METHOD AND SYSTEM FOR NONINVASIVE SCREENING PHYSIOLOGICAL PARAMETERS AND PATHOLOGY Russian patent published in 2018 - IPC A61B5/452 G06Q50/22 

FIELD: medicine.

SUBSTANCE: group of inventions relates to medical equipment, namely to means for screening pathologies that depend on cardiac activity of patients. Method comprises the steps of obtaining a user-defined pathology that depends on cardiac activity of a patient, and the pathology is selected by the user from the following options: chronic obstructive pulmonary disease, bronchial asthma, pulmonary tuberculosis, ischemic heart disease; forming a training and test sample of records of patients having a given pathology, depending on cardiac activity of a patient, and the training and test samples include records of patients of different sex and age, wherein each record contains at least one cardiac lead of the ECG signal and information about a patient; receiving a record from the training sample, wherein at least one cardiological ECG signal is processed for each record, heart rate variability (HRV) and averaged cardiac cycle parameters are calculated; training an artificial neural network to identify a given pathology, using the records of the training and test samples, comparing the parameters of the processed ECG signal, calculated parameters of heart rate variability and averaged cardiac cycle and patient information; preserving links and weight of the trained artificial neural network; obtaining at least one cardiological lead of the ECG signal and information about a diagnosed patient; processing the obtained at least one cardiological lead of the ECG signal, calculating the parameters of heart rate variability and averaged cardiac cycle; determining the presence of a given pathology by using the trained neural network, using the parameters of the processed ECG signal, calculated parameters of heart rate variability and averaged cardiac cycle and patient information. System comprises a diagnostic module configured to build and train a neural network to determine the presence of a given pathology by using the trained neural network and to receive, via the control diagnostic module processor, the data from the storage module, ECG signal processing module, HRV calculation module, module for calculating the averaged cycle and sending data to the data storage module configured to store the training and test samples of the artificial neural network, links and weights of the trained artificial neural network, patient records, ECG signals, to receive data from the data input/output module via the control processor, wherein the ECG signal processing module is configured to process at least one cardiological lead of the ECG signal obtained from the data storage module, HRV parameters calculation module is configured to calculate heart rate variability parameters, module for calculating the averaged cycle parameters is configured to calculate the parameters of the averaged cardiac cycle, and the data input/output module is configured to receive ECG signals and patient information and output data on the presence of a given pathology.

EFFECT: use of inventions provides increased accuracy of pathology detection in a patient based on neural network modeling.

17 cl, 6 dwg, 1 tbl