[go: up one dir, main page]

WO2025097232A1 - Procédé et système d'estimation de valeur de pression intracrânienne d'un patient, et procédé d'entraînement de modèle - Google Patents

Procédé et système d'estimation de valeur de pression intracrânienne d'un patient, et procédé d'entraînement de modèle Download PDF

Info

Publication number
WO2025097232A1
WO2025097232A1 PCT/BR2024/050514 BR2024050514W WO2025097232A1 WO 2025097232 A1 WO2025097232 A1 WO 2025097232A1 BR 2024050514 W BR2024050514 W BR 2024050514W WO 2025097232 A1 WO2025097232 A1 WO 2025097232A1
Authority
WO
WIPO (PCT)
Prior art keywords
intracranial pressure
patient
data
model
icp
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/BR2024/050514
Other languages
English (en)
Portuguese (pt)
Inventor
Gustavo Henrique Frigieri Vilela
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.)
Braincare Desenvolvimento e Inovacao Tecnologica SA
Original Assignee
Braincare Desenvolvimento e Inovacao Tecnologica SA
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 Braincare Desenvolvimento e Inovacao Tecnologica SA filed Critical Braincare Desenvolvimento e Inovacao Tecnologica SA
Publication of WO2025097232A1 publication Critical patent/WO2025097232A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/03—Measuring fluid pressure within the body other than blood pressure, e.g. cerebral pressure ; Measuring pressure in body tissues or organs
    • 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

Definitions

  • the present invention describes a method for estimating a patient's intracranial pressure values in real time, which incorporates a trained model implemented in a processor that interprets intracranial pressure morphology signal data sets and estimates the patient's intracranial pressure value from the intracranial pressure signal data set.
  • the present invention lies in the fields of medicine, neuroscience, electrical engineering and signal processing.
  • ICP intracranial pressure
  • the intracranial volume/pressure ratio which represents intracranial compliance (ICC)
  • ICC intracranial compliance
  • ICP monitoring is essential in neurocritical care.
  • the most widely used standard for ICP monitoring continues to be the insertion of a catheter into the ventricle or brain parenchyma, which has several limitations that include the need for specialized technicians to perform the procedure, the high cost of the procedure and, mainly, the technical challenges of evaluating small ventricles and the risks involved with invasive brain procedures.
  • TCD Transcranial Doppler
  • optic nerve sheath ultrasound and pupillometry
  • IH intracranial hypertension
  • TCD Transcranial Doppler
  • ABSP Arterial Blood Pressure
  • ONSD ultrasonographic optic nerve sheath diameter
  • these techniques demonstrate significant variability in the metrics used to determine the accuracy of these non-invasive ICP estimation methods, typically measured as mean absolute difference (MAD), mean absolute error (MAE), and a 95% confidence interval (CI).
  • Document WO20231 18556A1 discloses more generally a system that uses a trained model to predict a parameter indicative of intracranial pressure based on medical data provided from a database, a measuring unit, an intensive care unit, or from a receiver or transceiver for receiving medical data.
  • document WO2023118556A1 does not mention the use of intracranial pressure morphology curves by the model to generate an intracranial pressure value.
  • Document US20130041271 A1 discloses a method and device for monitoring intracranial hemodynamic parameters, such as ICP, cerebral blood volume, cerebral blood flow and cerebral perfusion pressure, where waveforms are extracted from impedance plethysmography signals and are used to estimate intracranial hemodynamic parameters continuously. Furthermore, the waves are used to build a signal analysis model to determine an average ICP value over a period of time, for example, a single cardiac cycle.
  • document US20130041271 A1 does not mention the use of intracranial pressure morphology curves by the model to generate an intracranial pressure value.
  • WO2023049529A1 discloses a method for determining a patient's ICP, which collects ultrasound data obtained from measuring acoustic signals from the patient's brain to determine a measurement of the brain's cerebral blood flow velocity (CBFV), and data from measuring the brain's arterial blood pressure (ABP) to generate, from the two measurements, an input to a model trained to output an ICP measurement and to provide input to the model to obtain a measurement of the patient's ICP.
  • CBFV brain's cerebral blood flow velocity
  • ABSP brain's arterial blood pressure
  • WO2023049529A1 does not cite the use of intracranial pressure morphology curves by the model to generate an intracranial pressure value.
  • Document CN1 15804582A discloses a non-invasive continuous ICP monitoring system using microwaves.
  • the system has a processor configured to transmit a first microwave signal and receive a second returned microwave signal and perform filtering processing. It also has a computer used to analyze the frequency bands of the first microwave signal and the second microwave signal that is received and reflected to obtain related parameters, in addition to a model implemented in the computer to train the related parameters and the first intracranial pressure value to obtain a monitoring model.
  • document CN1 15804582A does not disclose the use of intracranial pressure morphology curves by the model to generate an intracranial pressure value.
  • ICP monitoring devices should have a continuous output in the range of 0-100 mmHg, with an accuracy of ⁇ 2 mmHg in the range of 0-20 mmHg and a maximum prediction error of 10% for ICP >20 mmHg.
  • Previously proposed noninvasive ICP data-driven models can exhibit varying degrees of mean error, ranging from ⁇ 5 mmHg to approximately ⁇ 20 mmHg, often accompanied by a high standard deviation. This variability reflects the importance of considering trends and anticipating ICP peaks rather than relying solely on passive observation until a predefined threshold is exceeded for these prior art estimation models.
  • the state of the art lacks a non-invasive method capable of providing real-time ICP estimates and changes that allow proactive patient management and early intervention, aligning with the broader goal of improving patient outcomes.
  • the present invention solves the problems of the prior art by obtaining an ICP value that is generated by means of a specifically trained artificial intelligence model, which receives the signal from the intracranial pressure morphology curve and estimates the ICP value related to the respective curve.
  • This model is implemented to operate both in real time, that is, collecting real-time data from the intracranial pressure morphology curve, and in cases where the curve is previously collected and stored in a memory, for later computation/estimation of the ICP value.
  • the present invention presents a method for estimating the intracranial pressure value of a patient comprising the steps of: a. receiving, by a processor, at least one data window from a patient's intracranial pressure morphology signal; b. processing the data window by means of a model implemented in the processor; and c. generation of an intracranial pressure value, from the data window, by the model, said model being previously trained to receive one or more data windows of the intracranial pressure morphology signal and generate an intracranial pressure value related to the received data window.
  • the present invention presents a system for obtaining a patient's intracranial pressure value comprising at least one processor that reads at least one data window from at least one intracranial pressure morphology signal from a patient, in which the processor is provided with a model that processes and generates an intracranial pressure value, from the data window read, said model being previously trained to receive one or more data windows from the intracranial pressure morphology signal and generate an intracranial pressure value related to the processed data window received.
  • the present invention presents a model training method for estimating the intracranial pressure value of a patient, which is performed by an algorithm comprising at least one intracranial pressure morphology signal pre-processing step among: a. extraction, by a processor, of one or more data windows from a plurality of distinct intracranial pressure morphology signals; and b. comparing said data windows with absolute intracranial pressure values of the respective distinct intracranial pressure morphology signals.
  • the present invention presents a computer program comprising instructions executable by the computer, in which the instructions, when executed by the computer, reproduce the method for estimating the intracranial pressure value of a patient.
  • a system which has a device for measuring intracranial pressure non-invasively, where the system is adapted to implement any of the methods defined above.
  • Figure 1 shows a diagram illustrating the input of an intracranial pressure data window into the model and the output of a numerical intracranial pressure value.
  • Figure 2 shows a flowchart illustrating the patient and data selection step for the method using Random Forest classification and regression.
  • Figure 3 shows a flowchart illustrating the separation of patients used in testing and training the Random Forest classification and regression method.
  • Figure 4 shows a flowchart illustrating the patient and data selection step for the method using gradient histogram boosting with a temporal convolutional network.
  • Figure 5 shows a flowchart illustrating the separation of patients used in testing and training the method using gradient histogram boosting with a temporal convolutional network.
  • Figure 6 shows a flowchart illustrating the separation of patients used in testing or training the method using regression tool and gradient histogram boosting method.
  • Figure 7 shows a graph with the MAE and MSE results for elCP synchronized with changes in invasively measured intracranial pressure (ICP).
  • Figure 8 shows a Bland-Altiman analysis that illustrates the difference average between ICP and elCP.
  • Figure 9 shows the Spearman correlation between ICP and elCP.
  • Figure 10 shows the error percentages of the calculated differences between the obtained elCP means and actual intracranial pressure (ICP).
  • Intracranial Pressure is the relationship between the volume of the intracranial space and its components: cerebrospinal fluid (CSF), blood and brain parenchyma. In each cardiac cycle, blood flows to the brain, creating the ICP wave.
  • the intracranial pressure wave/curve has a typically known morphology, with three distinct components related to the patient's physiological parameters, namely the P1, P2 and P3 peaks.
  • the first P1 peak is the percussion wave and reflects the systolic blood pressure transmitted from the choroid plexus to the cerebral ventricle.
  • the second P2 peak is related to brain tissue compliance, which is variable and presents an increase in amplitude as intracranial compliance decreases; when it exceeds the P1 wave level, it suggests a significant drop in intracranial compliance.
  • the P3 wave is associated with the closure of the aortic valve.
  • TTP time to peak
  • a first object of the invention is a method for estimating the value of the intracranial pressure of a patient comprising the steps of: a. receiving, by a processor, at least one window of data coming from a morphology signal of intracranial pressure of a patient; b.
  • the data window is formed by a quantity of information representative of a signal of the intracranial pressure morphology, so that said data window is composed of all or part of the patient's ICP signal curve. Furthermore, for the purposes of example, said data window represents a period of the wave or the equivalent of a pulse of the ICP composed of the three components related to the patient's physiological parameters, the peaks P1, P2 and P3.
  • the data window has sampled data from the curve of a single ICP pulse and returns an intracranial pressure value related to the respective curve, being, for example, a vector of discretized numerical data, representing the pulse of the patient's ICP curve.
  • the processor performs a sample on the received signal to extract a set of points from the ICP curve, before inputting the information into the model.
  • the data window received by the processor comprises the filtered and/or “cleaned” “raw signal” of the collected ICP curve.
  • the data window comprises at least one image of the ICP curve collected from the patient, where said image is sampled by the processor by means of an image recognition algorithm, in which said sampling converts the image into one or more data vectors with numerical values for the composition of the data window.
  • the data window comprises at least one static or dynamic image of the ICP curve, for example, of a pulse of the patient's ICP, so that such image is input into the model, which is trained to recognize and process static or dynamic images.
  • the processor is capable of receiving real-time bedside ICP morphology data measured using a non-invasive ICP measurement device.
  • the processor is capable of acquiring the PIC morphology signal from a database or a file containing the PIC morphology to be interpreted and processed. This signal may be collected automatically or manually, in the latter case the data being manually input into the processor.
  • the method proposed herein comprises a preliminary step of pre-processing the ICP morphology/curve signal for the composition of the data window.
  • said pre-processing is performed on the data from the data window.
  • an algorithm is implemented in the processor, which performs steps of filtering the intracranial pressure morphology signals, selecting standardized data windows from said signals and classifying the intracranial pressure morphology signals based on a quality index. Through these steps it is possible to “clean” the signal to be used in the model, removing unwanted artifacts from the signal, records with missing or incomplete data, noisy and erroneous values, etc.
  • the quality index for classifying PIC morphology signals involves a signal quality index of 0-1 based on the spectral analysis of one-minute data with reduced sampling and no trend. With this, added to the other steps, a threshold is defined that allows to classify whether the collected signal is sufficient to be absorbed by the machine learning model, preventing poor signals or signals with some interference from being used in the model - during its use or training.
  • steps are performed to adapt the collected ICP curves to a standard that can be absorbed and interpreted by the processor and machine learning model during the method steps, in which the adaptation of the curves includes data cleaning steps (removal of incomplete records, missing data, noisy and erroneous values, etc.), integration of the “cleaned” data and extraction of parameters related to pulse morphology, such as the P2/P1 ratio, TTP, areas under the curve and results of its dimensionality reduction, so that the numerical value of intracranial pressure estimated at the end of the processing is free of inconsistent data.
  • the model implemented in the processor is capable of mathematically processing and interpreting the windowed ICP data.
  • the trained model is capable of returning a number that indicates the value of the patient's intracranial pressure based on its collected ICP morphology curve.
  • the value of the patient's intracranial pressure generated by the model is given in at least one unit among: mmHg, cmH2O, mmH20, cmHg, Pascal, Bar, Psi, among others that can be used to represent the respective physical quantity. Said resulting value is attributed to or related to the collected pulse, that is, through the ICP morphology curve, a numerical value is arrived at that represents the ICP in the desired unit.
  • the model is also capable of operating in real time, in order to receive the ICP curves and, in real time, return the absolute value of the patient's ICP.
  • the value numeric returned by the model also changes relatively.
  • the machine learning model is a classifier and regressor based on decision trees or used for forming decision trees.
  • a Random Forest model is used.
  • the model is a Histogram Gradient Boosting.
  • the analysis guided by the method comprising the model of the present invention allows the monitoring of patients' intracranial pressure in real time, providing information derived from wearable technology data and electronic health records that inform evidence-based clinical data, promoting preventive medicine.
  • the invention also includes a training method for estimating a patient's intracranial pressure value, which is performed by an algorithm that performs pre-processing steps on the ICP morphology signal.
  • the method comprises a preliminary step of training the model by means of a regression tool using a gradient histogram boosting method.
  • the model training step includes a step of extracting, by the processor, one or more parameters from a plurality of distinct intracranial pressure morphology signals, such as, for example, areas, dimensionality reductions, P2/P1 ratio and TTP, for training the model, as well as comparing said data windows with absolute intracranial pressure values of the respective distinct intracranial pressure morphology signals.
  • a plurality of distinct intracranial pressure morphology signals such as, for example, areas, dimensionality reductions, P2/P1 ratio and TTP
  • said distinct intracranial pressure morphology signals comprise morphology signals of the PIC of different patients, with different pathological conditions, with different skull conditions, with different diagnoses, etc.
  • said extracted parameter comprises at least one of: segmented area under the ICP curve, wherein one unit represents 20% of the waveform length; amplitude of the waveform; total area under the ICP curve; correlation coefficient; derivative of the wave slope; dimensionality reduction elements (ISOMAP); intracranial compliance scale; P2/P1, being the ratio between the P1 and P2 peaks of the ICP waveform; TTP, being the time to peak - the highest amplitude value of the wave; or a combination thereof.
  • segmented area under the ICP curve wherein one unit represents 20% of the waveform length; amplitude of the waveform; total area under the ICP curve; correlation coefficient; derivative of the wave slope; dimensionality reduction elements (ISOMAP); intracranial compliance scale; P2/P1, being the ratio between the P1 and P2 peaks of the ICP waveform; TTP, being the time to peak - the highest amplitude value of the wave; or a combination thereof.
  • such extracted data and/or parameters are refined for dimensionality reduction, by means of the regression tool using gradient histogram boosting method, based on distinct absolute intracranial pressure values.
  • such absolute intracranial pressure values are sourced from a database.
  • the model is then trained to identify the ICP morphology signal pattern and extract numbers corresponding to the ICP morphology, generating a numerical value of the patient's ICP in real time.
  • said method for estimating the intracranial pressure value of a patient being used as a guide for the precise interpretation of ICP curves, allowing the ICP curve measured non-invasively to be converted into a numerical value for subsequent precise and efficient medical diagnosis.
  • an object of the invention is a system for estimating the intracranial pressure value of a patient comprising a processor that reads at least one data window from at least one intracranial pressure morphology signal of a patient, in which the processor is provided with a model that processes and generates an intracranial pressure value, from the data window read, said model being previously trained to receive one or more data windows from the intracranial pressure morphology signal and generate an intracranial pressure value related to the window of processed data received.
  • connection interface that receives the PIC morphology data and transmits it to the processor.
  • Said connection interface within the scope of the invention, is a physical or electronic medium that allows the reception and forwarding/transmission of data to the processor.
  • the connection interface is a physical data bus that connects an electronic device to the processor.
  • the connection interface is an instruction or routine implemented in software that receives the data and forwards it to the processor.
  • the connection interface is a bus connectable to a peripheral to which a user is able to input PIC curve data. Such examples certainly should not limit the scope of the invention.
  • connection interface is communicative with a non-invasive intracranial pressure measuring device, which collects real-time data on the patient's ICP morphology and transmits it to the processor.
  • connection interface is communicative with a database to acquire intracranial pressure morphology signals, which are transmitted to the processor.
  • the system comprises a value display of intracranial pressure communicating with the processor, which displays the intracranial pressure value obtained through processing.
  • the display allows a quick and practical visualization of the numerical value of the intracranial pressure obtained.
  • an object of the invention is a system and method for estimating the intracranial pressure value in mmHg of a patient, comprising generating an intracranial pressure value, in mmHg, from a window of data coming from an intracranial pressure morphology signal of the patient, the intracranial pressure value in mmHg being generated by means of processing through a model implemented in a processor, in which the model is previously trained to receive one or more data windows of the intracranial pressure morphology signal and generate an intracranial pressure value, in mmHg, related to the received data window.
  • the system and methods of the present invention can be used as a guide for interpreting intracranial pressure morphology curves, allowing the non-invasively measured ICP curve to be converted into a numerical value in mmHg for subsequent accurate and efficient medical use.
  • Example 1 Method for estimating intracranial pressure value in mmHg
  • a system and method for estimating a numerical value of intracranial pressure, in mmHg, from a patient's ICP curve was developed.
  • the present method uses only ICP morphology curves/waves to estimate an intracranial pressure value in mmHg in real time.
  • the patient's ICP curves are measured in real time at the bedside by means of a measuring device non-invasive PIC.
  • Figure 1 shows a simplified schematic diagram where a pulse from the patient's intracranial pressure curve is represented being input into the machine learning model.
  • a decision tree model trained with a Histogram Gradient Boosting (HGB) technique was used.
  • HGB Histogram Gradient Boosting
  • the data window received by the previously trained model is a vector of amplitudes related to the collected PIC curve itself, where the amplitudes are obtained by a temporal sampling performed on the collected signal.
  • the number of points that is, the length of the vector, is previously defined so that it is sufficient and compatible with the model parameters.
  • a set of approximately 260 points of the PIC curve was used, which have amplitude values in micrometers assigned to each point, with such numbers being interpreted by the model.
  • the senor collects the “raw signal” of the ICP curve in real time at the bedside, so that the processor performs a filtering process to “clean” the signal and, thus, extract the values of each signal point to compose the data window.
  • This filtering process comprises: selection of standardized data windows and classification of the ICP signals in a quality index, to adapt the ICP curves to a pattern that can be absorbed and interpreted by the model.
  • the data window is input into the model, which interprets the sampled signal from the ICP curve measured in real time and returns a numerical value of the patient's intracranial pressure in mmHg.
  • the ability of the present method to provide real-time ICP estimates and changes becomes increasingly valuable for management proactive patient monitoring and early intervention, aligning with the broader goal of improving patient outcomes, as it obtains the ICP morphology curve non-invasively and also generates an absolute ICP value related to the collected curve.
  • the present system and method provides simplicity of handling and immediate acquisition of information, in addition to the absence of any type of energy emission and suitability for locations with fewer financial resources.
  • the model's use of the measured ICP curve itself represents a true physiological signal of ICP dynamics on a beat-by-beat basis of the cardiac pulse, which is an advantage compared to prior art models for non-invasive ICP estimation, which use only secondary parameters related to ICP dynamics, such as cerebral blood velocity and mean arterial blood pressure.
  • the present developed method is more advantageous because it is based on only one physiological signal, avoiding possible discrepancies arising from a multiparameter architecture.
  • the present method enables the inclusion of artificial intelligence mechanisms capable of providing the value of the patient's ICP estimated at the point of care, as well as continuous non-invasive monitoring so that ICP becomes a more universally accessible vital sign.
  • the method developed in this example aims to use artificial intelligence to read a data window of an intracranial pressure curve to generate an estimated numerical value of a patient's intracranial pressure from the interpretation of the processed data window.
  • the patient's ICP curves are obtained by means of of a non-invasive ICP measurement device attached around the patient's head, which measures ICP and provides curves of the patient's ICP morphology in real time at the bedside.
  • the method can be used as an accurate interpretation guide for ICP curves, allowing the non-invasively measured ICP curve to be converted into a numerical value in mmHg for subsequent accurate and efficient medical use.
  • the model creation process involved cross-validation, meaning that the patient data used for testing and training were mixed at each stage of the cross-validation process, comprising 5 stages in total. This methodology ensured robust validation, as it avoided possible biases that could arise from having the same patient data in the training and testing datasets.
  • Example 3 Validation of the model that uses classification and regression by Random Forest to estimate non-invasive intracranial pressure from its morphology curves
  • FIG. 1 shows a flowchart illustrating the aforementioned data selection step.
  • the model was developed using cross-validation, ensuring that the patient data used in the training and testing were intermingled, i.e., there is no data from a single patient present in both the training and testing groups at each stage of the cross-validation process. This ensures the robustness of the evaluation, avoiding possible biases arising from the over-representation of any individual patient in the training and testing data sets, as illustrated in Figure 3.
  • Table 1 shows the distribution of patients used in this test, the majority of whom were women with an average age of 43 years, presenting traumatic brain injury in 77% of cases.
  • the model was statistically evaluated using the Mean Absolute Error (MAE) and Mean Squared Error (MSE) metrics. As illustrated in Table 2 below, the MAE showed favorable results. Both the training and test population groups demonstrated close margins with a margin of 3.7, being a value within the clinically beneficial range. In both tests, there is a remarkable correspondence between the values derived from the test and the training populations, signaling the absence of overfitting. This supports the robustness of the model and its readiness for clinical deployment, assuming that the described error margins are acceptable in the specific clinical context.
  • MAE Mean Absolute Error
  • MSE Mean Squared Error
  • Table 4 shows the median values of these parameters, along with their standard deviations. In addition, it highlights the discrepancies between them, representing the error identified when analyzing the medians of each patient, in mmHg.
  • Example 4 Machine Learning Framework Using Gradient Histogram Boosting with a Temporal Convolutional Network
  • the method developed in this example aims to use artificial intelligence to read a data window of an intracranial pressure curve to generate an estimated numerical value of a patient's intracranial pressure from the interpretation of the processed data window.
  • the patient's ICP curves are obtained by means of a non-invasive ICP measuring device attached around the patient's head, which measures the ICP and provides the patient's ICP morphology curves in real time at the bedside.
  • the method can be used as an accurate interpretation guide for ICP curves, allowing the non-invasively measured ICP curve to be converted into a numerical value in mmHg for subsequent accurate and efficient medical use.
  • the model creation process involved cross-validation, meaning that patient data used for testing and training were mixed at each stage of the cross-validation process, comprising 5 stages in total. This methodology ensured robust validation as it avoided potential biases that could arise from having the same patient data in the training and testing datasets.
  • Example 4 Model validation using gradient histogram boosting with a temporal convolutional network for non-invasive intracranial pressure estimation from its morphology curves
  • FIG. 4 shows a flowchart illustrating the aforementioned data selection step.
  • the model was developed using cross-validation, ensuring that the patient data used in the training and testing were intermingled, i.e., there is no data from a single patient present in both the training and testing groups at each stage of the cross-validation process. This ensures the robustness of the evaluation, avoiding possible biases arising from the over-representation of any individual patient in the training and testing data sets, as illustrated in Figure 5.
  • the model was statistically evaluated using the Mean Absolute Error (MAE) and Mean Squared Error (MSE) metrics, whose equations (3) and (4), respectively, are described below:
  • MAE Mean Absolute Error
  • MSE Mean Squared Error
  • Table 5 shows the distribution of patients used in this test, the majority of whom were women with an average age of 43 years, presenting traumatic brain injury in 77% of cases.
  • Table 7 Average values for the invasive ICP measurement sensor (ICPm) and for the developed model (elCP). [0126] Table 8 below shows the median values of these parameters, along with their standard deviations. In addition, it highlights the discrepancies between them, representing the error identified when analyzing the medians of each patient, in mmHg.
  • Table 8 Median values for the invasive ICP measurement sensor (ICPm) and for the developed model (elCP).
  • Example 5 Machine Learning Framework using Regression Tool and Gradient Histogram Boosting Method
  • the method developed in this example aims to use artificial intelligence to read a data window of an intracranial pressure curve to generate an estimated numerical value of a patient's intracranial pressure from the interpretation of the processed data window.
  • the patient's ICP curves are obtained by means of a non-invasive ICP measuring device attached around the patient's head, which measures the ICP and provides the patient's ICP morphology curves in real time at the bedside.
  • the method can be used as a guide for the accurate interpretation of ICP curves, allowing the non-invasively measured ICP curve to be converted into a numerical value in mmHg for later use. precise and efficient doctor.
  • the model used to estimate intracranial pressure employed a gradient histogram boosting regressor, a learning technique that sequentially trains decision trees to correct errors made by previous trees.
  • This approach effectively captures complex relationships and nonlinear patterns in the data by constructing trees based on histograms of parameter values.
  • the process involved the extraction of several parameters from the waveform collected by the non-invasive ICP measuring device. This process resulted in the extraction of approximately 1,180 parameters, including: segmented area under the ICP curve, where one unit represents 20% of the waveform length; waveform amplitude; total area under the ICP curve; correlation coefficient; wave slope derivative; ISOMAP dimensionality reduction elements; intracranial compliance scale; P2/P1, being the ratio between the P1 and P2 peaks of the ICP waveform; TTP, being the time to peak; or a combination thereof.
  • 15 parameters were selected according to the degree of importance in the calculation. Spearman's correlation was used to select the main parameters (cited in Example 6).
  • parameters derived from the morphological segments of the intracranial pressure waveform collected by the non-invasive ICP measuring device such as the P2/P1 ratio, time to peak (TTP) and area under the curve, and results from dimensionality reduction techniques, such as ISOMAP, were used in the development of the model of this example. Furthermore, it is important to emphasize that no parameters derived from any other physiological signal (e.g. ABP, cerebral blood velocity) were included in the model.
  • Example 6 Model validation using regression tool and gradient histogram boosting method for estimation of non-invasive intracranial pressure from its morphology curves
  • the model was statistically evaluated using the Mean Absolute Error (MAE) and Mean Squared Error (MSE) metrics. As illustrated in Table 9 below, the MAE and MSE yielded favorable results.
  • ICP intracranial pressure
  • Table 10 below presents the elCP values for the validation dataset individually, which displays the mean ICP and elCP values, along with the observed difference for each patient.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Hematology (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

La présente invention concerne un procédé d'estimation de valeur de pression intracrânienne d'un patient et un procédé d'entraînement d'un modèle à mettre en oeuvre dans le cadre dudit procédé d'estimation. Plus particulièrement, la présente invention concerne un procécé destiné à estimer les valeurs de pression intracrânienne d'un patient en temps réel, faisant intervenir un modèle entraîné mis en oeuvre dans un processeur qui interprète des ensembles de données de signaux de morphologie de pression intracrânienne et estime la valeur de la pression intracrânienne du patient à partie de l'ensemble de données du signal de la pression intracrânienne. La présente invention trouve une application dans les domaines de la médecine, de la neuroscience, de l'ingénierie électrique et du traitement des signaux.
PCT/BR2024/050514 2023-11-10 2024-11-11 Procédé et système d'estimation de valeur de pression intracrânienne d'un patient, et procédé d'entraînement de modèle Pending WO2025097232A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
BR102023023629 2023-11-10
BR1020230236294 2023-11-10

Publications (1)

Publication Number Publication Date
WO2025097232A1 true WO2025097232A1 (fr) 2025-05-15

Family

ID=95694713

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/BR2024/050514 Pending WO2025097232A1 (fr) 2023-11-10 2024-11-11 Procédé et système d'estimation de valeur de pression intracrânienne d'un patient, et procédé d'entraînement de modèle

Country Status (1)

Country Link
WO (1) WO2025097232A1 (fr)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
BRPI0802279A2 (pt) * 2008-06-06 2010-03-02 Oliveira Sergio Mascarenhas De equipamento nço invasivo para monitoramento da pressço intracraniana (pic)
EP2757939A2 (fr) * 2011-09-19 2014-07-30 Oliveira Mascarenhas, Sérgio Système de pression intracrânien non invasif
EP2836115A1 (fr) * 2012-04-13 2015-02-18 Branchpoint Technologies, Inc. Capteur, circuits et procédé de surveillance sans fil de pression intracrânienne
US11284808B2 (en) * 2014-10-11 2022-03-29 Linet Spol. S.R.O. Device and method for measurement of vital functions, including intracranial pressure, and system and method for collecting data
BR102020021338A2 (pt) * 2020-10-19 2022-05-03 Braincare Desenvolvimento E Inovacao Tecnologica S A Dispositivo e método de detecção e monitoramento de pressão intracraniana de forma não invasiva
US20220183656A1 (en) * 2019-04-03 2022-06-16 Sonovum Gmbh Method and device for a non-invasive determination and/or monitoring of intracranial compliance
CN114795171A (zh) * 2022-01-29 2022-07-29 上海寻是科技有限公司 基于人工智能技术和近红外技术的颅内压无创测量方法
EP4213710A1 (fr) * 2020-12-16 2023-07-26 iNDTact GmbH Dispositif de mesure pour la détection non invasive de la pression intracrânienne d'un patient et procédé associé

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
BRPI0802279A2 (pt) * 2008-06-06 2010-03-02 Oliveira Sergio Mascarenhas De equipamento nço invasivo para monitoramento da pressço intracraniana (pic)
EP2757939A2 (fr) * 2011-09-19 2014-07-30 Oliveira Mascarenhas, Sérgio Système de pression intracrânien non invasif
BR112014006364B1 (pt) * 2011-09-19 2022-01-25 Braincare Desenvolvimento E Inovação Tecnologica Ltda Método e dispositivo para produzir digitalmente e comunicar dados da pressão intracraniana
EP2836115A1 (fr) * 2012-04-13 2015-02-18 Branchpoint Technologies, Inc. Capteur, circuits et procédé de surveillance sans fil de pression intracrânienne
US11284808B2 (en) * 2014-10-11 2022-03-29 Linet Spol. S.R.O. Device and method for measurement of vital functions, including intracranial pressure, and system and method for collecting data
US20220183656A1 (en) * 2019-04-03 2022-06-16 Sonovum Gmbh Method and device for a non-invasive determination and/or monitoring of intracranial compliance
BR102020021338A2 (pt) * 2020-10-19 2022-05-03 Braincare Desenvolvimento E Inovacao Tecnologica S A Dispositivo e método de detecção e monitoramento de pressão intracraniana de forma não invasiva
EP4213710A1 (fr) * 2020-12-16 2023-07-26 iNDTact GmbH Dispositif de mesure pour la détection non invasive de la pression intracrânienne d'un patient et procédé associé
CN114795171A (zh) * 2022-01-29 2022-07-29 上海寻是科技有限公司 基于人工智能技术和近红外技术的颅内压无创测量方法

Similar Documents

Publication Publication Date Title
Bian et al. Respiratory rate estimation using PPG: A deep learning approach
Thiyagaraja et al. A novel heart-mobile interface for detection and classification of heart sounds
AU2002251604B2 (en) Device, method and system for monitoring pressure in body cavities
Wang et al. Phonocardiographic signal analysis method using a modified hidden Markov model
CN113557576A (zh) 在表征生理系统时配置和使用神经网络的方法和系统
RU2657384C2 (ru) Способ и система неинвазивной скрининговой оценки физиологических параметров и патологий
Moran et al. Deep transfer learning for chronic obstructive pulmonary disease detection utilizing electrocardiogram signals
JP2019514635A (ja) 血管系の健康を監視するためのシステムおよび方法
US20230131629A1 (en) System and method for non-invasive assessment of elevated left ventricular end-diastolic pressure (LVEDP)
Al Younis et al. Non-invasive technologies for heart failure, systolic and diastolic dysfunction modeling: a scoping review
Daydulo et al. Deep learning based fetal distress detection from time frequency representation of cardiotocogram signal using Morse wavelet: research study
Argha et al. Blood pressure estimation from korotkoff sound signals using an end-to-end deep-learning-based algorithm
Wołk et al. Early and remote detection of possible heartbeat problems with convolutional neural networks and multipart interactive training
Seo et al. A deep neural network based wake-after-sleep-onset time aware sleep apnea severity estimation scheme using single-lead ECG data
Lei et al. An end-to-end deep learning framework for accurate estimation of intracranial pressure waveform characteristics
KR102149748B1 (ko) 심폐음 신호 획득 방법 및 장치
Ignácz et al. NB-SQI: A novel non-binary signal quality index for continuous blood pressure waveforms
JP2024534128A (ja) 生理学的システムを特徴付ける際に使用するために生物物理学的信号から呼吸数関連特徴を設計するための方法及びシステム
JP2024532279A (ja) 上昇左心室拡張末期圧を非侵襲的に査定するための方法及びシステム
US20250040894A1 (en) Personalized chest acceleration derived prediction of cardiovascular abnormalities using deep learning
WO2025097232A1 (fr) Procédé et système d'estimation de valeur de pression intracrânienne d'un patient, et procédé d'entraînement de modèle
BR102024023463A2 (pt) Método e sistema para estimação de valor de pressão intracraniana de um paciente, e método para treinamento de modelo
JP2021112479A (ja) 心電信号分析装置及び心電信号分析プログラム
Nour et al. Machine Learning and Electrocardiography Signal‐Based Minimum Calculation Time Detection for Blood Pressure Detection
KR102149753B1 (ko) 심폐음 신호 획득 방법 및 장치

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: 24887178

Country of ref document: EP

Kind code of ref document: A1