CN118430774A

CN118430774A - Heart aging degree prediction method, electronic device, and readable storage medium

Info

Publication number: CN118430774A
Application number: CN202410451146.1A
Authority: CN
Inventors: 刘澄玉; 李昱旻; 凌力; 刘耀诚; 潘俊杰; 李欢; 周亚楠; 杨晨熙; 李建清
Original assignee: Goertek Inc; Southeast University
Current assignee: Goertek Inc; Southeast University
Priority date: 2024-04-15
Filing date: 2024-04-15
Publication date: 2024-08-02

Abstract

The application discloses a heart aging degree prediction method, electronic equipment and a readable storage medium, and relates to the technical field of medicine, wherein the heart aging degree prediction method comprises the following steps: synchronously acquiring physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals; extracting features of the physiological signal to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, a pulse transmission time and a pulse arrival time; and inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model. The application improves the accuracy of predicting the heart aging degree.

Description

Heart aging degree prediction method, electronic device, and readable storage medium

Technical Field

The present application relates to the field of medical technology, and in particular, to a heart aging degree prediction method, an electronic device, and a readable storage medium.

Background

The heart age has been attracting more and more attention as a feature for measuring the degree of heart aging in humans. In real life, a phenomenon that the appearance of a person is bigger or smaller than the actual age is more acceptable to people; the fact that the heart age of a person does not exactly coincide with the actual age of the person is difficult to understand by a person in general. Due to the different degrees of heart protection and the influence of the overall health condition, the heart age is different from the actual age of the person, and the unhealthy life style, habit and behavior of the person usually lead the person to age in advance. Knowing the true heart age of all persons will help understand the physical condition, understanding improvements in lifestyle, habits, behavior and other precautions may reduce the risk of future heart attack. For most people, the computing method enables people to know how much potential benefit the body is in maintaining a well-being lifestyle, habit, behavior at a young age.

The heart age prediction method is mainly to predict by means of electrocardiosignals and questionnaires, and the electrocardiosignals can reflect part of heart information, but other factors affecting the heart aging degree cannot be evaluated, so that the heart aging degree prediction accuracy is low.

The foregoing background is only for the purpose of providing an understanding of the principles and concepts of the application and is not necessarily related to the prior art or the technical teaching of this patent application, but is not necessarily related to the prior art.

Disclosure of Invention

The application mainly aims to provide a heart aging degree prediction method, a heart aging degree prediction device, electronic equipment and a readable storage medium, and aims to solve the technical problem of how to improve the accuracy of heart aging degree prediction.

To achieve the above object, the present application provides a heart aging degree prediction method comprising:

synchronously acquiring physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals;

Extracting features of the physiological signal to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, a pulse transmission time and a pulse arrival time;

And inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model.

Optionally, the step of extracting features of the physiological signal to obtain signal features includes:

Acquiring ejection time based on the pulse signal in the same cardiac cycle of the physiological signal, and taking the ejection time acquired based on the pulse signal as first ejection time;

acquiring ejection time based on the heart sound signal in the cardiac cycle, and taking the ejection time acquired based on the heart sound signal as second ejection time;

Taking as a first ratio a ratio of the first ejection time to the second ejection time in each of the cardiac cycles;

the mean of all the first ratios is taken as the ejection time ratio.

Optionally, the step of acquiring ejection time based on the heart sound signal in the cardiac cycle includes:

performing heart sound segmentation on the heart sound signals to obtain first heart sound and second heart sound corresponding to the heart sound signals;

Determining an aortic valve opening time of the first heart sound in the cardiac cycle, and determining an aortic valve closing time of the second heart sound in the cardiac cycle;

a time difference between the aortic valve opening time and the aortic valve closing time is determined, and the time difference is taken as a ejection time acquired based on the heart sound signal.

Optionally, the step of determining the aortic valve opening time of the first heart sound in the cardiac cycle comprises:

taking a heart sound peak value of the first heart sound in the cardiac cycle as a first peak value;

adjusting the first peak value based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is smaller than the first peak value;

Determining a first maximum value of the first heart sounds in the cardiac cycle based on the first threshold value, and taking the corresponding time of each first maximum value as a first time, wherein the first maximum value comprises all maximum heart sound values which are larger than the first threshold value in the maximum heart sound values of the first heart sounds in the cardiac cycle;

Determining a first target time based on each first time, and taking the first target time as the aortic valve opening time of the first heart sound, wherein the first target time comprises the median time of all the first times.

Optionally, the step of determining the aortic valve closing time of the second heart sound in the cardiac cycle comprises:

taking a heart sound peak value of the second heart sound in the cardiac cycle as a second peak value;

Adjusting the second peak value based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is smaller than the second peak value;

Determining a second maximum value of the second heart sounds in the cardiac cycle based on the second threshold value, and taking the corresponding time of each second maximum value as a second time, wherein the second maximum value comprises all maximum heart sound values which are larger than the second threshold value in the maximum heart sound values of the second heart sounds in the cardiac cycle;

And determining a second target time based on each second time, and taking the second target time as the aortic valve closing time of the second heart sound, wherein the second target time comprises the median time of all the second times.

Optionally, the step of extracting features of the physiological signal to obtain a signal feature further includes:

for the same cardiac cycle of the physiological signal, acquiring a pre-ejection time based on an electrocardiosignal in the cardiac cycle and a heart sound signal in the cardiac cycle;

Taking a time difference between the corresponding first ejection time and the second ejection time in the cardiac cycle as an ejection time difference;

taking the ratio of the pre-ejection time to the ejection time difference corresponding to each cardiac cycle as a third ratio;

the mean value of all the third ratios is taken as the ejection time difference ratio.

For the same cardiac cycle of the physiological signal, acquiring a fast ejection time based on the pulse signal in the cardiac cycle, and taking the fast ejection time acquired based on the pulse signal as a first fast ejection time;

acquiring the systole time corresponding to the heart sound signal in the cardiac cycle, and adjusting the systole time based on a preset adjustment coefficient to obtain a second rapid ejection time;

Taking the ratio of the first rapid ejection time to the second rapid ejection time corresponding to each cardiac cycle as a second ratio;

the mean of all the second ratios is taken as the fast ejection time ratio.

taking the time difference between the first rapid ejection time and the second rapid ejection time corresponding to the cardiac cycle as a rapid ejection time difference;

taking the ratio of the pre-ejection time to the fast ejection time difference corresponding to each cardiac cycle as a fourth ratio;

the mean value of all the fourth ratios is taken as the fast ejection time difference ratio.

In addition, in order to achieve the above object, the present application provides a heart aging degree prediction apparatus comprising:

the physiological signal acquisition module is used for synchronously acquiring physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals;

The feature extraction module is used for carrying out feature extraction on the physiological signals to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, pulse transmission time and pulse arrival time;

And the heart age prediction module is used for inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model.

The application also provides an electronic device, which is entity equipment, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the heart aging degree prediction method as described above.

The present application also provides a readable storage medium which is a computer readable storage medium having stored thereon a program for realizing the heart aging degree prediction method, the program for realizing the heart aging degree prediction method being executed by a processor to realize the steps of the heart aging degree prediction method as described above.

The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of a heart aging degree prediction method as described above.

The application synchronously collects physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals; extracting features of the physiological signal to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, a pulse transmission time and a pulse arrival time; and inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model. Thus, compared with the mode of predicting the heart aging degree based on electrocardiosignals in the prior art, the embodiment of the application predicts the heart age based on the combined characteristics of the electrocardiosignals, the pulse signals, the physiological signals such as heart sound signals and the like, the rapid ejection time ratio, the ejection time difference ratio, the rapid ejection time difference ratio, the pulse transmission time, the pulse arrival time and the like, so that the heart aging degree is estimated based on the heart age, the influence of various factors such as the ejection time, the rapid ejection time, the pulse transmission time, the pulse arrival time and the like on the heart aging degree is comprehensively considered, the heart age is comprehensively estimated from three angles of the electrocardiosignals, the heart sound signals and the pulse signals, and the heart aging degree prediction accuracy is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a flow chart of a first embodiment of a method for predicting the degree of heart aging according to the present application;

FIG. 2 is a schematic diagram of a signal processing flow of a heart aging degree prediction method according to the present application;

FIG. 3 is a schematic diagram of the signal feature extraction and heart age assessment flow chart of the heart aging degree prediction method of the present application;

FIG. 4 is a flow chart of a method for predicting the degree of heart aging according to the present application;

FIG. 5 is a schematic view of a device module of the heart aging degree prediction device of the present application;

fig. 6 is a schematic diagram of an apparatus structure of a hardware operating environment related to a heart aging degree prediction apparatus according to an embodiment of the present application.

The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

In order to make the above objects, features and advantages of the present invention more comprehensible, the following description of the embodiments accompanied with the accompanying drawings will be given in detail. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Example 1

The present application proposes a method for predicting the degree of heart aging according to a first embodiment, referring to fig. 1, the method for predicting the degree of heart aging includes:

Step S10, synchronously acquiring physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals;

The heart aging degree prediction method in the present embodiment can be applied to a portable device, and the portable device can be specifically a smart watch, a smart bracelet, and the like.

Illustratively, the portable device includes a housing, and a sensor disposed in the housing for acquiring a physiological signal. The sensor comprises a first sensor for collecting heart sound signals, a second sensor for collecting pulse signals, and a third sensor for collecting electrocardiosignals, wherein the first sensor can be one or more of a VPU (Voice Pick Up) sensor and a microphone sensor, the second sensor can be an optoelectronic pulse sensor, the third sensor can be an electrode sensor, the electrode sensor can comprise three electrodes, the first electrode and the third electrode are used for forming a loop and used for electrocardiosignal collection, the second electrode provides a reference point to eliminate potential difference between a body and portable equipment, and the signal to noise ratio of electrocardiosignal collection is improved.

Further, the portable device includes a device processor for executing program code in the memory to perform various functions of the portable device; the time calibration module is used for displaying real-time and synchronously acquiring and calibrating data; the interaction module is used for collecting personalized information of the user, and the physiological signal acquisition module is used for collecting physiological signals and acceleration gyroscope signals related to blood pressure measurement of the user. The physiological signals related to blood pressure measurement include electrocardiosignals, pulse signals and heart sound signals. The signal processing module is used for processing the physiological signals collected by the physiological signal measuring module in real time, and the signal processing step mainly comprises a signal normalization module, a signal filtering module and signal quality evaluation. And the wireless communication module is used for transmitting the acquired physiological signal data, the heart age of the user and the personalized information of the user to the server or the terminal through the wireless module. And the heart age prediction module is used for analyzing physiological signals and/or personalized information of the user, and finally predicting the heart age and returning a heart age prediction result.

In addition, the physiological signal acquisition module can also comprise a 6-axis signal acquisition module, acceleration and gyroscope signals are mainly acquired through the 6-axis signal acquisition module, and the 6-axis signal acquisition module mainly comprises a 6-axis sensor integrated in equipment. Before heart age prediction is carried out, the 6-axis signal acquisition module can calculate the current Euler angle and assist a user to position and acquire the position and the posture; in the heart age prediction process, the 6-axis signal acquisition module can monitor the movement condition of the arm of a user, is combined with electrocardiosignals, heart sound signals and pulse signals, performs denoising of physiological signals, and can improve the signal-to-noise ratio of the signals in the acquisition process.

It will be appreciated that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on portable devices. It may have more or fewer components described above, or certain components may be combined, or certain components may be split, or different arrangements of components may be provided. The various components described above may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing or application specific integrated circuits.

Further, the physiological signals are collected simultaneously at the same time, and the relation between the electrocardiosignal, the pulse signal and the heart sound signal and the time is determined so as to ensure the strict synchronism of the physiological signals. And the time of data acquisition from the start can be recorded by the real-time after the calibration.

Step S20, extracting features of the physiological signals to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, pulse transmission time and pulse arrival time;

Further, before extracting the signal features of the physiological signal, in order to improve the accuracy of the extracted signal features, signal processing may be performed on the physiological signal, such as filtering, noise reduction, segmentation, and the like, on the physiological signal. And extracting the characteristics based on the processed physiological signals to obtain signal characteristics.

In a possible embodiment, referring to fig. 2, before the step of extracting features from the physiological signal to obtain signal features, the method includes:

Step S201, performing signal preprocessing on the physiological signal to obtain a preprocessed physiological signal, wherein the signal preprocessing comprises one or more of filtering, normalization and noise reduction;

In this embodiment, the signal preprocessing preferably includes normalization, filtering, and noise reduction. Optionally, the acquired physiological signals are normalized, further filtered by a pre-designed zero-phase shift Butterworth filter, the electrocardiosignal, the pulse signal and the heart sound signal are filtered, high-frequency noise interference and baseline drift are eliminated, the filtered data and the acceleration signal are subjected to self-adaptive filtering for secondary treatment, and noise generated by motion artifacts is filtered, so that a clean high-quality physiological signal is obtained.

Step S202, evaluating the preprocessed physiological signals to obtain preprocessed physiological signals, wherein the signal preprocessing comprises one or more of filtering, normalizing and noise reduction;

As one embodiment, the signal quality of each segment of sub-physiological signal is evaluated, which may be that in each sub-physiological signal segment, RR intervals, KSQI indexes, etc. of the electrocardiograph signal, peak intervals, standard deviations of peak intervals, number of zero crossings, etc. of the pulse signal, SSQI coefficients of the heart sound signal, signal mean value, etc. are calculated, and then the signal segment interfered by noise is eliminated by combining with the variation time of the amplitude of the acceleration signal (such as excluding the sub-physiological signal overlapped with the amplitude time of the acceleration signal). The features are input into a classification model, such as an SVM (Support Vector Machine ) model, and each segment of the signal is subjected to rough classification, such as separation into usable sub-physiological signals and unusable sub-physiological signals, and signal features are extracted based on the usable sub-physiological signals.

Step S202, determining the signal duration of the preprocessed physiological signal;

Step S203, if the duration of the signal is longer than the preset duration, performing signal segmentation processing on the preprocessed physiological signal to obtain a plurality of segments of sub-physiological signals;

Step S204, signal quality of each segment of sub-physiological signal is evaluated, a signal quality evaluation result is obtained, the sub-physiological signal with the signal quality evaluation result meeting a preset condition is taken as a target sub-physiological signal, and signal characteristics are extracted based on the target sub-physiological signal, wherein the preset condition comprises that the signal quality evaluation result is an available sub-physiological signal.

The pre-processed physiological signals are subjected to signal segmentation processing to obtain multi-segment sub-physiological signals, and if the duration of the signals is 12 seconds and the duration of the signals is 3 seconds, the signals can be divided into four sub-physiological signals of 0-3 seconds, 3-6 seconds, 6-9 seconds and 9-12 seconds. The physiological signals may also be segmented in a time overlapping manner, each signal being divided into signal segments of a fixed duration (sig_t), the overlapping length being any value in the range (0-sig_t-1). If the duration of the signal is 9 seconds, and the signal segmentation is performed with the fixed duration of 3 seconds and the overlapping length of 1 second, the signal segmentation can be divided into four sub-physiological signals of 0-3 seconds, 2-5 seconds, 4-7 seconds and 6-9 seconds.

Further, after the preprocessed physiological signals are subjected to signal segmentation processing to obtain a plurality of segments of sub physiological signals, the sub physiological signals with poor signal quality can be deleted for evaluating the signal quality of each segment of sub physiological signals, the signal characteristics are extracted based on the sub physiological signals with good signal quality, and the effectiveness of the extracted signal characteristics is ensured.

The signal characteristics include, but are not limited to, a ratio of ejection times, a ratio of fast ejection times, a ratio of ejection time differences, a ratio of fast ejection times differences, pulse transit time, pulse arrival time, as may also include time domain characteristics, frequency domain characteristics, time frequency characteristics, statistical characteristics, and the like.

The Pulse Arrival Time (PAT) may be a time difference between an R-wave peak point of the electrocardiograph signal and a feature point of the pulse signal, where the feature point may be a peak point, a valley point, a isthmus time point, and the like of the pulse signal, one or more pulse wave feature points may be selected to obtain one or more corresponding pulse arrival times, that is, the pulse arrival time includes one or more pulse arrival times, and the user may set a rule for selecting the pulse arrival time according to an actual situation.

The Pulse Transfer Time (PTT) may be a time difference between an aortic valve opening time point of a heart sound signal and a feature point of the pulse signal, where the feature point may be a peak point, a valley point, a isthmus time point, and the like of the pulse signal, and one or more pulse wave feature points may be selected to obtain one or more corresponding pulse transfer times, that is, the pulse transfer time includes one or more pulse transfer times, and the user may set a rule for selecting the pulse transfer time according to an actual situation.

Time domain features include, but are not limited to, the following: R-R intervals (RR), R-R Standard Deviation (SDNN), root mean square deviation (RMSSD) of electrocardiographic signals, etc.; PP interval (PP), half-width pulse width (PW 50), systolic time, diastolic time, rise time, fastest rise area, peak height, rise slope, etc. of the pulse signal; the first zero crossing point time, the last inflection point time, the slope of the peak value and the first zero crossing point, the slope of the peak value, the area of the peak value and the like of the VPG signal (the pulse signal is obtained by performing first-order differential processing); the method comprises the steps of (1) carrying out second-order differential processing on an APG signal (the pulse signal is obtained through second-order differential processing), wherein the time of the lowest point, the slope of the peak point and the lowest point, and the slope of the first zero crossing point and the slope of the lowest point; a first heart sound duration, a second heart sound duration, a systolic duration, a diastolic duration, etc. in the heart sound signal.

Frequency domain features include, but are not limited to, the following: electrocardiographic signal power spectral density; the pulse signal comprises a first component frequency and amplitude magnitude thereof, a second component frequency and amplitude magnitude thereof, and a third component frequency and amplitude magnitude thereof; heart sound signal S1 mainly constitutes frequencies, S2 mainly constitutes frequencies, etc.

Time-frequency characteristics include, but are not limited to, the following: wavelet coefficients, hilbert-yellow transform coefficients, mel-cepstral coefficients, linear prediction coefficient characteristics, etc.;

Statistical features include, but are not limited to, the following: kurtosis factor, skewness factor, standard deviation of characteristic sequences, etc.

In this embodiment, each cardiac cycle of the physiological signal is an extraction unit of a signal feature, that is, a sub-signal feature corresponding to the physiological signal in each cardiac cycle is extracted based on each cardiac cycle of the physiological signal, further, a mean value of the sub-signal features corresponding to each cardiac cycle is used as a final signal feature and is input into a heart age prediction model to predict heart age, wherein blood pressure is one of important factors affecting heart age, and pulse transfer time and pulse arrival time are related to blood pressure, so that heart age prediction is performed by using pulse transfer time and pulse arrival time, and accuracy of heart age prediction results can be improved.

Furthermore, after extracting the signal characteristics of each cardiac cycle, the outlier processing can be performed on all the sub-signal characteristics, and the abnormal characteristics can be deleted. Optionally, for each cardiac cycle of sub-signal features, outlier feature sequence processing is performed following the box plot principle, and an exemplary process flow may be as follows: s1, feature values of each segment of sub-signal feature form an n-dimensional feature sequence X (t), wherein n is the number of features; s2, setting the upper edge and the lower edge of each dimension feature, for example, calculating the upper quartile Q1i, the lower quartile Q3i and the quartile IQRi of each dimension feature, taking the upper edge Q1i-1.5IQRi and the lower edge Q3i+1.5IQRi, wherein i=1: n; s3, filtering abnormal data of each dimension characteristic outside the upper edge and the lower edge; s4, obtaining a characteristic sequence S (t) with abnormal values removed. S5, calculating the average value of the screened feature sequences to obtain average value signal features S-, and obtaining final signal features.

And step S30, inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model.

The trained blood pressure model can be a heart aging degree prediction model trained based on a database, wherein the database at least comprises heart age data and signal characteristic data corresponding to each heart age data. The database may be obtained by pre-collecting heart age and signal characteristic data.

Further, in order to improve the prediction accuracy of the heart aging degree prediction model and realize personalized prediction of heart age, physiological signals of a detection object can be collected for many times in advance, an individual data set is established, and the individual data set is used as a database for training the prediction model to complete training of the heart aging degree prediction model. The detection object can use a user corresponding to the current login account of the portable device.

As one embodiment, the pre-training process of the heart age prediction model may be: s1, selecting characteristics from a multi-category characteristic library through an existing database; s2, calculating mutual information between the features, wherein p (x) is the probability of occurrence of x, p (y) is the probability of occurrence of y, and p (x, y) is the probability of simultaneous occurrence of x and y, namely the joint probability. The higher the mutual information, the higher the degree of dependence between the two features. Removing the features below the mutual information threshold value to obtain a new feature subset; s3, calculating a correlation coefficient between the new feature subset and the blood pressure, wherein the higher the correlation coefficient is, the higher the linear correlation between the representative feature and the blood pressure is; s4, sorting the feature subsets from high to low according to the correlation coefficient to obtain sorted feature subsets; s5, dividing the ordered feature subsets into a training set and a testing set, wherein the proportion of the training set to the testing set is 8:2; s6, aiming at the training set, performing feature number selection by adopting ten-fold cross validation and backward feature selection to obtain a feature subset S with the lowest RMSE (Root Mean Squared Error, root mean square error); s7, training a multiple linear regression model by using the final feature subset: wherein BP is the specific heart age, S is the optimal feature subset, ki is the fitting coefficient of the multiple linear regression model, and n is the dimension of the optimal feature subset.

In addition, the personalized features of the testers can be collected, the personalized features comprise, but are not limited to, height, age, weight, diet, sleep, whether the testers are drunk and smoked, past cardiovascular medical history, medical history and signal feature data are subjected to model training to obtain a heart age prediction model after the pre-training is completed, the personalized features of the testers are further obtained after the signal features are extracted based on physiological signals, the signal features and the personalized features are input into the personalized heart age prediction model after the pre-training is completed, heart age prediction results are output, and the influence of factors such as height, age, weight, diet, sleep, whether the testers are drunk and smoked, past cardiovascular medical history, medical history and the like on heart age is considered, so that the accuracy of heart aging degree prediction can be further improved.

Further, after the heart age prediction result is obtained, the heart age prediction result can be output on the portable device, and meanwhile, the heart age prediction result can be uploaded to a terminal or a server which is in communication connection with the portable device for a user to view, and the terminal and the server can be used for viewing historical heart age data of the user, so that diagnosis of doctors is facilitated. When the remote diagnosis and treatment is carried out, an AI medical large model is accessed, the heart age change rate and the personalized characteristics are used as the input of the large model, a doctor is assisted in carrying out remote treatment, advice in aspects of diet, work and rest and exercise is provided, and abnormal changes of heart ages are reduced.

In this embodiment, physiological signals are synchronously collected, where the physiological signals include an electrocardiograph signal, a pulse signal, and a heart sound signal; extracting features of the physiological signal to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, a pulse transmission time and a pulse arrival time; and inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model. Thus, compared with the mode of predicting the heart aging degree based on the electrocardiosignal in the prior art, the embodiment predicts the heart age based on the combined characteristics of the electrocardiosignal, the pulse signal, the physiological signal such as the heart sound signal, the rapid ejection time ratio, the ejection time difference ratio, the rapid ejection time difference ratio, the pulse transmission time, the pulse arrival time and the like, so that the heart aging degree is estimated based on the heart age, the influence of various factors such as the ejection time, the rapid ejection time, the pulse transmission time, the pulse arrival time and the like on the heart aging degree is comprehensively considered, the heart age is comprehensively estimated from three angles of the electrocardiosignal, the heart sound signal and the pulse signal, and the prediction accuracy of the heart aging degree is improved.

To facilitate understanding of the technical concept or technical principle of the present application, a specific embodiment is listed:

Referring to fig. 3 to 4, the heart aging degree prediction flow in this embodiment is as follows:

The portable device is started through the device switch, meanwhile, the portable device can be connected with the server and the mobile phone APP, after time calibration, a user can input personalized information such as height, age, weight, diet, sleep, alcoholism and smoking, past cardiovascular medical history, medical history and the like, or the personalized information of the user is stored in the portable device, the stored personalized information can also be directly obtained, physiological signals are collected, the physiological signals comprise electrocardiosignals, heart sound signals and pulse signals, the collected physiological signals are subjected to signal processing such as normalization, filtering, signal quality evaluation and the like, the evaluation result of the signal quality evaluation is that the physiological signals with high signal quality are subjected to feature extraction, physiological joint features and physiological signal features are extracted, wherein the joint features are the signal features extracted based on two or more physiological signals, such as pulse arrival time extracted based on electrocardiosignals and pulse signals, pulse transmission time extracted based on pulse signals and heart sound signals and the like, physiological signal features are signal features extracted based on single physiological signals, such as S1 time, diastole time, S2 time, systole time, PP interval, pulse signal descending isthmus time, ascending time, descending time and the like of heart sound signals, feature screening is carried out on the extracted physiological combined features, the physiological signal features and personalized features of users, abnormal values in the features are removed, redundant features are removed by utilizing mutual information rules and the like, the screened features are input into a heart age prediction model, heart age prediction is carried out, and a heart age prediction result is uploaded to the cloud.

It should be noted that the above-mentioned embodiments are only for understanding the present application, and do not constitute limitation of the heart aging degree prediction procedure and limitation of the application device of the present application, and it is within the scope of the present application to make more simple changes based on the technical concept.

Example two

In another embodiment of the present application, the same or similar content as that of the first embodiment may be referred to the description above, and will not be repeated. On the basis, in the case that the signal features include the ejection time ratio, the step of extracting the features of the physiological signal to obtain the signal features includes:

Step A10, for the same cardiac cycle of the physiological signal, acquiring ejection time based on the pulse signal in the cardiac cycle, and taking the ejection time acquired based on the pulse signal as first ejection time;

It will be appreciated that the same cardiac cycle (also called heart cycle, heart beat) for physiological signals, i.e. for different physiological signals.

The ejection time is acquired based on the pulse signal in the cardiac cycle, and the ejection time acquired based on the pulse signal is taken as the first ejection time. In particular, the time difference between the valley point of the pulse signal and the falling isthmus point in the cardiac cycle may be taken as the first ejection time.

Step a20 of acquiring a ejection time based on the heart sound signal in the cardiac cycle, and taking the ejection time acquired based on the heart sound signal as a second ejection time;

The first ejection time may specifically be a time difference between an aortic valve opening time and an aortic valve closing time of the heart sound signal in the cardiac cycle.

Step A30, regarding the ratio of the first ejection time to the second ejection time in each cardiac cycle as a first ratio;

The first ratio may be specifically, but not limited to, a first ejection time and a second ejection time, or a second ejection time and a first ejection time.

Step A40, taking the average value of all the first ratios as the ejection time ratio.

In this embodiment, the time ratio of the ejection time of the pulse signal to the ejection time of the heart sound signal is used as the signal characteristic to predict the heart age, thereby improving the heart age prediction accuracy. As the peripheral arterial stiffness increases, the peripheral arterial waveform rise time changes, resulting in longer ejection times and faster ejection times. While peripheral arterial stiffness increases, resulting in increased vascular resistance, the heart requires a shorter ejection time to ensure that a fixed amount of blood flow can exit the heart. This tends to change the time period before the ejection of the heart, thereby increasing the load on the heart and increasing the heart age, and hence the heart age can be predicted in all directions by the ratio of the ejection times.

In a possible embodiment, the step of acquiring ejection time based on the heart sound signal in the cardiac cycle comprises:

step B10, performing heart sound segmentation on the heart sound signals to obtain first heart sound and second heart sound corresponding to the heart sound signals;

specifically, the heart sound segmentation may be performed by using a preset hidden markov model, or may be performed by using other modes, such as a segmentation threshold, which is not limited in this embodiment.

Step B20, determining the aortic valve opening time of the first heart sound in the cardiac cycle, and determining the aortic valve closing time of the second heart sound in the cardiac cycle;

For ease of description and explanation to follow, the aortic valve open time is denoted AO and the aortic valve closed time is denoted AC.

Step B30 of determining a time difference between the aortic valve opening time and the aortic valve closing time, and taking the time difference as a ejection time acquired based on the heart sound signal.

In this embodiment, the time difference between the aortic valve opening time and the aortic valve closing time is used as the ejection time acquired based on the heart sound signal, so that the validity of the ejection time of the heart sound signal is ensured, and a data basis is provided for the subsequent calculation of the ejection time ratio.

In a possible embodiment, the step of determining the aortic valve opening time of the first heart sound in the cardiac cycle comprises:

Step C10, taking a heart sound peak value of the first heart sound in the cardiac cycle as a first peak value;

step C20, adjusting the first peak value based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is smaller than the first peak value;

the preset adjustment coefficient may be 0.7, 0.8, etc., which is not particularly limited in this embodiment.

Step C40, determining a first maximum value of the first heart sounds in the cardiac cycle based on the first threshold value, and taking the corresponding time of each first maximum value as a first time, wherein the first maximum value comprises all maximum heart sound values which are larger than the first threshold value in the maximum heart sound values of the first heart sounds in the cardiac cycle;

the maximum heart sound value, i.e. the maximum value in heart sound values.

And step C50, determining a first target time based on each first time, and taking the first target time as the aortic valve opening time of the first heart sound, wherein the first target time comprises the median time of all the first times.

All the first times may be sorted in order of time from small to large, and the median of the sorted first times is the median time, and the median time is the aortic valve opening time.

In this embodiment, for each cardiac cycle, the threshold is determined by the heart sound peak value in the cardiac cycle, so as to implement adaptive adjustment of the threshold, instead of determining the AO time by using a fixed threshold, and improve the accuracy of the AO time. The median of time is used as the occurrence time of the AO event, so that the extraction stability of the characteristics such as the ejection time of PTT and heart sound signals is improved.

In a possible embodiment, the step of determining the aortic valve closing time of the second heart sound in the cardiac cycle comprises:

step D10, taking a heart sound peak value of the second heart sound in the cardiac cycle as a second peak value;

Step D20, adjusting the second peak value based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is smaller than the second peak value;

The preset adjustment coefficient may be 0.7, 0.8, etc., which is not particularly limited in this embodiment. The preset adjustment coefficient for adjusting the second peak value and the preset adjustment coefficient for adjusting the first peak value can be the same or different, and can be set in advance by a user respectively and are mutually independent.

Step D30, determining a second maximum value of the second heart sounds in the cardiac cycle, and taking the corresponding time of each second maximum value as a second time, wherein the second maximum value comprises all maximum heart sound values which are larger than the second threshold value in the maximum heart sound values of the second heart sounds in the cardiac cycle;

and step D40, determining a second target time based on each second time, and taking the second target time as the aortic valve closing time of the second heart sound, wherein the second target time comprises the median time of all the second times.

Similarly, all the second times may be ordered in order of time from small to large, and the median of the ordered second times is the median time, which is taken as the aortic valve opening time.

In this embodiment, for each cardiac cycle, the threshold is determined by the heart sound peak value in the cardiac cycle, so that adaptive adjustment of the threshold is realized, instead of determining the AC time by a fixed threshold, and accuracy of the AC time is improved. The median of the time is used as the time of the occurrence of the AC event, so that the stability of the extraction of the characteristics such as the ejection time of PTT and heart sound signals is improved.

In a possible implementation manner, in a case that the signal features include a difference ratio of ejection times, the step of extracting features from the physiological signal to obtain the signal features includes:

step E10, for the same cardiac cycle of the physiological signal, acquiring the pre-ejection time based on the electrocardiosignals in the cardiac cycle and the heart sound signals in the cardiac cycle;

the pre-ejection time may specifically be a time difference between a peak value time point of the R wave of the electrocardiograph signal and an AO time point of the heart sound signal in the same cardiac cycle.

Step E20, taking a time difference between the corresponding first ejection time and the second ejection time in the cardiac cycle as an ejection time difference;

Step E30, taking the ratio of the pre-ejection time to the ejection time difference corresponding to each cardiac cycle as a third ratio;

step E40, taking the average value of all the third ratios as the ejection time difference ratio.

In the embodiment, the ejection time difference ratio of the pulse signal, the electrocardiosignal and the heart sound signal is used as the signal characteristic to predict the heart age, so that the heart age prediction accuracy is improved. As the peripheral arterial stiffness increases, the peripheral arterial waveform rise time changes, resulting in longer ejection times and faster ejection times. While peripheral arterial stiffness increases, resulting in increased vascular resistance, the heart requires a shorter ejection time to ensure that a fixed amount of blood flow can exit the heart. This tends to change the time period before the ejection of the heart, thereby increasing the load on the heart and increasing the heart age, and hence the heart age can be predicted in all directions by the ratio of the ejection time differences.

in this embodiment, the procedure for determining the aortic valve closing time and the aortic valve opening time is as follows:

1. performing beat-by-beat segmentation of heart sounds by using a hidden Markov model to obtain S1 time, systolic time, S2 time and diastolic time;

2. extracting peak values in the beat-by-beat (i.e. every cardiac cycle) S1 time, and setting 70% of the peak values as threshold values;

3. all maxima in the S1 time which are larger than a threshold value are calculated, and time indexes of the maxima are ordered according to the sequence from small to large;

4. Taking the median of all the time indexes as the occurrence time point of the AO events (namely the aortic valve opening time) in the heart beat, and finally obtaining the occurrence time sequence of the beat-by-beat AO events;

5. extracting peak values in the beat-by-beat S2 time, and setting 80% of the peak values as threshold values;

6. Calculating all maximum values which are larger than a threshold in the S2 time, and sequencing time indexes of the maximum values from small to large;

7. taking the median of all peak indexes as the occurrence time point of the AC event in the heart beat (namely the closing time of the aortic valve), and finally obtaining the occurrence time sequence of the AC event beat by beat.

It should be noted that the above embodiments are only for understanding the present application, and do not limit the determining procedure of the aortic valve closing time and the aortic valve opening time, and it is within the scope of the present application to make more simple transformations based on the technical concept.

Example III

In another embodiment of the present application, the same or similar content as that of the first embodiment, the second embodiment, and the third embodiment of the present application can be referred to the description above, and the description is omitted. On the basis, in the case that the signal features comprise the fast ejection time ratio, the step of extracting the features of the physiological signal to obtain the signal features comprises the following steps:

Step F10, for the same cardiac cycle of the physiological signal, acquiring a rapid ejection time based on the pulse signal in the cardiac cycle, and taking the rapid ejection time acquired based on the pulse signal as a first rapid ejection time;

The first fast ejection time may specifically be a time difference between a valley point and a peak point of the pulse signal in the cardiac cycle.

Step F20, acquiring the systole time corresponding to the heart sound signal in the cardiac cycle, and adjusting the systole time based on a preset adjustment coefficient to obtain a second rapid ejection time;

it can be understood that, after the heart sound signal is divided, the systolic period time and the diastolic period time of each cardiac cycle can be obtained based on the first heart sound S1 and the second heart sound S2 respectively,

The preset adjustment coefficient may be 0.7, 0.8, etc., which is not particularly limited in this embodiment. The preset adjustment coefficient for adjusting the time of the systole and the preset adjustment coefficient for adjusting the peak value (comprising the first peak value and the second peak value) can be the same or different, can be set by a user in advance respectively, and are mutually independent.

Step F30, taking the ratio of the first rapid ejection time to the second rapid ejection time corresponding to each cardiac cycle as a second ratio;

and step F40, taking the average value of all the second ratios as the fast ejection time ratio.

In this embodiment, the time ratio of the ejection time of the pulse signal to the rapid ejection time of the heart sound signal is used as the signal characteristic to predict the heart age, thereby improving the heart age prediction accuracy. As the peripheral arterial stiffness increases, the peripheral arterial waveform rise time changes, resulting in longer ejection times and faster ejection times. While peripheral arterial stiffness increases, resulting in increased vascular resistance, the heart requires a shorter ejection time to ensure that a fixed amount of blood flow can exit the heart. This tends to change the time period before the ejection of the heart, and thus the burden on the heart increases, and the heart age increases, so that the heart age can be predicted in all directions by using the ratio of the ejection times and the ratio of the rapid ejection times.

In a possible implementation manner, in a case that the signal features include a fast ejection time difference ratio, the step of extracting features from the physiological signal to obtain signal features includes:

step G10, for the same cardiac cycle of the physiological signal, acquiring the pre-ejection time based on the electrocardiosignals in the cardiac cycle and the heart sound signals in the cardiac cycle;

Step G20, taking the time difference between the first rapid ejection time and the second rapid ejection time corresponding to the cardiac cycle as the rapid ejection time difference;

Step G30, taking the ratio of the pre-ejection time to the fast ejection time difference corresponding to each cardiac cycle as a fourth ratio;

step G40, taking the average value of all the fourth ratios as a fast ejection time difference ratio.

In the embodiment, the rapid ejection time difference ratio of the pulse signal, the electrocardiosignal and the heart sound signal is used as the signal characteristic to predict the heart age, so that the heart age prediction accuracy is improved. As the peripheral arterial stiffness increases, the peripheral arterial waveform rise time changes, resulting in longer ejection times and faster ejection times. While peripheral arterial stiffness increases, resulting in increased vascular resistance, the heart requires a shorter ejection time to ensure that a fixed amount of blood flow can exit the heart. This tends to change the time period before the ejection of the heart, and thus the burden on the heart increases, and the heart age increases, so that the heart age can be predicted in all directions by using the ratio of the ejection time differences and the ratio of the rapid ejection time differences.

Example IV

An embodiment of the present invention further provides a device for predicting a heart aging degree, referring to fig. 5, the device includes:

a physiological signal acquisition module 10 for synchronously acquiring physiological signals, wherein the physiological signals comprise an electrocardiosignal, a pulse signal and a heart sound signal;

A feature extraction module 20, configured to perform feature extraction on the physiological signal to obtain a signal feature, where the signal feature includes one or more of a ejection time ratio, a fast ejection time ratio, a ejection time difference ratio, a fast ejection time difference ratio, a pulse transfer time, and a pulse arrival time;

The heart age prediction module 30 is configured to input the signal features into a pre-trained heart age prediction model, so that the heart age prediction model outputs a heart age prediction result.

The feature extraction module 20 is further configured to:

the mean of all the first ratios is taken as the ejection time ratio.

The feature extraction module 20 is further configured to:

the mean of all the second ratios is taken as the fast ejection time ratio.

The feature extraction module 20 is further configured to:

The heart aging degree prediction device provided by the invention can solve the technical problem of how to improve the accuracy of predicting the heart aging degree by adopting the heart aging degree prediction method in the first embodiment, the second embodiment or the third embodiment. Compared with the prior art, the heart aging degree prediction device provided by the embodiment of the invention has the same beneficial effects as the heart aging degree prediction method provided by the embodiment, and other technical features in the heart aging degree prediction device are the same as the features disclosed by the method of the embodiment, and are not repeated herein.

Example five

The embodiment of the invention provides electronic equipment, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the heart aging degree prediction method in the first embodiment.

Referring now to fig. 6, a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. The electronic device in the embodiments of the present disclosure may be a portable device or the like. The electronic device shown in fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 6, the electronic device may include a processing means 1001 (e.g., a central processor, a graphics processor, etc.) which may perform various appropriate actions and processes according to a program stored in a read only memory (ROM 1002) or a program loaded from a storage means into a random access memory (RAM 1004). In the RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, the ROM1002, and the RAM1004 are connected to each other by a bus 1005. An input/output (I/O) interface is also connected to bus 1005.

In general, the following systems may be connected to the I/O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, and the like; an output device 1008 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage device 1003 including, for example, a magnetic tape, a hard disk, and the like; and communication means 1009. The communication means 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While electronic devices having various systems are shown in the figures, it should be understood that not all of the illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. The above-described functions defined in the method of the embodiment of the present disclosure are performed when the computer program is executed by the processing device 1001.

The electronic equipment provided by the invention adopts the heart aging degree prediction method in the embodiment, so that the technical problem of how to improve the accuracy of heart aging degree prediction can be solved. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the invention are the same as those of the heart aging degree prediction method provided by the embodiment, and other technical features of the electronic device are the same as those disclosed by the method of the previous embodiment, so that no description is given here.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Example six

An embodiment of the present invention provides a computer-readable storage medium having computer-readable program instructions stored thereon for performing the heart aging degree prediction method in the above embodiment.

The computer readable storage medium according to the embodiments of the present invention may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this embodiment, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The above-described computer-readable storage medium may be contained in an electronic device; or may exist alone without being assembled into an electronic device.

The computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to: synchronously acquiring physiological signals, wherein the physiological signals comprise electrocardiosignals, pulse signals and heart sound signals; extracting features of the physiological signal to obtain signal features, wherein the signal features comprise one or more of a blood ejection time ratio, a rapid blood ejection time ratio, a blood ejection time difference ratio, a rapid blood ejection time difference ratio, a pulse transmission time and a pulse arrival time; and inputting the signal characteristics into a pre-trained heart age prediction model so as to output and obtain a heart age prediction result by the heart age prediction model.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented in software or hardware. Wherein the name of the module does not constitute a limitation of the unit itself in some cases.

The readable storage medium provided by the invention is a computer readable storage medium, and the computer readable storage medium stores computer readable program instructions for executing the heart aging degree prediction method, so that the technical problem of how to improve the heart aging degree prediction accuracy can be solved. Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the embodiment of the present invention are the same as those of the heart aging degree prediction method provided by the first, second or third embodiments, and are not described in detail herein.

Example seven

The embodiments of the present invention also provide a computer program product comprising a computer program which, when executed by a processor, implements the steps of the heart aging degree prediction method as described above.

The computer program product provided by the application can solve the technical problem of how to improve the prediction accuracy of the heart aging degree. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the heart aging degree prediction method provided by the first embodiment, the second embodiment or the third embodiment, and are not described in detail herein.

The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein, or any application, directly or indirectly, within the scope of the application.

Claims

1. A method for predicting the degree of heart aging, comprising:

2. The method of predicting degree of heart aging of claim 1, wherein, in the case where the signal features include a ratio of ejection times, the step of feature extracting the physiological signal to obtain signal features includes:

the mean of all the first ratios is taken as the ejection time ratio.

3. The heart aging degree prediction method according to claim 2, wherein the step of acquiring a ejection time based on the heart sound signal in the cardiac cycle comprises:

4. A method of predicting degree of heart aging as recited in claim 3, wherein the step of determining an aortic valve opening time of the first heart sound during the cardiac cycle comprises:

5. A method of predicting degree of heart aging as recited in claim 3, wherein the step of determining an aortic valve closure time of the second heart sound over the cardiac cycle comprises:

6. The method of predicting degree of heart aging as set forth in claim 2, wherein, in the case where the signal features include a difference ratio of ejection times, the step of feature-extracting the physiological signal to obtain signal features includes:

7. The method of predicting degree of heart aging of claim 1, wherein, in the case where the signal features include a fast ejection time ratio, the step of feature extracting the physiological signal results in signal features comprising:

the mean of all the second ratios is taken as the fast ejection time ratio.

8. The method of predicting degree of heart aging of claim 7, wherein, in the case where the signal features include a fast ejection time difference ratio, the step of feature extracting the physiological signal to obtain signal features includes:

9. An electronic device, the electronic device comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the heart aging level prediction method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that the readable storage medium is a computer readable storage medium having stored thereon a program for realizing the heart aging degree prediction method, the program for realizing the heart aging degree prediction method being executed by a processor to realize the steps of the heart aging degree prediction method according to any one of claims 1 to 8.