver injury/ failure (ALI/F).
  • FIG. 5 illustrates an example of a patient data display.
  • the health care provider may be able to navigate to the patient data display by selecting the “add patient” quick link, for example.
  • the patient data display may allow the health care provider to input initial patient health information at the time of presentation (e.g., at the time of admission to the health care facility).
  • the initial patient health information may include an overdose type of the patient (e.g., acute or chronic), an APAP formulation (e.g., immediate- or extended-release formulas), ingested dose (e.g., in grams), time since ingestion (e.g., in hours), and/or initial lab results (e.g., bloodwork data such as APAP, ALT, AST, and/ or INR measurement(s)).
  • an overdose type of the patient e.g., acute or chronic
  • an APAP formulation e.g., immediate- or extended-release formulas
  • ingested dose e.g., in grams
  • time since ingestion e.g., in hours
  • initial lab results e.g., bloodwork data such as APAP, ALT, AST, and/ or INR measurement(s)
  • the patient data display may allow the health care provider to enter subsequent patient health data.
  • the health care provider may be able to enter additional patient health information and/ or updated patient health information (
  • the device may receive the updated patient data.
  • the device may receive treatment information associated with the patient (e.g., information regarding treatments that have been administered to the patient).
  • the device may determine an updated metric indicative of effectiveness of an acetaminophen overdose treatment (e.g., NAC, activated charcoal, and/ or other treatment(s)) for the patient based, at least in part, on the updated patient data.
  • the updated metric may be determined based, at least in part, on a second cellular simulation of liver response to acetaminophen overdose.
  • Updated prognosis information may be output based on the updated metric (e.g., the updated prognosis information may be determined and output as described above).
  • FIG. 7 illustrates an example of a treatment assessment display (e.g., a NAC treatment assessment display).
  • the NAC treatment assessment display may include information about whether to begin NAC treatment on the patient. For example, the NAC treatment assessment display may indicate that starting NAC treatment is recommended.
  • the NAC treatment assessment display may (e.g., optionally) include a graphical representation of a nomogram (e.g., the Rumack- Matfoew nomogram, blurred out in FIG. 7). The nomogram may be used to determine whether to recommend a treatment.
  • the NAC treatment assessment display may include one or more criteria for stopping a treatment.
  • the NAC treatment assessment display may indicate whether the criteria have been met. For example, the NAC treatment assessment display may indicate whether foe APAP, ALT, and/ or INR of the patient are low 7 enough to stop NAC treatment.
  • the NAC treatment assessment display may not include a graphical representation of a nomogram.
  • foe NAC treatment assessment display may include other information regarding whether to start NAC treatment.
  • the NAC treatment assessment display may list criteria related to starting NAC treatment. For example, the criteria may include whether foe time of ingestion was more than 24 hours earlier. For example, the criteria may include whether foe patient has elevated ALT levels. The criteria may include, for example, whether APAP is detectable (e.g., in the patient’s blood). Tn some examples, the criteria may include whether the APAP ingested was in a particular form (e.g., an extended-release capsule). The criteria may include, for example, an indication of whether foe overdose was chronic (e.g., caused by repeated supra therapeutic ingestion (RSTI)).
  • RSTI repeated supra therapeutic ingestion
  • FIG. 8 illustrates an example additional treatment assessment display.
  • the additional treatment assessment display may include an indication (e.g., recommendation) of whether to start additional treatment.
  • the additional treatment assessment display may include one or more indicator(s) for determining whether to start the additional treatment.
  • the indicator(s) may include an ⁇ I .1/1' risk stratification indicator to indicate if the patient is at low or high risk of a fatal liver injury.
  • the indicator(s) may include the patient’s INR at the time of presentation.
  • the additional treatment assessment display may include graphical representations of the one or more indicator(s) .
  • the graphical representation of the ALI/F risk stratification indicator may be a graph with a risk line that divides the low-risk and high-risk patients based on certain lab results.
  • the x-axis on the graph may represent the time a lab was taken relative to the time of APAP ingestion.
  • the y-axis on the graph may represent an AT product of the patient.
  • Line 802 may represent a first time-since-ingestion threshold.
  • the line 802 may indicate that patients will be classified as low risk if the lab results were taken within 3.5 hours since ingestion. This may be regardless of the patient’s AT product level.
  • Line 804 may represent a first AT product threshold.
  • the line 804 may be set at 19,000 mg/L * IU/L.
  • Line 806 may represent a second time-since-ingestion threshold. The line 806 may be set at, for example, 9 hours. Accordingly, if a patient ingested APAP between the first time-since- ingestion threshold (3.5 hours) and the second time-since-ingestion threshold (9 hours), the patient may be classified as high risk if the patient’s AT product level is above the first AT product threshold. Similarly, if a patient ingested APAP between the first time-since-ingestion threshold and the second time-since-ingestion threshold, the patient may be classified as low risk if the patient’s AT product level is below the first AT product threshold.
  • Line 808 may represent a second AT product threshold.
  • the line 808 may be set at 1460 mg/L * IU/L.
  • the patient may be classified as high risk if the patient’s AT product level is above the second AT product threshold.
  • the patient may be classified as low risk if the patient’s AT product level is below the second AT product threshold.
  • the risk line may be changed based on a goal of the risk assessment (e.g., to include only patients with severe ALI/F, or to include only patients who are not likely well-treated with NAG alone).
  • the risk line may be determined by optimizing the sensitivity and/ or specificity of the risk line using retrospective data.
  • the simulator may be used to confirm the sensitivity and/or specificity of the risk line using simulated data.
  • the simulator may be used to provide additional data points to the retrospective data.
  • the sensitivity and/or specificity of the risk line may then be optimized using the combined retrospective data and simulated data.
  • the risk line may be dynamically determined. For example, the risk line may be determined based on inputs and/ or the intended use of the risk line.
  • the additional treatment assessment display may include a graphical representation of the INR indicator, as shown.
  • the graphical representation of the INR indicator may have a horizontal risk line 810.
  • the patient may be classified as high risk if the patient’s INR is above the risk line 810 (e.g., higher than a threshold INR).
  • the patient may be classified as low risk if the patient’s INR is below the risk line 810 (e.g., lower than the threshold INR).
  • Examples of additional treatment may include the administration of a substance (e.g., a drug) other than NAG.
  • the additional treatment may involve the administration of activated charcoal.
  • Activated charcoal may reduce the peak serum concentration of acetaminophen and/ or reduce acetaminophen levels in the patient (e.g., thereby decreasing the number of patients who will rely on NAG to survive).
  • An example additional treatment may involve the administration of Fomepizole (e.g., as an adjunct therapy).
  • U.S. Published Application No. 20200237871 discloses methods and kits for mitigating liver injury, and promoting liver regeneration, hypertrophy and engraftment of liver cells in a subject in need thereof that includes administering to the subject an effective amount of a thrombopoietin (TPO) mimetic (TPOm) alone or in combination with cell transplant in conjunction with radiation or radiomimetics to promote beneficial effects.
  • TPO thrombopoietin
  • TPOm thrombopoietin
  • An example additional treatment may involve the administration of an agent drat can bind with specificity to a thrombopoietin receptor (e.g., such as a TPOm).
  • Another example additional treatment may involve the use of hepatocytes and/or liver sinusoidal endothelial cells.
  • Other example additional treatments may involve the use/administration of a therapeutic dose of: certain quaternary pyridinium compounds; propylene glycol; diallyl sulfide and/ or diallyl sulfone; a disulfide and/ or thiol- containing compound; and/ or the like.
  • FIG. 9 is an illustration of an example prognostic analysis.
  • the prognostic analysis may help a health care provider continuously monitor the outcome for the patient.
  • the prognostic analysis may be based on patient health information and/ or treatment information.
  • the prognostic analysis may be based on whether the patient received NAG treatment.
  • the prognostic analysis may be based on how quickly the patient received treatment after ingesting APAP.
  • the prognostic analysis may include one or more probabilities of adverse events.
  • the prognostic analysis may include probabilities for ATI with functional impairment, encephalopathy, and/or death.
  • the prognostic analysis may include graphical representations of the probabilities.
  • FIG. 10 illustrates an example flow chart 1000.
  • a device e.g., the device 202 may receive patient data indicative of an acetaminophen overdose, a time associated with acetaminophen ingestion, and an aminotransferase (AT) product level.
  • a metric indicative of effectiveness of an acetaminophen overdose treatment e.g., NAG, activated charcoal, and/ or other treatment(s)
  • prognosis information may be output based on the metric.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Epidemiology (AREA)
  • Theoretical Computer Science (AREA)
  • Primary Health Care (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Molecular Biology (AREA)
  • Automation & Control Theory (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Fuzzy Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne un dispositif de stratification des risques pour des patients. Le dispositif peut comprendre un processeur configuré pour effectuer une ou plusieurs actions. Le processeur peut recevoir des données de patient indiquant une surdose d'acétaminophène, un temps associé à une ingestion d'acétaminophène, et un niveau de produit d'aminotransférase (AT). Une métrique indiquant l'efficacité d'un traitement de surdose d'acétaminophène pour le patient peut être déterminée sur la base des données de patient et d'une simulation cellulaire de réponse hépatique à une surdose d'acétaminophène. Des informations de pronostic peuvent être délivrées sur la base de la métrique.
PCT/US2024/014572 2023-02-17 2024-02-06 Stratification dynamique des risques basée sur une simulation Ceased WO2024173096A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202363446560P 2023-02-17 2023-02-17
US63/446,560 2023-02-17

Publications (1)

Publication Number Publication Date
WO2024173096A1 true WO2024173096A1 (fr) 2024-08-22

Family

ID=92420605

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2024/014572 Ceased WO2024173096A1 (fr) 2023-02-17 2024-02-06 Stratification dynamique des risques basée sur une simulation

Country Status (1)

Country Link
WO (1) WO2024173096A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100285082A1 (en) * 2003-08-22 2010-11-11 Fernandez Dennis S Integrated Biosensor and Simulation System for Diagnosis and Therapy
US20150366821A1 (en) * 2012-11-13 2015-12-24 Ucl Business Plc Adrenergic agonists for use in treating liver damage
US20190093077A1 (en) * 2015-12-04 2019-03-28 EMULATE, Inc. Devices and methods for simulating a function of a liver tissue
US20190325995A1 (en) * 2018-04-20 2019-10-24 NEC Laboratories Europe GmbH Method and system for predicting patient outcomes using multi-modal input with missing data modalities
US20210219910A1 (en) * 2019-08-13 2021-07-22 Twin Health, Inc. Precision treatment platform enabled by whole body digital twin technology

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100285082A1 (en) * 2003-08-22 2010-11-11 Fernandez Dennis S Integrated Biosensor and Simulation System for Diagnosis and Therapy
US20150366821A1 (en) * 2012-11-13 2015-12-24 Ucl Business Plc Adrenergic agonists for use in treating liver damage
US20190093077A1 (en) * 2015-12-04 2019-03-28 EMULATE, Inc. Devices and methods for simulating a function of a liver tissue
US20190325995A1 (en) * 2018-04-20 2019-10-24 NEC Laboratories Europe GmbH Method and system for predicting patient outcomes using multi-modal input with missing data modalities
US20210219910A1 (en) * 2019-08-13 2021-07-22 Twin Health, Inc. Precision treatment platform enabled by whole body digital twin technology

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CHRISTOPHER H. REMIEN; FREDERICK R. ADLER; LINDSEY WADDOUPS; TERRY D. BOX; NORMAN L. SUSSMAN: "Mathematical modeling of liver injury and dysfunction after acetaminophen overdose: Early discrimination between survival and death", HEPATOLOGY, vol. 56, no. 2, 6 July 2012 (2012-07-06), US , pages 727 - 734, XP071570319, ISSN: 0270-9139, DOI: 10.1002/hep.25656 *

Similar Documents

Publication Publication Date Title
Bosworth et al. Two self-management interventions to improve hypertension control: a randomized trial
Hersh et al. Caveats for the use of operational electronic health record data in comparative effectiveness research
Sheldon et al. Age of first faint in patients with vasovagal syncope
RU2601197C2 (ru) Компьютерная система для прогнозирования результатов лечения
US7917374B2 (en) System and method for early identification of safety concerns of new drugs
US20100010831A1 (en) Automatically determining ideal treatment plans for complex neuropsychiatric conditions
Chew et al. An evaluation of the Virtual Monitoring Clinic, a novel nurse‐led service for monitoring patients with stable rheumatoid arthritis
Lee et al. Antiepileptic drug adherence and persistence in children with epilepsy attending a large tertiary care children's hospital
Farhan et al. Prevalence and predictors of home use of glucometers in diabetic patients
Ell et al. One-year postcollaborative depression care trial outcomes among predominantly Hispanic diabetes safety net patients
Mahler et al. Adherence to an accelerated diagnostic protocol for chest pain: secondary analysis of the HEART pathway randomized trial
Levintow et al. Pragmatic considerations for negative control outcome studies to guide non‐randomized comparative analyses: a narrative review
Burkhardt et al. Effect of prior cardiopulmonary resuscitation knowledge on compression performance by hospital providers
Pradeepa et al. Use of a large diabetes electronic medical record system in India: clinical and research applications
Garg et al. Self‐monitoring of blood glucose
Beachler et al. Development and validation of a predictive model algorithm to identify anaphylaxis in adults with type 2 diabetes in US administrative claims data
Davazdahemami et al. Examining the effect of prescription sequence on developing adverse drug reactions: The case of renal failure in diabetic patients
WO2024173096A1 (fr) Stratification dynamique des risques basée sur une simulation
Topp et al. Psychometric properties of the COPD-specific beliefs about medicine questionnaire in an outpatient population: a Rasch-analysis
Ramaswamy et al. CKD subpopulations defined by risk‐factors: A longitudinal analysis of electronic health records
McCabe et al. An investigation of the measurement properties of the Physiotherapy therapeutic relationship measure in patients with musculoskeletal conditions
Palmer Quality health care
Jeong et al. Influence of illness uncertainty on health behavior in individuals with coronary artery disease: a path analysis
Bani et al. Validation of the Italian version of the Injection Phobia Scale-Anxiety and application to blood donors
Weng et al. Heart rate trajectories in patients recovering from acute myocardial infarction: a longitudinal analysis of Apple Watch heart rate recordings

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: 24757434

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE