Method and device for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot

Abstract

The embodiments of the present application relate to the field of heart rate analysis, and specifically to a method and device for nonlinear analysis of heart rate variability and generation of an electrocardiogram scatter plot. A specific implementation of the method includes: obtaining an initial electrocardiogram signal within a preset time length; obtaining a sequence of heart rate positive wave intervals; splitting processing to obtain a sequence of heart rate positive wave interval groups; constructing a three-dimensional scatter plot of a heart rate positive wave; performing a first feature extraction process to obtain a first heart rate feature information sequence; performing a second feature extraction process to obtain a second heart rate feature information; performing a fusion process to obtain target heart rate feature information; performing an abnormal recognition process on the target heart rate feature information to obtain an abnormal heart rate recognition result; in response to determining that the abnormal heart rate recognition result meets a preset abnormal condition, sending the three-dimensional scatter plot of the positive heart rate wave, the target heart rate feature information and the abnormal heart rate recognition result to an alarm terminal for alarm. This implementation improves the accuracy of abnormal heart rate state recognition.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of heart rate analysis, and specifically to a method and device for nonlinear analysis of heart rate variability and generation of an electrocardiogram scatter plot. Background Art

[0002] Heart rate variability refers to the variability of heartbeat intervals regulated by the heart's autonomic nervous system. It has been widely used in clinical cardiology, neurology, and psychiatry to assess the state of cardiac autonomic nervous function. Existing heart rate variability analysis methods are mainly based on the analysis of two consecutive RR intervals (i.e., the interval between two R waves), and extract heart rhythm information through time domain, frequency domain, or nonlinear methods.

[0003] However, in practice, it is found that when the above method is used for nonlinear analysis of heart rate variability, the following technical problems often occur:

[0004] The method of extracting cardiac rhythm information only through time domain, frequency domain or nonlinear methods is often too simple. When dealing with complex physiological states (such as arrhythmia and stress state), it is difficult to fully reveal the dynamic characteristics of cardiac rhythm, resulting in reduced accuracy in identifying abnormal heart rate states. Summary of the invention

[0005] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present application propose a method for nonlinear analysis of heart rate variability and generation of an electrocardiogram scatter plot, a computer device, and a computer-readable storage medium to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present application provide a method for nonlinear analysis of heart rate variability and generation of an ECG scatter plot, the method comprising: acquiring an initial ECG signal within a preset time length; performing recognition processing on the initial ECG signal to obtain a heart rate positive wave interval sequence; performing splitting processing on the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence; constructing a three-dimensional scatter plot of the heart rate positive wave based on the heart rate positive wave interval group sequence; performing first feature extraction processing on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information , obtain a first heart rate characteristic information sequence; perform a second feature extraction process on the above-mentioned heart rate positive wave three-dimensional scatter plot to obtain second heart rate characteristic information; perform a fusion process on the above-mentioned first heart rate characteristic information sequence and the above-mentioned second heart rate characteristic information to obtain target heart rate characteristic information; perform an abnormality identification process on the above-mentioned target heart rate characteristic information to obtain a heart rate abnormality identification result; in response to determining that the above-mentioned heart rate abnormality identification result meets a preset abnormality condition, send the above-mentioned heart rate positive wave three-dimensional scatter plot, the above-mentioned target heart rate characteristic information and the above-mentioned heart rate abnormality identification result to an alarm terminal for alarm processing.

[0008] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0009] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0010] The above-mentioned embodiments of the present application have the following beneficial effects: through the nonlinear analysis of heart rate variability and the electrocardiogram generation method of some embodiments of the present application, the accuracy of abnormal heart rate state recognition can be improved. Specifically, the reason for the reduced accuracy of abnormal heart rate state recognition is that the method of extracting cardiac rhythm information only through time domain, frequency domain or nonlinear method is often too simple, and it is difficult to fully reveal the dynamic characteristics of cardiac rhythm when dealing with complex physiological states (such as arrhythmia, stress state). Based on this, the nonlinear analysis of heart rate variability and the electrocardiogram generation method of some embodiments of the present application first obtain the initial electrocardiogram signal within a preset time length. Secondly, the above-mentioned initial electrocardiogram signal is identified and processed to obtain a heart rate positive wave interval sequence. Thus, the initial signal can be processed to identify the peak in the heart rate signal, which is convenient for subsequent abnormal identification of the heart rate signal. Then, the above-mentioned heart rate positive wave interval sequence is split and processed to obtain a heart rate positive wave interval group sequence. Thus, three consecutive heart rate intervals can be used as a group for abnormal identification, further improving the accuracy of abnormal heart rate identification. Then, based on the above-mentioned heart rate positive wave interval group sequence, a three-dimensional scatter plot of the heart rate positive wave is constructed. Thus, a scatter plot can be obtained to characterize the three-dimensional feature information of the heart rate signal. Then, each heart rate positive wave interval group in the above-mentioned heart rate positive wave interval group sequence is subjected to a first feature extraction process to generate a first heart rate feature information, and a first heart rate feature information sequence is obtained. Thus, feature information generated based on heart rate interval data can be obtained. Subsequently, a second feature extraction process is performed on the above-mentioned heart rate positive wave three-dimensional scatter plot to obtain second heart rate feature information. Thus, feature information generated by a scatter plot generated based on heart rate interval information can be obtained. Then, the above-mentioned first heart rate feature information sequence and the above-mentioned second heart rate feature information are fused to obtain target heart rate feature information. Thus, fused feature information can be obtained. Then, the above-mentioned target heart rate feature information is subjected to an abnormality recognition process to obtain a heart rate abnormality recognition result. Thus, the heart rate signal can be abnormally recognized based on the fused heart rate feature information. Finally, in response to determining that the above-mentioned heart rate abnormality recognition result meets the preset abnormal condition, the above-mentioned heart rate positive wave three-dimensional scatter plot, the above-mentioned target heart rate characteristic information and the above-mentioned heart rate abnormality recognition result are sent to the alarm terminal for alarm processing. In this way, abnormal information in the heart rate signal can be found. Therefore, some of the nonlinear analysis of heart rate variability and electrocardiogram scatter plot generation methods of the present application can first perform frequency domain analysis on the heart rate signal to identify the peaks and heart rate intervals in the heart rate signal, and then take three consecutive heart rate intervals as a group to extract the data features and spatial features of the heart rate interval information for abnormal identification. Thereby, in the case of complex arrhythmia, the changes in heart rhythm can be accurately reflected, information with diagnostic value can be extracted from a large amount of heart rate interval data, and potential pathological characteristics in heart rhythm can be revealed through nonlinear analysis methods.Thereby, the accuracy of identifying abnormal heart rate states can be improved, and further, the diagnostic accuracy and early warning capability of heart disease can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0012] Figure 1 is a flow chart of some embodiments of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot according to the present application;

[0013] Figure 2 is a schematic diagram of a three-dimensional scatter plot of a heart rate positive wave according to some embodiments of the method for nonlinear analysis of heart rate variability and generation of an electrocardiogram scatter plot of the present application;

[0014] Figure 3 is a schematic diagram of the phase space trajectory information of the heart rate positive wave according to some embodiments of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot of the present application;

[0015] Figure 4 is a schematic diagram of a heart rate phase space cross section according to some embodiments of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plots of the present application;

[0016] Figure 5 It is a schematic diagram of the structure of a computer device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0017] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0023] Figure 1 The process 100 of some embodiments of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot according to the present application is shown. The method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot comprises the following steps:

[0024] Step 101, obtaining an initial ECG signal within a preset time period.

[0025] In some embodiments, the execution subject of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot can obtain the initial electrocardiogram signal within a preset time length from the storage terminal through a wired connection or a wireless connection. The above-mentioned storage terminal can be a storage terminal included in the electrocardiogram monitoring device. The above-mentioned initial electrocardiogram signal can represent the electrocardiogram of the target user within the above-mentioned preset time length. The above-mentioned target user can be a user who wants to perform nonlinear analysis of heart rate variability and generate an electrocardiogram scatter plot.

[0026] As an example, the ECG monitoring device may be an ECG monitor. The preset time period may be 24 hours.

[0027] It should be noted that the above wireless connection methods may include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0028] Step 102, identifying and processing the initial electrocardiogram signal to obtain a heart rate positive wave interval sequence.

[0029] In some embodiments, the execution subject may identify and process the initial electrocardiogram signal to obtain a sequence of positive heart rate wave intervals.

[0030] In some optional implementations of some embodiments, the execution subject identifies and processes the initial electrocardiogram signal to obtain a heart rate positive wave interval sequence, which may include the following steps:

[0031] The first step is to perform low-pass filtering on the initial ECG signal to obtain an ECG low-pass filtered signal. The initial ECG signal can be low-pass filtered using a preset low-pass filter to obtain an ECG low-pass filtered signal.

[0032] As an example, the preset low-pass filter may be a second-order Butterworth filter with a first preset cutoff frequency. The first preset cutoff frequency may be 5 Hz.

[0033] The second step is to perform high-pass filtering on the ECG low-pass filtered signal to obtain an ECG high-pass filtered signal. The ECG low-pass filtered signal can be high-pass filtered by a preset high-pass filter to obtain an ECG high-pass filtered signal.

[0034] As an example, the preset high-pass filter may be a second-order Butterworth filter with a second preset cutoff frequency. The second preset cutoff frequency may be 10 Hz.

[0035] The third step is to perform differentiation processing on the ECG high-pass filter signal to obtain an ECG differential signal. The ECG high-pass filter signal can be differentiated by a preset differential formula to obtain an ECG differential signal.

[0036] As an example, the above-mentioned preset differential formula may be a five-point differential formula.

[0037] The fourth step is to square the ECG differential signal to obtain a cardiac level square signal. The square of the ECG differential signal can be determined as the cardiac level square signal.

[0038] The fifth step is to perform sliding integration processing on the above cardiac level square signal to obtain an electrocardiogram integrated signal. The above cardiac level square signal can be processed by sliding integration using a preset integration algorithm to obtain an electrocardiogram integrated signal.

[0039] As an example, the preset integration algorithm mentioned above may be a sliding window algorithm.

[0040] Step 6: Filter the ECG integrated signal to obtain a heart rate positive wave coordinate sequence. The ECG integrated signal can be filtered by a preset filtering algorithm to obtain a heart rate positive wave coordinate sequence. The heart rate positive wave coordinate in the heart rate positive wave coordinate sequence can correspond to an R wave in the initial ECG signal.

[0041] As an example, the above-mentioned preset filtering algorithm may be a threshold method.

[0042] In the seventh step, for each heart rate positive wave coordinate in the heart rate positive wave coordinate sequence, the signal between the heart rate positive wave coordinate and the next heart rate positive wave coordinate of the heart rate positive wave coordinate in the initial electrocardiogram signal is determined as a heart rate positive wave interval. The heart rate positive wave interval can represent an RR interval (the interval between two adjacent R waves).

[0043] In the eighth step, each determined heart rate positive wave interval is determined as the above-mentioned heart rate positive wave interval sequence.

[0044] Step 103, splitting the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence.

[0045] In some embodiments, the execution subject may split the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence.

[0046] In some optional implementations of some embodiments, the execution subject splits the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence, which may include the following steps:

[0047] In the first step, for the above heart rate positive wave interval sequence, perform the following splitting steps:

[0048] In the first sub-step, the first heart rate positive wave interval in the heart rate positive wave interval sequence and two heart rate positive wave intervals after the first heart rate positive wave interval are determined as a heart rate positive wave interval group.

[0049] In the second sub-step, the first three heart rate positive wave intervals of the heart rate positive wave interval sequence are deleted from the heart rate positive wave interval sequence to obtain a deleted heart rate positive wave interval sequence.

[0050] In the second step, in response to determining that the deleted heart rate positive wave interval sequence meets the preset splitting condition, the deleted heart rate positive wave interval sequence is determined as the heart rate positive wave interval sequence to perform the above splitting step again. The above preset splitting condition can be that the number of heart rate positive wave intervals in the deleted heart rate positive wave interval sequence is greater than or equal to the preset number of intervals.

[0051] As an example, the preset number of intervals may be 3.

[0052] The third step is to determine the determined heart rate positive wave interval groups as the above-mentioned heart rate positive wave interval group sequence.

[0053] Therefore, three adjacent RR intervals can be analyzed as a group of data, which improves the dimension and accuracy of heart rate variability analysis.

[0054] Step 104: construct a three-dimensional scatter plot of the heart rate positive wave based on the above heart rate positive wave interval group sequence.

[0055] In some embodiments, the execution subject may construct a three-dimensional scatter plot of the positive heart rate wave based on the positive heart rate wave interval group sequence. The construction of the three-dimensional scatter plot of the positive heart rate wave based on the positive heart rate wave interval group sequence may be as follows: first, for each positive heart rate wave interval group in the positive heart rate wave interval group sequence, a point with the first positive heart rate wave interval in the positive heart rate wave interval group as the horizontal coordinate, the second positive heart rate wave interval in the positive heart rate wave interval group as the vertical coordinate, and the third positive heart rate wave interval in the positive heart rate wave interval group as the vertical coordinate is determined as a three-dimensional scatter plot of the positive heart rate wave. Then, the determined three-dimensional scatter plots of the positive heart rate wave are determined as the three-dimensional scatter plots of the positive heart rate wave included in the positive heart rate wave three-dimensional scatter plot.

[0056] As an example, the above three-dimensional scatter plot of the heart rate positive wave can be referred to Figure 2 A schematic diagram of a three-dimensional scatter plot of a heart rate positive wave according to some embodiments of the method for nonlinear analysis of heart rate variability and generation of an electrocardiogram scatter plot of the present application is shown.

[0057] Step 105: Perform a first feature extraction process on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information, thereby obtaining a first heart rate feature information sequence.

[0058] In some embodiments, the execution subject may perform a first feature extraction process on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information, and obtain a first heart rate feature information sequence.

[0059] In some optional implementations of some embodiments, the execution subject performs a first feature extraction process on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information, which may include the following steps:

[0060] In the first step, the duration value corresponding to each heart rate positive wave interval in the above heart rate positive wave interval group is determined as the heart rate positive wave interval value, and a heart rate positive wave interval value group is obtained. Among them, the duration value corresponding to the above heart rate positive wave interval can be the duration value of the RR interval represented by the above heart rate positive wave interval.

[0061] In the second step, the average of each heart rate positive wave interval value in the above heart rate positive wave interval value group is determined as the heart rate interval mean.

[0062] In the third step, the standard deviation of each heart rate positive wave interval value in the above heart rate positive wave interval value group is determined as the heart rate interval standard deviation value.

[0063] The fourth step is to determine the difference rate value corresponding to the above-mentioned heart rate positive wave interval value group as the heart rate interval difference rate value. Among them, the difference rate value corresponding to the above-mentioned heart rate positive wave interval value group can be generated by the following steps: first, the difference between every two heart rate positive wave interval values ​​in the above-mentioned heart rate positive wave interval value group is determined as the heart rate positive wave interval difference value, and a heart rate positive wave interval difference value set is obtained. Then, the ratio of the number of heart rate positive wave interval difference values ​​in the above-mentioned heart rate positive wave interval difference value set that is greater than the preset difference value to the number of heart rate positive wave interval difference values ​​in the above-mentioned heart rate positive wave interval difference value set is determined as the difference rate value corresponding to the above-mentioned heart rate positive wave interval value group.

[0064] As an example, the preset difference may be 50 milliseconds.

[0065] The fifth step is to fuse the heart rate interval mean, the heart rate interval standard deviation, and the heart rate interval difference rate value to obtain the first heart rate characteristic information. The heart rate interval mean, the heart rate interval standard deviation, and the heart rate interval difference rate value can be determined as the heart rate interval mean, the heart rate interval standard deviation, and the heart rate interval difference rate value included in the first heart rate characteristic information.

[0066] Step 106, performing a second feature extraction process on the three-dimensional scatter plot of the heart rate positive wave to obtain second heart rate feature information.

[0067] In some embodiments, the execution subject may perform a second feature extraction process on the three-dimensional scatter plot of the positive heart rate wave to obtain second heart rate feature information.

[0068] In some optional implementations of some embodiments, the execution subject performs second feature extraction processing on the three-dimensional scatter plot of the heart rate positive wave to obtain second heart rate feature information, which may include the following steps:

[0069] The first step is to generate the phase space trajectory information of the heart rate positive wave based on the above three-dimensional scatter plot of the heart rate positive wave.

[0070] The second step is to determine the heart rate phase space characteristic index value, heart rate phase space fractal dimension value, and heart rate phase space section crossing coordinate value corresponding to the above-mentioned heart rate positive wave phase space trajectory information. Among them, the heart rate phase space characteristic index value corresponding to the above-mentioned heart rate positive wave phase space trajectory information can be determined by a preset characteristic index formula. The heart rate phase space fractal dimension value corresponding to the above-mentioned heart rate positive wave phase space trajectory information is determined by a preset fractal dimension algorithm. The heart rate phase space section crossing coordinate value corresponding to the above-mentioned heart rate positive wave phase space trajectory information is determined by a preset section formula.

[0071] As an example, the above-mentioned preset characteristic index formula may be a Lyapunov index formula. The above-mentioned preset fractal dimension algorithm may be but is not limited to at least one of the following: a Box-Counting algorithm, a Variation algorithm, or a PSD (Power Spectral Density) algorithm. The above-mentioned preset cross-section formula may be a Poincaré cross-section formula. The cross-section corresponding to the coordinate value of the above-mentioned heart rate phase space cross-section may refer to Figure 4 A schematic diagram of a heart rate phase space cross section is shown according to some embodiments of the method for nonlinear analysis of heart rate variability and generation of electrocardiogram scattergrams of the present application.

[0072] The third step is to integrate the above-mentioned heart rate phase space characteristic index value, the above-mentioned heart rate phase space fractal dimension value and the above-mentioned heart rate phase space section crossing coordinate value to obtain the target heart rate phase space characteristic value.

[0073] The fourth step is to fuse the above-mentioned heart rate phase space characteristic index value, the above-mentioned heart rate phase space fractal dimension value, the above-mentioned heart rate phase space section crossing coordinate value and the above-mentioned target heart rate phase space characteristic value to obtain the second heart rate characteristic information. Among them, the above-mentioned heart rate phase space characteristic index value, the above-mentioned heart rate phase space fractal dimension value, the above-mentioned heart rate phase space section crossing coordinate value and the above-mentioned target heart rate phase space characteristic value can be determined as the heart rate phase space characteristic index value, the heart rate phase space fractal dimension value, the heart rate phase space section crossing coordinate value and the target heart rate phase space characteristic value included in the above-mentioned second heart rate characteristic information.

[0074] In some optional implementations of some embodiments, the execution subject generates the phase space trajectory information of the heart rate positive wave based on the three-dimensional scatter diagram of the heart rate positive wave, which may include the following steps:

[0075] The first step is to determine the delay time value corresponding to the three-dimensional scatter diagram of the positive heart rate wave. The delay time value corresponding to the three-dimensional scatter diagram of the positive heart rate wave can be determined by a preset time determination algorithm.

[0076] As an example, the above-mentioned preset duration determination algorithm may be but is not limited to at least one of the following: an autocorrelation function or a mutual information algorithm.

[0077] The second step is to determine the embedding dimension value corresponding to the three-dimensional scatter plot of the positive heart rate wave. The embedding dimension value corresponding to the three-dimensional scatter plot of the positive heart rate wave can be determined by a preset dimension determination algorithm.

[0078] As an example, the above-mentioned preset dimension determination algorithm may be but is not limited to at least one of the following: a FNN (False Nearest Neighbors) algorithm or a time delay embedding algorithm.

[0079] The third step is to generate the phase space trajectory information of the positive wave of heart rate corresponding to the three-dimensional scatter plot of the positive wave of heart rate based on the delay time value and the embedding dimension value. The delay time value can be used as the delay time of the phase space vector, and the embedding dimension value can be used as the dimension value of the phase space vector to construct the phase space vector. Then, the generated phase space vector is determined as the phase space trajectory information of the positive wave of heart rate.

[0080] As an example, the above phase space trajectory information can be referred to Figure 3 A schematic diagram of the heart rate positive wave phase space trajectory information according to some embodiments of the heart rate variability nonlinear analysis and electrocardiogram scatter plot generation method of the present application is shown.

[0081] In some optional implementations of some embodiments, the execution subject integrates the heart rate phase space characteristic index value, the heart rate phase space fractal dimension value and the heart rate phase space section crossing coordinate value to obtain the target heart rate phase space characteristic value, which may include the following steps:

[0082] The first step is to standardize the characteristic index value of the heart rate phase space, the fractal dimension value of the heart rate phase space, and the cross-section crossing coordinate value of the heart rate phase space, respectively, to obtain the characteristic index standard value, the fractal dimension standard value, and the cross-section crossing coordinate standard value. Among them, the characteristic index value of the heart rate phase space, the fractal dimension value of the heart rate phase space, and the cross-section crossing coordinate value of the heart rate phase space can be standardized by a preset standardization algorithm, to obtain the characteristic index standard value, the fractal dimension standard value, and the cross-section crossing coordinate standard value.

[0083] As an example, the above-mentioned preset normalization algorithm may include but is not limited to at least one of the following: min-max algorithm, z-score algorithm, proportion method and two-dimensional one-dimensional projection algorithm (adding the horizontal coordinate and the vertical coordinate in the coordinate, and then normalizing to obtain the standard value of the coordinate).

[0084] The second step is to perform weighted summation processing on the above characteristic index standard value, the above fractal dimension standard value and the above cross-section crossing coordinate standard value based on the preset weight value set to obtain the heart rate phase space characteristic value. Among them, the weight values ​​in the above weight value set correspond to the above characteristic index standard value, the above fractal dimension standard value and the above cross-section crossing coordinate standard value respectively. The above preset weight value set is generated by a preset weight generation algorithm.

[0085] As an example, the above-mentioned preset weight generation algorithm can be but is not limited to at least one of the following: a random number generation algorithm, a regression analysis algorithm or a machine learning algorithm.

[0086] The third step is to determine the above heart rate phase space eigenvalue as the above target heart rate phase space eigenvalue.

[0087] Therefore, the heart rate information of the target user can be analyzed nonlinearly by generating phase space trajectory information and then analyzing and extracting features from the phase space trajectory information. Compared with the existing method of analyzing based on two consecutive RR intervals, the present application can perform nonlinear analysis in three-dimensional space through three consecutive RR intervals, thereby improving the data dimension. Thus, the accuracy of heart rate variability analysis can be improved, and further, the accuracy of identifying abnormal heart rate states can be improved.

[0088] Step 107: fusing the first heart rate characteristic information sequence and the second heart rate characteristic information to obtain target heart rate characteristic information.

[0089] In some embodiments, the execution subject may fuse the first heart rate characteristic information sequence and the second heart rate characteristic information to obtain the target heart rate characteristic information. The fusion processing of the first heart rate characteristic information sequence and the second heart rate characteristic information to obtain the target heart rate characteristic information may be: determining the first heart rate characteristic information sequence and the second heart rate characteristic information as the first heart rate characteristic information sequence and the second heart rate characteristic information included in the target heart rate characteristic information.

[0090] Step 108, performing abnormality recognition processing on the target heart rate characteristic information to obtain a heart rate abnormality recognition result.

[0091] In some embodiments, the execution subject may perform abnormality recognition processing on the target heart rate characteristic information to obtain a heart rate abnormality recognition result, wherein the heart rate abnormality recognition result may be information indicating that "the heart rate is abnormal" or information indicating that "the heart rate is not abnormal".

[0092] In some optional implementations of some embodiments, the execution subject performs abnormality recognition processing on the target heart rate characteristic information to obtain a heart rate abnormality recognition result, which may include the following steps:

[0093] The first step is to generate a heart rate characteristic abnormality identification value based on the first heart rate characteristic information sequence included in the above target heart rate characteristic information. The above method of generating a heart rate characteristic abnormality identification value based on the first heart rate characteristic information sequence included in the above target heart rate characteristic information may include the following sub-steps:

[0094] In the first sub-step, for each first heart rate characteristic information in the first heart rate characteristic information sequence, the following determination steps are performed:

[0095] The first determination step is to determine the first preset value as the interval abnormality identification value in response to determining that the heart rate interval mean value included in the first heart rate characteristic information is less than the preset interval mean value.

[0096] As an example, the preset interval average value may be 40 milliseconds. The first preset value may be 1.

[0097] The second determination step is to determine the first preset value as the standard deviation abnormal identification value in response to determining that the heart rate interval standard deviation value included in the first heart rate characteristic information is less than the preset interval standard deviation value.

[0098] As an example, the preset interval standard deviation value may be 50 milliseconds.

[0099] The third determination step is to determine the first preset value as the interval difference rate abnormality identification value in response to determining that the heart rate interval difference rate value included in the first heart rate characteristic information is less than the preset interval difference rate value.

[0100] As an example, the preset interval difference rate value may be 0.75%.

[0101] In the fourth determination step, the sum of the above-mentioned interval abnormality identification value, the above-mentioned standard difference normal identification value, and the above-mentioned interval difference rate abnormality identification value is standardized to obtain the first heart rate characteristic abnormality identification value. Among them, the above-mentioned preset standardization algorithm can be used. The sum of the above-mentioned interval abnormality identification value, the above-mentioned standard difference normal identification value, and the above-mentioned interval difference rate abnormality identification value is standardized to obtain the first heart rate characteristic abnormality identification value.

[0102] The second sub-step is to perform a normalization process on the sum of the generated first heart rate characteristic abnormality identification values ​​to obtain the above-mentioned heart rate characteristic abnormality identification value. The sum of the generated first heart rate characteristic abnormality identification values ​​can be normalized by the above-mentioned preset normalization algorithm to obtain the above-mentioned heart rate characteristic abnormality identification value.

[0103] Optionally, in response to determining that the heart rate interval mean included in the above-mentioned first heart rate characteristic information is greater than or equal to the above-mentioned preset interval mean, the second preset value is determined as the interval abnormality identification value.

[0104] As an example, the second preset value may be 0.5.

[0105] Optionally, in response to determining that the heart rate interval standard deviation value included in the above-mentioned first heart rate characteristic information is greater than or equal to a preset interval standard deviation value, the second preset value is determined as the standard deviation abnormal identification value.

[0106] Optionally, in response to determining that the heart rate interval difference rate value included in the above-mentioned first heart rate characteristic information is greater than or equal to a preset interval difference rate value, the second preset value is determined as the interval difference rate abnormality identification value.

[0107] The second step is to generate a characteristic index abnormality identification value based on the heart rate phase space characteristic index value included in the above target heart rate characteristic information. The above generation of the characteristic index abnormality identification value based on the heart rate phase space characteristic index value included in the above target heart rate characteristic information may be: in response to determining that the heart rate phase space characteristic index value included in the above target heart rate characteristic information is less than the preset phase space characteristic index value, a first preset value is determined as the characteristic index abnormality identification value. In response to determining that the heart rate phase space characteristic index value included in the above target heart rate characteristic information is greater than or equal to the preset phase space characteristic index value, a second preset value is determined as the characteristic index abnormality identification value.

[0108] As an example, the preset phase space characteristic index value may be 0.

[0109] The third step is to generate a dimension abnormality identification value based on the fractal dimension value of the heart rate phase space included in the target heart rate characteristic information. The step of generating a dimension abnormality identification value based on the fractal dimension value of the heart rate phase space included in the target heart rate characteristic information may be: in response to determining that the fractal dimension value of the heart rate phase space included in the target heart rate characteristic information is greater than a preset fractal dimension value, a first preset value is determined as the dimension abnormality identification value. In response to determining that the fractal dimension value of the heart rate phase space included in the target heart rate characteristic information is less than or equal to the preset fractal dimension value, a second preset value is determined as the dimension abnormality identification value.

[0110] As an example, the preset fractal dimension value may be 3.

[0111] The fourth step is to generate a phase space abnormality identification value based on the target heart rate phase space characteristic value included in the target heart rate characteristic information. The above-mentioned generation of the phase space abnormality identification value based on the target heart rate phase space characteristic value included in the target heart rate characteristic information may be: in response to determining that the target heart rate phase space characteristic value included in the target heart rate characteristic information is greater than the preset phase space characteristic value, the first preset value is determined as the phase space abnormality identification value. In response to determining that the target heart rate phase space characteristic value included in the target heart rate characteristic information is less than or equal to the preset phase space characteristic value, the second preset value is determined as the phase space abnormality identification value.

[0112] As an example, the preset phase space eigenvalue may be 0.8.

[0113] The fifth step is to perform weighted summation processing on the above-mentioned heart rate characteristic abnormal identification value, the above-mentioned characteristic index abnormal identification value, the above-mentioned dimension abnormal identification value and the above-mentioned phase space abnormal identification value to obtain a target heart rate abnormal identification value. Among them, based on a preset abnormal weight value set, the above-mentioned heart rate characteristic abnormal identification value, the above-mentioned characteristic index abnormal identification value, the above-mentioned dimension abnormal identification value and the above-mentioned phase space abnormal identification value can be weighted summation processing to obtain a target heart rate abnormal identification value. The abnormal weight values ​​in the above-mentioned abnormal weight value set correspond one to one with the above-mentioned heart rate characteristic abnormal identification value, the above-mentioned characteristic index abnormal identification value, the above-mentioned dimension abnormal identification value and the above-mentioned phase space abnormal identification value. Specifically, the above-mentioned preset abnormal weight value set can be generated by the above-mentioned preset weight generation algorithm.

[0114] Step 6: In response to determining that the target heart rate abnormality recognition value satisfies a preset abnormality recognition condition, the first preset recognition information is determined as a heart rate abnormality recognition result. The preset abnormality recognition condition may be that the target heart rate abnormality recognition value is greater than a preset abnormality value. The first preset recognition information may be information indicating that "heart rate is abnormal".

[0115] As an example, the preset abnormal value may be 0.8.

[0116] Optionally, in response to determining that the target heart rate abnormality identification value does not meet the preset abnormality identification condition, the execution subject may determine the second preset identification information as the heart rate abnormality identification result. The second preset identification information may be information indicating that "the heart rate is not abnormal".

[0117] Step 109, in response to determining that the heart rate abnormality recognition result meets the preset abnormality condition, the heart rate positive wave three-dimensional scatter plot, the target heart rate characteristic information and the heart rate abnormality recognition result are sent to the alarm terminal for alarm processing.

[0118] In some embodiments, the execution subject may, in response to determining that the abnormal heart rate recognition result satisfies a preset abnormal condition, send the three-dimensional scatter plot of the positive heart rate wave, the target heart rate characteristic information, and the abnormal heart rate recognition result to an alarm terminal for alarm processing. Among them, the preset abnormal condition may be: the abnormal heart rate recognition result is information characterizing "abnormal heart rate". Here, the alarm terminal may be: a terminal for displaying warning text or emitting a prompt sound in response to receiving the three-dimensional scatter plot of the positive heart rate wave, the target heart rate characteristic information, and the abnormal heart rate recognition result.

[0119] The above-mentioned embodiments of the present application have the following beneficial effects: through the nonlinear analysis of heart rate variability and the electrocardiogram generation method of some embodiments of the present application, the accuracy of abnormal heart rate state recognition can be improved. Specifically, the reason for the reduced accuracy of abnormal heart rate state recognition is that the method of extracting cardiac rhythm information only through time domain, frequency domain or nonlinear method is often too simple, and it is difficult to fully reveal the dynamic characteristics of cardiac rhythm when dealing with complex physiological states (such as arrhythmia, stress state). Based on this, the nonlinear analysis of heart rate variability and the electrocardiogram generation method of some embodiments of the present application first obtain the initial electrocardiogram signal within a preset time length. Secondly, the above-mentioned initial electrocardiogram signal is identified and processed to obtain a heart rate positive wave interval sequence. Thus, the initial signal can be processed to identify the peak in the heart rate signal, which is convenient for subsequent abnormal identification of the heart rate signal. Then, the above-mentioned heart rate positive wave interval sequence is split and processed to obtain a heart rate positive wave interval group sequence. Thus, three consecutive heart rate intervals can be used as a group for abnormal identification, further improving the accuracy of abnormal heart rate identification. Then, based on the above-mentioned heart rate positive wave interval group sequence, a three-dimensional scatter plot of the heart rate positive wave is constructed. Thus, a scatter plot can be obtained to characterize the three-dimensional feature information of the heart rate signal. Then, each heart rate positive wave interval group in the above-mentioned heart rate positive wave interval group sequence is subjected to a first feature extraction process to generate a first heart rate feature information, and a first heart rate feature information sequence is obtained. Thus, feature information generated based on heart rate interval data can be obtained. Subsequently, a second feature extraction process is performed on the above-mentioned heart rate positive wave three-dimensional scatter plot to obtain second heart rate feature information. Thus, feature information generated by a scatter plot generated based on heart rate interval information can be obtained. Then, the above-mentioned first heart rate feature information sequence and the above-mentioned second heart rate feature information are fused to obtain target heart rate feature information. Thus, fused feature information can be obtained. Then, the above-mentioned target heart rate feature information is subjected to an abnormality recognition process to obtain a heart rate abnormality recognition result. Thus, the heart rate signal can be abnormally recognized based on the fused heart rate feature information. Finally, in response to determining that the above-mentioned heart rate abnormality recognition result meets the preset abnormal condition, the above-mentioned heart rate positive wave three-dimensional scatter plot, the above-mentioned target heart rate characteristic information and the above-mentioned heart rate abnormality recognition result are sent to the alarm terminal for alarm processing. In this way, abnormal information in the heart rate signal can be found. Therefore, some of the nonlinear analysis of heart rate variability and electrocardiogram scatter plot generation methods of the present application can first perform frequency domain analysis on the heart rate signal to identify the peaks and heart rate intervals in the heart rate signal, and then take three consecutive heart rate intervals as a group to extract the data features and spatial features of the heart rate interval information for abnormal identification. Thereby, in the case of complex arrhythmia, the changes in heart rhythm can be accurately reflected, information with diagnostic value can be extracted from a large amount of heart rate interval data, and potential pathological characteristics in heart rhythm can be revealed through nonlinear analysis methods.Thereby, the accuracy of identifying abnormal heart rate states can be improved, and further, the diagnostic accuracy and early warning capability of heart disease can be improved.

[0120] The present application also provides a computer device 500. Figure 5 As shown, the computer device 500 includes: a bus 501, a processor 502, a memory 503 and a communication interface 504. The processor 502, the memory 503 and the communication interface 504 communicate with each other through the bus 501. The computer device 500 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 500.

[0121] The bus 501 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus 501 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 501 may include a path for transmitting information between various components of the computer device 500 (for example, the memory 503, the processor 502, and the communication interface 504).

[0122] The processor 502 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0123] The memory 503 may include a volatile memory, such as a random access memory (RAM). The memory 503 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0124] The memory 503 stores executable program codes, and the processor 502 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby implementing the aforementioned heart rate variability nonlinear analysis and electrocardiogram scatter plot generation method. That is, the memory 503 stores instructions for executing the aforementioned heart rate variability nonlinear analysis and electrocardiogram scatter plot generation method.

[0125] The communication interface 504 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 500 and other devices or a communication network.

[0126] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned heart rate variability nonlinear analysis and electrocardiogram scatter plot generation method.

[0127] The embodiment of the present application also provides a computer-readable storage medium. The above-mentioned computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The above-mentioned available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk). The computer-readable storage medium includes instructions, and the above-mentioned instructions instruct the computing device to execute the above-mentioned heart rate variability nonlinear analysis and electrocardiogram scatter plot generation method.

[0128] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot, comprising: Obtaining an initial ECG signal within a preset time period; Identify and process the initial electrocardiogram signal to obtain a heart rate positive wave interval sequence; Splitting the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence; Based on the heart rate positive wave interval group sequence, constructing a three-dimensional scatter plot of the heart rate positive wave; Performing a first feature extraction process on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information, thereby obtaining a first heart rate feature information sequence; Performing a second feature extraction process on the three-dimensional scatter plot of the heart rate positive wave to obtain second heart rate feature information; The first heart rate characteristic information sequence and the second heart rate characteristic information are fused to obtain target heart rate characteristic information, wherein the target heart rate characteristic information includes: the first heart rate characteristic information sequence, the heart rate phase space characteristic index value, the heart rate phase space fractal dimension value, the heart rate phase space section crossing coordinate value and the target heart rate phase space characteristic value; Performing abnormality recognition processing on the target heart rate characteristic information to obtain a heart rate abnormality recognition result; In response to determining that the heart rate abnormality recognition result meets a preset abnormality condition, sending the heart rate positive wave three-dimensional scatter plot, the target heart rate characteristic information and the heart rate abnormality recognition result to an alarm terminal for alarm processing; The step of identifying and processing the initial electrocardiogram signal to obtain a heart rate positive wave interval sequence includes: Performing low-pass filtering on the initial ECG signal to obtain an ECG low-pass filtered signal; Performing high-pass filtering on the ECG low-pass filtered signal to obtain an ECG high-pass filtered signal; Performing differentiation processing on the ECG high-pass filter signal to obtain an ECG differential signal; Squaring the electrocardiogram differential signal to obtain an electrocardiogram square signal; Performing sliding integration processing on the electrocardiogram signal to obtain an electrocardiogram integration signal; Filtering the electrocardiogram integrated signal to obtain a heart rate positive wave coordinate sequence; For each heart rate positive wave coordinate in the heart rate positive wave coordinate sequence, a signal in the initial electrocardiogram signal between the heart rate positive wave coordinate and the next heart rate positive wave coordinate of the heart rate positive wave coordinate is determined as a heart rate positive wave interval; Determining each determined heart rate positive wave interval as the heart rate positive wave interval sequence; The step of performing abnormality recognition processing on the target heart rate characteristic information to obtain a heart rate abnormality recognition result includes: generating a heart rate characteristic abnormality identification value based on a first heart rate characteristic information sequence included in the target heart rate characteristic information; generating a characteristic index abnormality identification value based on the heart rate phase space characteristic index value included in the target heart rate characteristic information; generating a dimension abnormality identification value based on the heart rate phase space fractal dimension value included in the target heart rate characteristic information; generating a phase space abnormality identification value based on the target heart rate phase space characteristic value included in the target heart rate characteristic information; Performing weighted sum processing on the heart rate characteristic abnormality identification value, the characteristic index abnormality identification value, the dimension abnormality identification value and the phase space abnormality identification value to obtain a target heart rate abnormality identification value; In response to determining that the target heart rate abnormality identification value satisfies a preset abnormality identification condition, the first preset identification information is determined as a heart rate abnormality identification result.

2. The method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot according to claim 1, wherein: The step of splitting the heart rate positive wave interval sequence to obtain a heart rate positive wave interval group sequence includes: For the heart rate positive wave interval sequence, the following splitting steps are performed: determining the first heart rate positive wave interval in the heart rate positive wave interval sequence and two heart rate positive wave intervals after the first heart rate positive wave interval as a heart rate positive wave interval group; The first three heart rate positive wave intervals of the heart rate positive wave interval sequence are deleted from the heart rate positive wave interval sequence to obtain a deleted heart rate positive wave interval sequence; In response to determining that the deleted heart rate positive wave interval sequence meets the preset splitting condition, determining the deleted heart rate positive wave interval sequence as the heart rate positive wave interval sequence, so as to perform the splitting step again; The determined respective heart rate positive wave interval groups are determined as the heart rate positive wave interval group sequence.

3. The method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot according to claim 1, wherein: The performing a first feature extraction process on each heart rate positive wave interval group in the heart rate positive wave interval group sequence to generate first heart rate feature information comprises: Determining the duration value corresponding to each heart rate positive wave interval in the heart rate positive wave interval group as the heart rate positive wave interval value, to obtain a heart rate positive wave interval value group; Determine the mean of each heart rate positive wave interval value in the heart rate positive wave interval value group as the heart rate interval mean; Determine the standard deviation of each heart rate positive wave interval value in the heart rate positive wave interval value group as the heart rate interval standard deviation value; Determine the difference rate value corresponding to the heart rate positive wave interval value group as the heart rate interval difference rate value; The heart rate interval mean, the heart rate interval standard deviation, and the heart rate interval difference rate are fused to obtain first heart rate characteristic information.

4. The method for nonlinear analysis of heart rate variability and generation of electrocardiogram scatter plot according to claim 1, wherein: The method further comprises: In response to determining that the target heart rate abnormality identification value does not satisfy the preset abnormality identification condition, second preset identification information is determined as the heart rate abnormality identification result.

5. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images