Psychological stress assessment method and system based on heart and brain coupling analysis

Through heart-to-brain coupling analysis, multivariate transfer entropy is used to evaluate the information transmission between heart-to-brain signals, which solves the shortcomings of the evaluation of complex interactions between central brain signals in the existing technology, and improves the comprehensiveness and accuracy of psychological stress assessment.

CN119033376APending Publication Date: 2024-11-29SHANDONG UNIV
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411122784.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The prior art is difficult to comprehensively and accurately evaluate psychological stress, especially the complex interaction between heart and brain signals under stressful states, resulting in the comprehensiveness and accuracy of the assessment need to be improved.

Method used

Using a method based on heart-to-brain coupling analysis, by obtaining ECG signals and dual-channel ECG signals, constructing inter-ECG sequences and multi-domain and multi-band feature sequences, calculating multivariable transfer entropy, and exploring the changes in heart-to-brain information transmission In the case, use support vector machine to evaluate psychological stress.

Benefits of technology

It improves the comprehensiveness and accuracy of psychological stress assessment, quantifies the interaction between the central nervous system and the autonomic nerve, and better describes the coupling paths within the heart-brain network through visual analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119033376A_ABST
    Figure CN119033376A_ABST
Patent Text Reader

Abstract

The invention discloses a psychological stress assessment method and system based on heart and brain coupling analysis, and belongs to the technical field of signal analysis. Comprising the following steps: acquiring a to-be-evaluated electrocardiosignal and a dual-channel electroencephalogram signal; interval sequence extraction is carried out on the electrocardiosignals, and an electrocardio interval sequence is constructed; carrying out interception and feature extraction on the dual-channel electroencephalogram signal according to the length of the electrocardio interval, and constructing an electroencephalogram multi-domain multi-band feature sequence; multivariable transfer entropy between the electrocardio interval sequence and the electroencephalogram multi-domain multi-band characteristic sequence is calculated, and an entropy value characteristic sequence is constructed; and processing the entropy feature sequence through a trained psychological stress classification model to generate and output a psychological stress assessment result. According to the method, multi-domain information in the cardiac and electroencephalogram signals is fully mined, psychological stress assessment is carried out according to the change condition of pressure on information transmission between the brain and the heart, and the problems that in the prior art, psychological stress assessment is not comprehensive, and the accuracy needs to be improved are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of signal analysis, and in particular to a psychological stress assessment method and system based on heart-brain coupling analysis. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] Stress reactions usually occur through the mediation pathways of the nervous system, endocrine system, and immune system. That is to say, the psychological basis of stress is a complex and interactive whole. It is impossible to obtain more comprehensive information by simply relying on a single modal psychological signal or the simple superposition of multimodal psychological signals. Therefore, it is necessary to analyze the interactions between psychological subsystems, which may provide useful information for stress assessment, health monitoring, and stress-related system dysfunction.

[0004] Many studies have evaluated the functional link between stress and sympathetic nervous system activity through related indicators of heart rate variability. In addition, EEG-based studies have also captured potential stress mechanisms. In fact, there is a bidirectional and dynamic relationship between the brain and the heart. Clinically, cerebrovascular accidents and transient ischemic attacks are often caused by arrhythmias, and atrial fibrillation is also associated with an increased risk of cognitive impairment and dementia. In addition, brain diseases including stroke and epilepsy are believed to be secondary to environmental stress (such as panic disorder and emotional distress) and may lead to cardiovascular disease. Therefore, there is an urgent need for a method that can comprehensively consider and quantitatively analyze the correlation between heart and brain signals, making it an effective indicator for monitoring abnormalities.

[0005] Recent developments in nonlinear dynamics, information theory, and network theory have provided opportunities to better understand how different integrated psychological systems and their complex structures and regulatory mechanisms describe overall behavior and different psychological functions at the organismal level. Transfer entropy is a model-free nonlinear method that has been shown to be effective in detecting the strength and direction of information transfer between joint processes. However, using classical transfer entropy to perform paired analysis of information transfer in systems with multiple interactions can lead to problems such as cascading effects and common driving effects. Summary of the invention

[0006] In order to address the deficiencies of the prior art, the present invention provides a psychological stress assessment method, system, electronic device, computer-readable storage medium and computer program product based on heart-brain coupling analysis, which fully consider the integrity of the human body in the central-autonomic neural network under stress, explore the information contained in heart-brain signals, and explore the changes in information transmission between the brain and the heart caused by stress through the causal nonlinear multivariable coupling method of multivariate transfer entropy, which is used to assess psychological stress, thereby improving the comprehensiveness and accuracy of the assessment.

[0007] In a first aspect, the present invention provides a method for assessing psychological stress based on heart-brain coupling analysis;

[0008] A psychological stress assessment method based on heart-brain coupling analysis, comprising:

[0009] Obtain the ECG signal and dual-channel EEG signal to be evaluated;

[0010] Extract the interval sequence of ECG signal and construct the ECG interval sequence; based on the ECG interval, intercept and extract the features of dual-channel EEG signal and construct the EEG multi-domain and multi-band feature sequence;

[0011] Calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence, and construct the entropy value feature sequence;

[0012] The entropy value feature sequence is processed by a trained psychological stress classification model to generate and output a psychological stress assessment result.

[0013] In some embodiments, the method further includes: drawing an information matrix in the form of a heat map based on the entropy value feature sequence.

[0014] In some embodiments, the extracting of interval sequences from ECG signals and constructing ECG interval sequences specifically include: locating the peak point of the R wave in the ECG signal, extracting the R wave position, and constructing the RR interval sequence.

[0015] In some embodiments, the intercepting of the dual-channel EEG signal based on the ECG interval is specifically: based on the ECG interval, the dual-channel EEG signal is intercepted and segmented in combination with the time synchronization information between the ECG signal and the dual-channel EEG signal.

[0016] In some embodiments, extracting features from dual-channel EEG signals and constructing EEG multi-domain and multi-band feature sequences specifically include:

[0017] Calculate the power spectrum density sequence based on the dual-channel EEG signal segmented by the ECG interval;

[0018] Integrate the δ, θ, α, β, and γ frequency bands of the power spectral density sequence to construct a power sequence;

[0019] Extract EEG frequency domain information from the power spectrum density sequence to obtain the mean, median, maximum, minimum and standard deviation of the power spectrum density;

[0020] The dual-channel EEG signals are processed using a bandpass filter to obtain sub-band signals; the sub-band signals are segmented according to the length of the ECG interval and the EEG nonlinear information is extracted to obtain energy and Shannon entropy.

[0021] In some embodiments, the method of calculating the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence and constructing the entropy value feature sequence is specifically as follows: combining the ECG interval sequence and the EEG multi-domain and multi-band feature sequence into a time series, selecting a source node and a target node in the time series nodes, and calculating the information transfer from the source node to the target node.

[0022] In some embodiments, training the psychological stress classification model specifically includes:

[0023] Obtain ECG signals and dual-channel EEG signals in resting and stress states, and construct entropy feature sequences;

[0024] The recursive feature elimination method based on support vector machine is used to select features of entropy feature sequence, and the support vector machine is trained using the selected feature set.

[0025] In a second aspect, the present invention provides a psychological stress assessment system based on heart-brain coupling analysis;

[0026] A psychological stress assessment system based on heart-brain coupling analysis, comprising:

[0027] An acquisition module is configured to: acquire an electrocardiogram signal and a dual-channel electroencephalogram signal to be evaluated;

[0028] The sequence construction module is configured to: extract the interval sequence of the ECG signal to construct the ECG interval sequence; based on the ECG interval, intercept and extract the features of the dual-channel EEG signal to construct the EEG multi-domain and multi-band feature sequence;

[0029] The entropy value construction module is configured to: calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence, and construct an entropy value feature sequence;

[0030] The psychological stress assessment module is configured to: process the entropy value feature sequence through a trained psychological stress classification model to generate and output a psychological stress assessment result.

[0031] In a third aspect, the present invention provides an electronic device;

[0032] An electronic device comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned psychological stress assessment method based on heart-brain coupling analysis.

[0033] In a fourth aspect, the present invention provides a computer-readable storage medium;

[0034] A computer-readable storage medium stores a computer program / instruction, which, when executed by a processor, implements the steps of the psychological stress assessment method based on heart-brain coupling analysis as claimed in the claim.

[0035] In a fifth aspect, the present invention provides a computer program product;

[0036] A computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned psychological stress assessment method based on heart-brain coupling analysis.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The technical solution provided by the present invention fully considers the changes in ECG and EEG signals caused by changes in psychological stress, and performs psychological stress assessment based on the coupled analysis of ECG and EEG signals, thus overcoming the limitations of single signal analysis.

[0039] 2. The technical solution provided by the present invention divides EEG signals according to ECG intervals, ensuring the synchronization of the heart-brain network; constructs ECG intervals and EEG multi-domain and multi-band sequences, fully tapping the time domain, frequency domain, and nonlinear information contained in ECG and EEG signals, ensuring the comprehensiveness of psychological information extracted from the signals. Multivariate transfer entropy is used to analyze the directionality of information flow within the heart-brain network, and by recursively calculating conditional entropy, all source nodes that have transmitted valid information to the target node are found, and the interaction between the central nervous system and the autonomic nervous system under psychological stress is quantified, thereby improving the accuracy of psychological stress assessment.

[0040] 3. The technical solution provided by the present invention better describes the coupling path within the heart-brain network through visual analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0042] Figure 1 A schematic diagram of a process flow of a psychological stress assessment method based on heart-brain coupling analysis provided by an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of a flow chart of multivariate transfer entropy calculation provided by an embodiment of the present invention;

[0044] Figure 3 A system for evaluating psychological stress based on heart-brain coupling analysis provided by an embodiment of the present invention. Schematic diagram of the system architecture. DETAILED DESCRIPTION

[0045] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0046] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0048] Terminology explanation:

[0049] Multivariate transfer entropy: It is a causal nonlinear multivariate coupling method used to describe the nonlinear information transfer between multivariate time series, extending the transfer entropy measure originally proposed for paired systems to multiple interaction processes. Its purpose is to find all source nodes that transfer valid information to the target node by recursively calculating the conditional entropy.

[0050] Embodiment 1

[0051] Existing psychological stress assessment only considers single-modal psychological signals or the simple superposition of multi-modal psychological signals, and does not analyze the interactions between psychological subsystems, resulting in the need to improve the comprehensiveness and accuracy of psychological stress assessment; therefore, the present invention provides a psychological stress assessment method based on heart-brain coupling analysis, which uses multivariate transfer entropy to explore the changes in information transmission between the brain and heart caused by stress, and accurately assesses psychological stress by analyzing the interaction between the central nervous system and the autonomic nervous system under stress.

[0052] Next, combine Figure 1-Figure 2, a psychological stress assessment method based on heart-brain coupling analysis disclosed in this embodiment is described in detail. The psychological stress assessment method based on heart-brain coupling analysis includes the following steps:

[0053] S1. Obtain the electrocardiogram signal and dual-channel electroencephalogram signal to be evaluated.

[0054] In order to remove various interferences generated during the signal acquisition process, as an implementation method, the ECG signal and dual-channel EEG signal to be evaluated are preprocessed. The specific process is as follows:

[0055] In this embodiment, the ECG signal is subjected to bandpass filtering and power frequency notch processing to remove baseline drift and power frequency interference; specifically, a second-order Butterworth bandpass filter (1-35Hz) is used to remove noise interference of the ECG signal, and a 50Hz notch is used to remove power frequency interference of the ECG signal.

[0056] The dual-channel EEG signals were first bandpass filtered and processed with power frequency notch to remove baseline drift and power frequency interference, and then independent component analysis was used to remove electrooculogram interference. Specifically, a Butterworth bandpass filter (0.5-45Hz) was used to remove noise interference in the EEG signals, a 50Hz notch was used to remove power frequency interference in the EEG signals, and independent component analysis was used to remove electrooculogram interference.

[0057] S2. Extract the interval sequence of the preprocessed ECG signal to construct an ECG interval sequence; based on the ECG interval, intercept and extract features of the preprocessed dual-channel EEG signal to construct an EEG multi-domain and multi-band feature sequence.

[0058] As an implementation method, the preprocessed ECG signal is subjected to interval sequence extraction, and the interval sequence is constructed specifically by: locating the peak point of the R wave in the ECG signal, extracting the R wave position, and constructing the RR interval sequence.

[0059] In this embodiment, the extracted ECG signal duration is 3 minutes, which includes several cardiac cycles. The position of the R wave peak in each cardiac cycle is detected, and the sampling point difference between two adjacent R wave peak positions is calculated to obtain the RR interval sequence. If there is an R wave peak point that is not detected, it needs to be added manually.

[0060] Furthermore, the preprocessed dual-channel EEG signals are segmented according to the RR interval sequence, that is, segmented according to the ECG interval, and the power spectral density sequence is calculated using the periodogram method; the δ, θ, α, β, and γ frequency bands of the power spectral density sequence are integrated respectively to construct a power sequence; and the mean, median, maximum, minimum, and standard deviation of the power spectral density in the power spectral density sequence are calculated as the frequency feature sequence corresponding to the power spectral density sequence to realize the extraction of frequency domain information in the dual-channel EEG signals.

[0061] The dual-channel EEG signal is filtered using a bandpass filter to obtain sub-band signals; the sub-band signals are segmented according to the length of the ECG interval, and their energy and Shannon entropy are calculated as the nonlinear feature sequence corresponding to the dual-channel EEG signal to achieve the extraction of nonlinear information in the dual-channel EEG signal. The above-mentioned power spectral density feature sequence, power sequence, energy and Shannon entropy sequence, that is, the frequency domain feature sequence and the nonlinear feature sequence constitute the EEG multi-domain and multi-band feature sequence of the dual-channel EEG signal, which fully mines the multi-domain information in the EEG signal, so as to make full use of the psychological stress assessment related information contained in it in the later stage.

[0062] The above time series were resampled and normalized, and finally 8 groups of synchronous feature sequences with consistent sampling rates were constructed. Each group consisted of RR interval sequences and EEG multi-domain and multi-band feature sequences.

[0063] S3. Calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence to construct an entropy feature sequence. Specifically include:

[0064] S301, six time series nodes (P δ ,P θ ,P α ,P β ,P γ ,RR) Select source node X and target node Y, and put the remaining nodes into Z. Construct candidate set CM = {X n-1 ,...,X n-μ ,Y n-1 ,...,Y n-μ ,Z n-1 ,...,Z n-μ}. CM contains all the candidates, and the vectors in CM represent the past variables of the corresponding time series nodes lagged by a specific time, where μ represents the maximum lag time.

[0065] S302, initialize an empty embedding vector V n (0) .

[0066] S303, select a candidate item in CM to be included in the embedding vector, perform this operation K times, in the Kth operation, calculate the mutual information between the target variable in the target node and the embedding vector, and select the candidate item with the largest mutual information, and determine whether it meets the candidate significance check. If so, put this item into the embedding vector and delete it from the candidate set. If not, calculate the information transfer from the source node X to the target node Y.

[0067] Exemplarily, a while loop is executed from 1 to the total number of initial candidates in CM.

[0068] In the kth cycle, k-1 candidates have been selected in CM and included in V n (k-1) After that, for the remaining candidates in CM, calculate the target variable Y n and V′ n The mutual information between n is the current item of CM W n (i) With V n (k-1) The temporary vector V′ n =[W n (i) V n (k-1) ]. The calculation formula of the mutual information between them is:

[0069] (Y n ; V n ′)=H(Y n )-H(Y n |V n ′);

[0070] Among them, H(Y n ) and H(Y n rV n ′) represent Shannon entropy and conditional entropy respectively, which can be calculated by the following formula:

[0071] H(Y n ) = -∑ρ(y)log(ρ(y));

[0072] H(Y n |V′ n )=∑ρ(y,v′)log(ρ(y|v′));

[0073] Where ρ(y) represents Y n = the probability of y, ρ(y,v′) represents Y n and V n ′, ρ(y|v′) represents the joint probability of Y n and V′ n The conditional probability distribution of .

[0074] Among all the remaining CM candidates tested, select the CM item that maximizes the mutual information. Check whether the selected CM item satisfies the candidate significance test. If it does, it means that the source node represented by the item has transmitted valid information to the target node, so put it into V so that And delete it from CM, and then continue to loop for the remaining items in CM. If it is not satisfied, the loop ends.

[0075] Furthermore, the candidate significance test specifically refers to the test of Wn The points are appropriately randomized and a null distribution is established based on experience, and the target variable Y n With W n The conditional mutual information between Compared with this null distribution, if Higher than 100(1-α) of this null distribution th If the percentile is less than 0.05, the candidate significance test is passed. α is the required significance level. In this embodiment, α=0.05 is selected.

[0076] Furthermore, the information transfer from the source node X to the target node Y is calculated, that is, the multivariate transfer entropy, and the entropy value feature sequence is obtained. The calculation formula is as follows:

[0077] MuTE(X→Y|Z)=H(Y|V -1 )-H(Y|V)

[0078] Among them, V -1 Represents the subset of the embedding vector set V that does not contain the source node sequence.

[0079] After traversing all source nodes, return to source node and target node selection until all nodes are selected as target nodes.

[0080] In this embodiment, the difference between the conditional entropy of the target node and the optimal embedding vector set containing or excluding the source node sequence is calculated, that is, the conditional entropy of the set is calculated to describe the transfer entropy value between the nodes.

[0081] In summary, multivariate transfer entropy refers to the existence of multiple time series nodes in a network. After confirming the source node, the target node and the remaining nodes, a candidate set is constructed through the past variables of the corresponding time series nodes lagged by a specific time, and then the mutual information is calculated through a while loop to select the node with the largest mutual information of the multi-target nodes, and determine whether the candidate significance test is satisfied, and finally calculate the transfer entropy. That is, the multivariate in this embodiment refers to multiple nodes, and there are steps such as cyclic calculation of mutual information and candidate significance test, and the calculation is more accurate.

[0082] S4. Process the entropy feature sequence through the trained psychological stress classification model to generate and output the psychological stress assessment result.

[0083] As an implementation method, before executing S4, the psychological stress classification model needs to be trained, specifically including:

[0084] (1) Obtain the ECG signals and dual-channel EEG signals in the resting state and the stress state, and construct the entropy feature sequence using the steps described in S1-S3 above.

[0085] (2) Use the recursive feature elimination method based on support vector machine to select features of the entropy feature sequence, use the selected feature set to train the support vector machine, and use the trained support vector machine as the psychological stress classification model.

[0086] In order to compare the status of information transmission between different nodes and the changes in information transmission when entering a stress state, and to compare the difference in information transmission between the heart and the brain, as an implementation method, the calculated entropy value is averaged across the whole brain, and the average entropy value matrix is ​​plotted in the form of a heat map. Each element in the 6*6 matrix is ​​the amount of information transmitted from the source node to the target node.

[0087] By analyzing the input and output of each node information and drawing a bar chart, the changes of the information input and output nodes under two states can be observed.

[0088] Embodiment 2

[0089] Combination Figure 3 This embodiment discloses a psychological stress assessment system based on heart-brain coupling analysis, including:

[0090] An acquisition module is configured to: acquire an electrocardiogram signal and a dual-channel electroencephalogram signal to be evaluated;

[0091] The sequence construction module is configured to: extract the interval sequence of the ECG signal to construct the ECG interval sequence; intercept and extract the features of the dual-channel EEG signal according to the length of the ECG interval to construct the EEG multi-domain and multi-band feature sequence;

[0092] The entropy value construction module is configured to: calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence, and construct an entropy value feature sequence;

[0093] The psychological stress assessment module is configured to: process the entropy value feature sequence through a trained psychological stress classification model to generate and output a psychological stress assessment result.

[0094] It should be noted that the acquisition module, sequence construction module, entropy construction module and psychological stress assessment module correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the modules are the same as those of the corresponding steps, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0095] Embodiment 3

[0096] Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned psychological stress assessment method based on heart-brain coupling analysis are completed.

[0097] Embodiment 4

[0098] Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned psychological stress assessment method based on heart-brain coupling analysis are completed.

[0099] Embodiment 5

[0100] Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned psychological stress assessment method based on heart-brain coupling analysis.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A psychological stress assessment method based on heart-brain coupling analysis, characterized in that: include: Obtain the ECG signal and dual-channel EEG signal to be evaluated; Extract the interval sequence of ECG signal and construct the ECG interval sequence; Based on the ECG interval, the dual-channel EEG signals are intercepted and feature extracted to construct EEG multi-domain and multi-band feature sequences; Calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence, and construct the entropy value feature sequence; The entropy value feature sequence is processed by a trained psychological stress classification model to generate and output a psychological stress assessment result.

2. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: Also includes: Based on the entropy feature sequence, the information matrix is ​​plotted in the form of a heat map.

3. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: The extracting of interval sequence from the ECG signal and constructing the ECG interval sequence specifically includes: locating the peak point of the R wave in the ECG signal, extracting the R wave position, and constructing the RR interval sequence.

4. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: The intercepting of the dual-channel EEG signal based on the ECG interval is specifically: based on the ECG interval, the dual-channel EEG signal is intercepted and segmented in combination with the time synchronization information between the ECG signal and the dual-channel EEG signal.

5. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: Extracting features from dual-channel EEG signals and constructing EEG multi-domain and multi-band feature sequences specifically include: Calculate the power spectrum density sequence based on the dual-channel EEG signal segmented by the ECG interval; Integrate the δ, θ, α, β, and γ frequency bands of the power spectral density sequence to construct a power sequence; Extract EEG frequency domain information from the power spectrum density sequence to obtain the mean, median, maximum, minimum and standard deviation of the power spectrum density; The dual-channel EEG signals are processed using a bandpass filter to obtain sub-band signals; the sub-band signals are segmented according to the length of the ECG interval and the EEG nonlinear information is extracted to obtain energy and Shannon entropy.

6. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: The method calculates the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain multi-band feature sequence to construct the entropy value feature sequence, specifically: combining the ECG interval sequence and the multi-domain EEG multi-band feature sequence into a time series, selecting a source node and a target node in the time series node, and calculating the information transfer from the source node to the target node.

7. The psychological stress assessment method based on heart-brain coupling analysis according to claim 1, characterized in that: Training the psychological stress classification model specifically includes: Obtain ECG signals and dual-channel EEG signals in resting and stress states, and construct entropy feature sequences; The recursive feature elimination method based on support vector machine is used to select features of entropy feature sequence, and the support vector machine is trained using the selected feature set.

8. A psychological stress assessment system based on heart-brain coupling analysis, characterized in that: include: An acquisition module is configured to: acquire an electrocardiogram signal and a dual-channel electroencephalogram signal to be evaluated; The sequence construction module is configured to: extract the interval sequence of the ECG signal to construct the ECG interval sequence; based on the ECG interval, intercept and extract the features of the dual-channel EEG signal to construct the EEG multi-band feature sequence; The entropy value construction module is configured to: calculate the multivariate transfer entropy between the ECG interval sequence and the EEG multi-domain and multi-band feature sequence, and construct an entropy value feature sequence; The psychological stress assessment module is configured to: process the entropy value feature sequence through a trained psychological stress classification model to generate and output a psychological stress assessment result.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the psychological stress assessment method based on heart-brain coupling analysis according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the psychological stress assessment method based on heart-brain coupling analysis described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Brain-heart coupling feature extraction method and device and electronic equipment

    CN120093237A

  • Emotion prediction method and system based on cardiac-computerized electrical coupling

    CN120514386A