Health pre-assessment method and system based on information monitoring

Abstract

The invention provides a health pre-assessment method and system based on information monitoring, and the method comprises the steps: obtaining ECG data of a user, analyzing a target ECG waveform, extracting heart electrophysiological parameters which comprise a heart rate, a heart rate variability standard deviation and a heart rate rhythm, recognizing a heart rate feature mode of the user, and carrying out the health pre-assessment of the user according to the heart rate feature mode. The periodic change of the electrocardio effect is evaluated, and heart rate characteristic mode information is obtained; based on the heart rate characteristic mode information, multiple physiological parameters of the user are collected in real time, the mutual influence relation between the multiple physiological parameters and heart mode measurement values is analyzed, the heart regulation efficiency of the user is evaluated, and a physiological correlation analysis result is obtained in combination with the correlation coefficient. Through the method and the corresponding system, important risks such as health deterioration and subclinical abnormality can be found in advance, and continuous and decision support is provided for clinical decision and individualized health management.

Description

TECHNICAL FIELD

[0001] The application provides a health pre-evaluation method and system based on information monitoring, and relates to the technical field of health evaluation. BACKGROUND

[0002] Cardiovascular disease (CVD) is one of the main chronic diseases that endanger human health. With the change of lifestyle and population aging, the incidence and mortality of cardiovascular disease are increasing year by year, which seriously threatens the life safety of residents and the social medical security system. In order to effectively prevent and control cardiovascular disease, health assessment and risk stratification are generally carried out in the clinical and public health fields, but the existing main methods have the following defects: 1. Relies on single parameter, intermittent detection, and cannot dynamically reflect health changes. Traditional cardiovascular health assessment relies on single or a few indicators such as static blood pressure, electrocardiogram, blood lipid, single-point and intermittent detection, such as annual physical examination in hospital and outpatient examination when symptoms occur. This kind of method cannot dynamically and continuously reflect the physiological regulation ability and diurnal variation of the cardiovascular system, and is easy to appear "missed diagnosis in asymptomatic period" or "short-term abnormality cannot be captured in time". 2. The relationship between physiological parameters is not comprehensively utilized. The existing method often only investigates single parameters such as heart rate, HRV and blood pressure, and lacks in-depth analysis of the coupling relationship between multiple physiological parameters. For example, the dynamic coupling of heart rate and blood pressure, heart rate and blood oxygen has an important indication function for cardiac autonomic regulation, but the conventional evaluation does not establish effective multi-parameter information fusion and interaction relationship modeling. SUMMARY

[0003] The application provides a health pre-evaluation method based on information monitoring, which comprises the following steps: Obtaining electrocardiogram (ECG) data of a user, analyzing target electrocardiogram waveform, extracting cardiac electrophysiological parameters, the cardiac electrophysiological parameters including heart rate, heart rate variability standard deviation and heart rate rhythm, identifying heart rate feature mode of the user, the measurement value of the heart rate feature mode including average heart rate, HRV parameter, heart rate mode type, QRS time limit and QT time limit, evaluating periodic changes of electrocardio effect, and obtaining heart rate feature mode information; Based on the heart rate feature mode information, real-time collection of multiple physiological parameters of the user is performed, including blood pressure, blood oxygen saturation and activity intensity, analysis of the mutual influence relationship between the multiple physiological parameters and the cardiac mode measurement value, evaluation of the cardiac regulation efficiency of the user, combination of the correlation coefficient, and obtaining of physiological correlation analysis results; Based on the physiological correlation analysis results, abnormal changes of the cardiac electrophysiological parameters are monitored and identified through time series analysis, abnormal reasons are identified and electrocardio abnormalities are classified, including arrhythmia, electrocardiogram waveform abnormality and blood pressure abnormality, and abnormal cardiovascular event detection results are generated; Based on the abnormality detection result, the cardiovascular health state of the user is evaluated by comprehensively analyzing the abnormal electrocardiogram of the user and related events, and the health state prediction value of multiple time points is calculated by using time series analysis to evaluate the cardiovascular health change trend, so as to realize continuous evaluation of the health state.

[0004] Further, the heart mode feature information includes heart rate parameters, HRV parameters, periodicity of RR interval, QT interval and abnormal heart rhythm type. The correlation analysis result is specifically a correlation coefficient of heart rate and blood pressure, dynamic correlation of HRV and SpO2, and parameter variability under exercise load. The abnormality recognition result includes arrhythmia information, HRV abnormality analysis, QRS waveform variation detection data and blood pressure anomaly identification. The health status evaluation information is specifically electrocardiogram variation index, blood pressure steady state level and HRV trend analysis result.

[0005] Further, the heart rate variability standard deviation is calculated, including: Based on electrocardiogram data, R waves are automatically detected, the start and end time of each heartbeat is identified, and the following operations are performed:

[0006] Wherein, RRi represents the RR interval of the i th heartbeat, ti represents the time point corresponding to the end of the i th heartbeat, ti-1 represents the time point corresponding to the start of the i th heartbeat. The heart rate variability standard deviation is calculated based on the RR interval:

[0007] Wherein, SDNN represents the heart rate variability standard deviation, and N represents the total number of detected heartbeats, RRi represents the RR interval of the i th heartbeat, RRm represents the average value of the RR interval.

[0008] Further, the correlation coefficient is calculated, including: Based on the heart mode feature information, the blood pressure, blood oxygen saturation and activity intensity of the user are collected in real time by using multiple physiological monitoring devices; The physiological parameter data set is constructed, and the electrocardiogram parameters such as heart rate and HRV are combined; The heart rate and blood pressure, HRV and blood oxygen saturation are analyzed by statistical correlation, the dynamic change of cardiovascular state is evaluated, and the correlation coefficient is calculated:

[0009] Among them, X is the physiological parameter measurement value, Y is the cardiac mode measurement value, represents the correlation coefficient.

[0010] Furthermore, cardiac regulatory efficiency is assessed, including: Cardiac regulation efficiency can be comprehensively evaluated according to the following model:

[0011] in, represents the weight coefficient, represents heart rate variability, represents the correlation coefficient between heart rate and blood pressure, Represents the correlation coefficient between heart rate and blood oxygen.

[0012] Furthermore, a health pre-assessment method based on information monitoring includes: Pre-processing of ECG, blood pressure and other data for abnormal rhythm analysis; Calculate the anomaly detection threshold:

[0013] in, is the observed value at time t, is the sample mean, is the sample standard deviation, is the standard score; Abnormal detection thresholds were used to detect arrhythmias, significant decreases in HRV, and abnormal QRS and QT intervals; Abnormal events are classified, including atrial fibrillation, premature ventricular contraction, ST segment abnormality and abnormal blood pressure, to generate abnormal cardiovascular event results.

[0014] Furthermore, the cardiovascular health status index model is comprehensively evaluated as follows:

[0015] in, Indicates the number of recorded arrhythmia events, Indicates the HRV abnormal event count, Indicates the QRS duration variation index, represents the blood pressure variation index, D represents the physiological load index, Represents the calculated cardiovascular health status index.

[0016] Furthermore, the health pre-assessment method based on information monitoring includes: Build a time series forecasting model: Based on the time series health status index, build a model:

[0017] wherein, is a cardiovascular health index at time t, is an autoregressive coefficient, is a moving average coefficient, is a white noise term; The health indexes at multiple time points are compared and analyzed to identify trends and early warn of cardiovascular health deterioration.

[0018] Further, a health pre-evaluation system based on information monitoring, the system comprises:

[0019] An acquisition of heart rate feature pattern information module is configured to acquire electrocardiogram (ECG) data of a user, analyze a target ECG waveform, extract cardiac electrophysiological parameters, including heart rate, heart rate variability, and heart rate rhythm, identify a heart rate feature pattern of the user, the measurement values of the heart rate feature pattern including average heart rate, HRV parameters, heart rate pattern type, QRS time limit, and QT time limit, evaluate the periodic changes of ECG effects, and obtain heart rate feature pattern information. A physiological correlation analysis module is configured to generate physiological correlation analysis results based on the heart rate feature pattern information, collect multiple physiological parameters of the user in real time, including blood pressure, blood oxygen saturation, and activity intensity, analyze the mutual influence relationship between the multiple physiological parameters and the cardiac mode measurement values, evaluate the cardiac regulation efficiency of the user, combine the correlation coefficient, and obtain physiological correlation analysis results. An abnormal event detection result generation module is configured to monitor and identify abnormal changes in cardiac electrophysiological parameters based on the physiological correlation analysis results through time series analysis, identify abnormal causes and classify ECG abnormalities, including arrhythmia, ECG waveform abnormality, and blood pressure abnormality, and generate abnormal cardiovascular event detection results. A health pre-evaluation module is configured to evaluate the cardiovascular health status of the user based on the abnormal detection results by comprehensively analyzing abnormal ECG and related events of the user, and calculate health status prediction values at multiple time points by using time series analysis to evaluate the cardiovascular health change trend, thereby realizing continuous evaluation of the health status. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 FIG. 1 is a schematic diagram of the health pre-evaluation method based on information monitoring according to the present application. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the present application will be described in detail below in conjunction with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0022] Many particular details are set forth in the following description in order to provide a thorough understanding of the application. The embodiments described are merely exemplary in nature and do not limit the scope of the application. Based on the embodiments of the application, any other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of the application.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0024] One embodiment of the application is a health pre-evaluation method based on information monitoring, the method comprising: Obtaining electrocardiogram (ECG) data of a user, analyzing target ECG waveforms, extracting cardiac electrophysiological parameters, including heart rate, heart rate variability (HRV) standard deviation, and heart rate rhythm, identifying heart rate feature patterns of the user, the measurement values of the heart rate feature patterns including average heart rate, HRV parameters, heart rate pattern type, QRS time limit, and QT time limit, evaluating periodic changes of ECG effects, and obtaining heart rate feature pattern information; Based on the heart rate feature pattern information, real-time collection of multiple physiological parameters of the user, including blood pressure, blood oxygen saturation, and activity intensity, analysis of the mutual influence relationship between the multiple physiological parameters and the cardiac pattern measurement values, evaluation of the cardiac regulation efficiency of the user, combination of the correlation coefficients, and obtaining of physiological correlation analysis results; Based on the physiological correlation analysis results, monitoring and identifying abnormal changes in cardiac electrophysiological parameters through time series analysis, identifying abnormal causes and classifying ECG abnormalities, including arrhythmia, ECG waveform abnormalities, and blood pressure abnormalities, and generating abnormal cardiovascular event detection results; Based on the abnormal detection results, comprehensive analysis of abnormal ECG and related events of the user, evaluation of the cardiovascular health status of the user, calculation of health status prediction values at multiple time points using time series analysis, evaluation of the cardiovascular health change trend, and continuous evaluation of the health status.

[0025] One embodiment of the application, the cardiac pattern feature information includes heart rate parameters, HRV parameters, periodicity of RR intervals, QT intervals, and abnormal heart rhythm types; The correlation analysis results are specifically the correlation coefficient of heart rate and blood pressure, the dynamic correlation of HRV and SpO2, and the parameter variability under exercise load; The abnormal identification results include heart rate disorder information, HRV abnormality analysis, QRS waveform variation detection data, and blood pressure abnormality identification; The health condition evaluation information is specifically electrocardiogram variation indexes, blood pressure steady state level and HRV trend analysis results.

[0026] In one embodiment of the present application, the heart rate variability standard deviation is calculated, including: Based on electrocardiogram data, R waves are automatically detected, the start and end time of each heartbeat is identified, and the following operations are performed:

[0027] wherein, RRi represents the RR interval of the i th heartbeat, ti represents the time point corresponding to the end of the i th heartbeat, ti-1 represents the time point corresponding to the start of the i th heartbeat; The heart rate variability standard deviation is calculated based on the RR interval:

[0028] wherein, σn represents the heart rate variability standard deviation, and N represents the total number of heartbeats detected, RRi represents the RR interval of the i th heartbeat, μ represents the average value of the RR interval.

[0029] In one embodiment of the present application, based on the heart mode feature information, the blood pressure, blood oxygen saturation and activity intensity of the user are collected in real time by using multiple physiological monitoring devices; The physiological parameter data set is constructed, and the electrocardiogram parameters such as heart rate and HRV are combined; The heart rate and blood pressure, the HRV and the blood oxygen saturation are analyzed by statistical correlation, the dynamic change of the cardiovascular state is evaluated, and the correlation coefficient is calculated:

[0030] wherein, X is a physiological parameter measurement value, Y is a heart mode measurement value, ρ represents the correlation coefficient.

[0031] In one embodiment of the present application, the health pre-evaluation method based on information monitoring evaluates the heart regulation efficiency, including: The heart regulation efficiency can be comprehensively evaluated according to the following model:

[0032] wherein, wi represents a weight coefficient, σn represents the heart rate variability, ρ1 represents the correlation coefficient of the heart rate and the blood pressure, ρ2 represents the correlation coefficient of the heart rate and the blood oxygen.

[0033] One embodiment of the present application is a health pre-evaluation system based on information monitoring, which comprises: Pretreatment of electrocardiogram, blood pressure and other data for abnormal rhythm analysis; Calculate abnormal detection threshold:

[0034] Wherein, is the observation value at time t, is the sample mean, is the sample standard deviation, is the standard score; Abnormal arrhythmia, significant decrease in HRV, QRS and QT interval abnormal events are found through abnormal detection threshold; Classify abnormal events, including atrial fibrillation, premature ventricular contraction, ST segment abnormality and blood pressure abnormality, and generate abnormal cardiovascular event results.

[0035] One embodiment of the present application is a cardiovascular health status index modeling method, which is evaluated as follows:

[0036] Wherein, represents the number of recorded arrhythmia events, represents the HRV abnormal event count, represents the QRS time limit variation index, represents the blood pressure variation index, and D represents the physiological load index, represents the calculated cardiovascular health status index.

[0037] One embodiment of the present application is a health pre-evaluation method based on information monitoring, which comprises: Establish a time series prediction model: Based on the time series health status index, a model is constructed:

[0038] Wherein, is the cardiovascular health index at time t, is the autoregressive coefficient, is the moving average coefficient, is the white noise term; Compare and analyze the health index at multiple time points to identify trends and warn of cardiovascular health deterioration.

[0039] One embodiment of the present application is a health pre-evaluation system based on information monitoring, which comprises: The heart rate feature pattern information module is configured to acquire electrocardiogram (ECG) data of a user, analyze a target ECG waveform, extract cardiac electrophysiological parameters, including heart rate, heart rate variability, and heart rate rhythm, identify a heart rate feature pattern of the user, measure values of the heart rate feature pattern including average heart rate, HRV parameters, heart rate pattern type, QRS time limit, and QT time limit, and evaluate periodic changes of ECG effects to obtain heart rate feature pattern information. The physiological correlation analysis module is configured to generate physiological correlation analysis results based on the heart rate feature pattern information, collect multiple physiological parameters of the user in real time, including blood pressure, blood oxygen saturation, and activity intensity, analyze mutual influence relationships between the multiple physiological parameters and the cardiac pattern measurement values, evaluate cardiac regulation efficiency of the user, and obtain physiological correlation analysis results in combination with the correlation coefficients. The abnormal event detection result generation module is configured to monitor and identify abnormal changes of the cardiac electrophysiological parameters through time series analysis based on the physiological correlation analysis results, identify abnormal causes, and classify ECG abnormalities, including arrhythmia, ECG waveform abnormality, and blood pressure abnormality, and generate abnormal cardiovascular event detection results. The health pre-evaluation module is configured to evaluate a cardiovascular health status of the user by comprehensively analyzing abnormal ECG and related events of the user based on the abnormal detection results, calculate health status prediction values at multiple time points by using time series analysis, evaluate a cardiovascular health change trend, and realize continuous evaluation of the health status.

[0040] The working principle and effect of the above technical solution are: real-time acquisition of electrocardiogram (ECG) data of the user through an ECG device, denoising and feature extraction of the original ECG signal, identification of ECG waveforms such as P wave, QRS wave and T wave, and then calculation of cardiac electrophysiological parameters such as heart rate (HR), heart rate variability (HRV) standard deviation and heart rate rhythm; cardiac feature parameter extraction and pattern recognition, in-depth analysis of the collected data, extraction of detailed ECG parameters such as average heart rate, HRV parameters, heart rate pattern type, QRS time limit and QT time limit, evaluation of the periodic changes of the ECG signal, identification and classification of the user's heart rate feature mode; multi-physiological parameter correlation acquisition and analysis, synchronous acquisition of other physiological parameters (such as blood pressure, blood oxygen saturation, activity intensity, etc.), based on time alignment and data fusion technology, analysis of the correlation between these physiological parameters and ECG feature parameters, evaluation of the heart regulation efficiency, and obtaining of the physiological correlation analysis result; abnormal change detection and event classification, application of time series analysis method to real-time monitoring of the detected changes in cardiac electrophysiological parameters. Detecting abnormal changes in the data and identifying abnormal types (such as arrhythmia, ECG waveform abnormality, blood pressure abnormality, etc.) using intelligent classification method, forming abnormal cardiovascular event detection results; comprehensive health assessment and trend prediction, comprehensive analysis of the detected abnormal events and daily monitoring data, assessment of the user's cardiovascular health status through an algorithm model, and prediction of the health status change trend at different time points in the future based on historical data using time series analysis, realizing continuous and dynamic assessment of cardiovascular health. Precise ECG parameter extraction and identification can efficiently and accurately extract key ECG parameters and heart rate patterns, realize personalized ECG analysis of the user, and improve the accuracy of ECG interpretation; multi-parameter joint analysis can comprehensively reflect the health status, realize dynamic joint analysis of cardiac function and important physiological indicators by integrating multiple parameters such as blood pressure, blood oxygen and activity, reflect the user's real cardiovascular regulation ability and health status; intelligent abnormal detection and health warning can automatically identify ECG abnormalities and cardiovascular events, timely issue health risk warnings, and improve the efficiency of early detection and intervention of cardiovascular diseases; dynamic health trend prediction can predict future health trends based on historical and real-time data, helping the user to understand health risks early; realizing non-invasive and continuous health monitoring and assessment, providing personalized and long-term health management support for users, doctors or health management platforms, and improving the intelligent level of health services.

[0041] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A health pre-assessment method based on information monitoring, characterized in that: The method comprises: Acquire user electrocardiogram (ECG) data, analyze target ECG waveforms, extract cardiac electrophysiological parameters, including heart rate, heart rate variability standard deviation, and heart rate rhythm, identify the user's heart rate characteristic pattern, including average heart rate, HRV parameters, heart rate pattern type, QRS duration, and QT duration, evaluate periodic changes in ECG function, and obtain heart rate characteristic pattern information; Based on the heart rate characteristic pattern information, multiple physiological parameters of the user are collected in real time, including blood pressure, blood oxygen saturation, and activity intensity, and the mutual influence relationship between the multiple physiological parameters and the heart pattern measurement value is analyzed to evaluate the user's heart regulation efficiency. Combined with the correlation coefficient, a physiological correlation analysis result is obtained; Based on the physiological correlation analysis results, through time series analysis, abnormal changes in cardiac electrophysiological parameters are monitored and identified, the causes of abnormalities are identified, and ECG abnormalities are classified, including arrhythmias, ECG waveform abnormalities, and blood pressure abnormalities, to generate abnormal cardiovascular event detection results; Based on the abnormal detection results, the user's abnormal electrocardiogram and related events are comprehensively analyzed to evaluate the user's cardiovascular health status. Time series analysis is used to calculate the health status prediction values ​​at multiple time points, evaluate the trend of cardiovascular health changes, and achieve continuous assessment of health status.

2. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: The cardiac pattern characteristic information includes heart rate parameters, HRV parameters, RR interval periodicity, QT interval and abnormal rhythm type; The correlation analysis results specifically include the correlation coefficient between heart rate and blood pressure, the dynamic correlation between HRV and SpO2, and the parameter variability under exercise load; The abnormality identification results include arrhythmia information, HRV abnormality analysis, QRS waveform variation detection data and blood pressure abnormality identification; The health status assessment information specifically includes electrocardiogram variability indicators, blood pressure steady-state levels, and HRV trend analysis results.

3. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: Calculates the standard deviation of heart rate variability, including: Based on the ECG data, the R wave is automatically detected, the start and end time of each heartbeat are identified, and the following calculations are performed: in, represents the RR interval of the i-th heartbeat, represents the time point corresponding to the termination of the i-th heartbeat, represents the time point corresponding to the onset of the i-th heartbeat; Calculate the standard deviation of heart rate variability based on the RR interval: in, represents the standard deviation of heart rate variability, N represents the total number of heart beats detected, represents the RR interval of the i-th heartbeat, represents the mean RR interval.

4. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: Calculate correlation coefficients, including: Based on cardiac pattern feature information, a variety of physiological monitoring devices are used to collect the user's blood pressure, blood oxygen saturation, and activity intensity in real time; Construct a physiological parameter data set, combining ECG parameters such as heart rate and HRV; Statistical correlation analysis is performed on heart rate and blood pressure, HRV and blood oxygen saturation to evaluate the dynamic changes in cardiovascular status and calculate the correlation coefficient: Among them, X is the physiological parameter measurement value, Y is the cardiac mode measurement value, represents the correlation coefficient.

5. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: Assess cardiac regulatory efficiency, including: Cardiac regulation efficiency can be comprehensively evaluated according to the following model: in, represents the weight coefficient, represents heart rate variability, represents the correlation coefficient between heart rate and blood pressure, Represents the correlation coefficient between heart rate and blood oxygen.

6. A health pre-assessment method based on information monitoring, characterized in that: The method comprises: Pre-processing of ECG, blood pressure and other data for abnormal rhythm analysis; Calculate the anomaly detection threshold: in, is the observation value at time t, is the sample mean, is the sample standard deviation, is the standard score; Abnormal detection thresholds were used to detect arrhythmias, significant decreases in HRV, and abnormal QRS and QT intervals; Abnormal events are classified, including atrial fibrillation, premature ventricular contraction, ST segment abnormality and abnormal blood pressure, to generate abnormal cardiovascular event results.

7. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: The cardiovascular health status index modeling is comprehensively evaluated as follows: in, Indicates the number of recorded arrhythmia events, Indicates the HRV abnormal event count, Indicates the QRS duration variation index, represents the blood pressure variation index, D represents the physiological load index, Represents the calculated cardiovascular health status index.

8. The health pre-assessment method based on information monitoring according to claim 1, characterized in that: Build a time series forecasting model: Based on the time series health status index, build a model: in, is the cardiovascular health index at time t, is the autoregressive coefficient, is the moving average coefficient, is the white noise term; Compare and analyze health indices at multiple time points to identify trends and warn of deteriorating cardiovascular health.

9. A health pre-assessment system based on information monitoring, characterized in that: The system comprises: A heart rate characteristic pattern information acquisition module is used to acquire user electrocardiogram (ECG) data, analyze the target ECG waveform, extract cardiac electrophysiological parameters, including heart rate, heart rate variability, and heart rate rhythm, identify the user's heart rate characteristic pattern, and the measured values ​​of the heart rate characteristic pattern include average heart rate, HRV parameters, heart rate pattern type, QRS duration, and QT duration, evaluate the periodic changes of electrocardiogram (ECG) functions, and obtain heart rate characteristic pattern information; a physiological correlation analysis module, configured to generate physiological correlation analysis results based on the heart rate characteristic pattern information, collect multiple physiological parameters of the user in real time, including blood pressure, blood oxygen saturation, and activity intensity, analyze the mutual influence relationship between the multiple physiological parameters and the cardiac pattern measurement value, evaluate the user's cardiac regulation efficiency, and obtain physiological correlation analysis results based on the correlation coefficient; Generate abnormal event detection result module, which is used to monitor and identify abnormal changes in cardiac electrophysiological parameters through time series analysis based on the physiological correlation analysis results, identify abnormal causes and classify ECG abnormalities, including arrhythmia, ECG waveform abnormalities and blood pressure abnormalities, and generate abnormal cardiovascular event detection results; The health pre-assessment module is used to evaluate the user's cardiovascular health status based on the abnormal detection results by comprehensively analyzing the user's abnormal electrocardiogram and related events; and use time series analysis to calculate the health status prediction values ​​​​at multiple time points, evaluate the trend of cardiovascular health changes, and realize continuous assessment of health status.

Images