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

Abstract

The invention provides a brain-heart coupling feature extraction method, a brain-heart coupling feature extraction device and electronic equipment, and belongs to the field of electric digital signal processing. The method comprises the steps that electroencephalogram signals and electrocardiosignals are obtained, analysis is conducted on the basis of objective physiological data, power spectrum density information corresponding to the electroencephalogram signals is obtained, heart rate variability data are obtained on the basis of the electrocardiosignals, the time-varying regulation and control coupling strength of the brain to low-frequency and high-frequency components of heart activity is further determined, and then the time-varying regulation and control coupling strength is obtained. And performing fusion analysis based on the time-varying regulation coupling strength and the power spectrum density information corresponding to the electroencephalogram signal, depicting a physiological mechanism related to cognition, and capturing features of interaction between the brain and the heart, thereby obtaining first coupling feature information of the brain corresponding to the target user for the heart. The cognitive level misjudgment rate can be effectively reduced, the extracted first coupling feature information can reflect the real cognitive state of the target user more accurately, and a more accurate basis is provided for cognitive level evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical digital signal processing, and in particular to a method, device and electronic equipment for extracting brain-heart coupling features. Background Art

[0002] Cognitive level is a key basis for measuring the functional state of an individual's brain and assessing the risk of neurological diseases. In related technologies, the cognitive level of subjects is mainly assessed by physicians' interviews and various cognitive scales.

[0003] However, the evaluation of the cognitive level of the subjects is based on the physician's interview and various cognitive scales. On the one hand, the data acquisition is limited to the subjective description and scale filling of the subjects, lacking the support of objective physiological indicators, and the data dimension is single; on the other hand, the evaluation process is easily interfered by subjective factors, resulting in a high rate of misjudgment and missed judgment. These problems make it difficult for the evaluation results to accurately reflect the true cognitive state of the subjects. Summary of the invention

[0004] The embodiments of the present invention provide a method, device and electronic device for extracting brain-heart coupling features to solve the problem of difficulty in accurately reflecting the real cognitive state of a subject.

[0005] In a first aspect, an embodiment of the present invention provides a method for extracting brain-heart coupling features, comprising: Acquire an EEG signal and an ECG signal of a target user, and obtain heart rate variability data of the target user based on the ECG signal, and obtain power spectrum density information of the target user based on the EEG signal; Based on the heart rate variability data, determining a first time-varying regulatory coupling strength of the brain for the low-frequency component of the heart activity and a second time-varying regulatory coupling strength of the brain for the high-frequency component of the heart activity; According to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the first coupling characteristic information of the brain to the heart corresponding to the target user is obtained; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

[0006] In a possible implementation, the power spectrum density information includes first power information of the preprocessed EEG signal in a first preset frequency band and second power information of the preprocessed EEG signal in a second preset frequency band; wherein the first preset frequency band is a frequency band associated with a low arousal state of the brain, and the second preset frequency band is a frequency band associated with a higher neural function of the brain; The obtaining the power spectrum density information of the target user based on the EEG signal includes: Preprocessing the EEG signal to obtain a preprocessed EEG signal; wherein the preprocessing includes filtering, re-referencing and artifact removal; The preprocessed EEG signal is integrated in the first preset frequency band and the second preset frequency band using short-time Fourier transform to obtain first power information of the preprocessed EEG signal in the first preset frequency band and second power information of the preprocessed EEG signal in the second preset frequency band.

[0007] In a possible implementation, the first coupling feature information includes a high-to-low frequency ratio coupling feature of the brain to the heart and a coupling feature of the brain to the heart when the brain is active in a second preset frequency band; The obtaining, according to the power spectrum density information, the first time-varying regulation coupling strength, and the second time-varying regulation coupling strength, first coupling characteristic information of the brain to the heart corresponding to the target user includes: According to the first power information, the second power information and the first time-varying regulation coupling strength, a high-to-low frequency ratio coupling feature of the brain on the heart is obtained; wherein the high-to-low frequency ratio coupling feature represents a relative relationship between the regulation strengths of the brain on the heart activity when the brain is active in the first preset frequency band and the second preset frequency band, and the upper frequency limit in the first preset frequency band is less than the lower frequency limit in the second preset frequency band; According to the second power information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band are obtained.

[0008] In a possible implementation, obtaining the high-to-low frequency ratio coupling characteristics of the brain to the heart according to the first power information, the second power information, and the first time-varying regulation coupling strength includes: Determine that the value of the first time-varying regulation coupling strength at a first preset moment is a first regulation coupling strength, and determine, based on the first power information, that the power of the preprocessed EEG signal in the first preset frequency band in a time window before the first preset moment is a first power, and determine, based on the second power information, that the power of the preprocessed EEG signal in the second preset frequency band in a time window before the first preset moment is a second power; The ratio between the first regulation coupling strength and the first power is used as a coupling coefficient of the brain to the cardiac low frequency when the brain is active in the first preset frequency band; The ratio between the first regulation coupling strength and the second power is used as a coupling coefficient of the brain to the cardiac low frequency when the brain is active in the second preset frequency band; The ratio of the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band to the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band is used as the high-low frequency ratio coupling feature.

[0009] In a possible implementation, obtaining the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band according to the second power information, the first time-varying regulation coupling strength, and the second time-varying regulation coupling strength includes: Determine that the value of the first time-varying regulation coupling strength at the second preset moment is the second regulation coupling strength, and determine that the value of the second time-varying regulation coupling strength at the second preset moment is the third regulation coupling strength; and determine, based on the second power information, that in a time window before the second preset moment, the power of the preprocessed EEG signal in the second preset frequency band is the fourth power; Using the ratio between the second regulated coupling strength and the fourth power as the coupling coefficient of the brain to the cardiac low frequency when the brain is active in the second preset frequency band; Using the ratio between the third regulated coupling strength and the fourth power as the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band; The ratio between the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band and the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band is used as the coupling characteristic of the brain to the heart when the brain is active in the second preset frequency band.

[0010] In a possible implementation, determining, based on the heart rate variability data, a first time-varying regulation coupling strength of the brain for the low-frequency component of the cardiac activity and a second time-varying regulation coupling strength of the brain for the high-frequency component of the cardiac activity includes: Constructing a heartbeat model corresponding to the heart rate variability data; wherein the heartbeat model is composed of an average heart rate term and an autonomic nerve activity term, and the autonomic nerve activity term is used to simulate the regulation of the heart by the autonomic nervous system; Based on the Poincare map features corresponding to the heart rate variability data, the first time-varying regulatory coupling strength of the brain for the low-frequency components of cardiac activity and the second time-varying regulatory coupling strength of the brain for the high-frequency components of cardiac activity in the autonomic nervous activity item are calculated.

[0011] In a possible implementation, after obtaining the heart rate variability data of the target user based on the electrocardiogram signal and obtaining the power spectrum density information of the target user based on the electroencephalogram signal, the method further includes: The heart rate variability data is integrated in a low frequency band and a high frequency band by using short-time Fourier transform to obtain low frequency power information of the heart rate variability data in the low frequency band and high frequency power information of the heart rate variability data in the high frequency band; wherein the low frequency band is a frequency band reflecting the comprehensive regulatory effect of the sympathetic nerves and the parasympathetic nerves in the autonomic nervous system, and the high frequency band is a frequency band reflecting the regulatory effect of the parasympathetic nerves on the cardiac activity; Based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, second coupling characteristic information of the heart to the brain corresponding to the target user is obtained; wherein the modulation information of the heart to the brain is determined based on the power density information of the target user, and the second coupling characteristic information is used to evaluate the cognitive level of the target user.

[0012] In a possible implementation, the second coupling characteristic information includes a low-high frequency ratio characteristic of the heart to the brain and a mixing frequency ratio characteristic of the heart to the brain; The obtaining, based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, second coupling characteristic information of the heart to the brain corresponding to the target user includes: Determine, according to the low-frequency power information, the high-frequency power information, and the modulation information of the heart to the brain, a coupling coefficient of the high-frequency activity of the heart to a first preset frequency band of the brain, a coupling coefficient of the high-frequency activity of the heart to a second preset frequency band of the brain, and a coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain; The ratio between the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain and the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain is used as a low-high frequency ratio feature of the heart to the brain; The ratio between the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain is used as the mixing ratio characteristic of the heart to the brain.

[0013] In a second aspect, an embodiment of the present invention provides a brain-heart coupling feature extraction device, the device comprising: A first processing unit is used to obtain an EEG signal and an ECG signal of a target user, and obtain heart rate variability data of the target user based on the ECG signal, and obtain power spectrum density information of the target user based on the EEG signal; A second processing unit is used to determine a first time-varying regulatory coupling strength of the brain for the low-frequency component of the cardiac activity and a second time-varying regulatory coupling strength of the brain for the high-frequency component of the cardiac activity based on the heart rate variability data; The third processing unit is used to obtain the first coupling characteristic information of the brain to the heart corresponding to the target user according to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the brain-heart coupling feature extraction method as described in the first aspect or any possible implementation method of the first aspect are implemented.

[0015] The embodiment of the present invention provides a method, device and electronic device for extracting brain-heart coupling features. By introducing objective physiological data, including EEG signals and ECG signals, and analyzing based on these objective physiological data, the limitations of subjective information are avoided, objective support is provided for cognitive level assessment, and the results are more reliable. In addition, the embodiment of the present invention not only obtains power spectrum density information using EEG signals, but also obtains heart rate variability data based on ECG signals, and further determines the time-varying regulation coupling strength of the brain on the low-frequency and high-frequency components of cardiac activity, enriching the data dimension. Then, based on multi-dimensional data, fusion analysis is performed to more carefully characterize the physiological mechanism related to cognition, and more comprehensively capture the characteristics of the interaction between the brain and the heart, so as to obtain the first coupling feature information of the brain corresponding to the target user for the heart. In summary, the embodiment of the present invention gets rid of the problem that the traditional assessment is easily affected by subjective judgment or subjective expression. By processing and analyzing objective signals, the misjudgment and missed judgment rates can be effectively reduced, so that the extracted first coupling feature information more accurately reflects the real cognitive state of the target user, providing a more accurate basis for cognitive level assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a brain-heart coupling feature extraction method provided by an embodiment of the present invention; Figure 2 A flowchart of another brain-heart coupling feature extraction method provided by an embodiment of the present invention; Figure 3 A comparative schematic diagram of high-low frequency ratio coupling characteristics provided by an embodiment of the present invention; Figure 4 A comparative schematic diagram of coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band provided by an embodiment of the present invention; Figure 5 A flowchart of another brain-heart coupling feature extraction method provided by an embodiment of the present invention; Figure 6 A schematic diagram for comparing low to high frequency ratio characteristics provided by an embodiment of the present invention; Figure 7 A schematic diagram for comparing mixing ratio characteristics provided by an embodiment of the present invention; Figure 8 A schematic diagram of the structure of a brain-heart coupling feature extraction device provided by an embodiment of the present invention; Fig. 9 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0019] Cognitive level is the key basis for measuring the functional state of an individual's brain and assessing the risk of neurological diseases. In related technologies, the cognitive level of the subject is mainly assessed by the physician's interview and various cognitive scales. However, relying on the physician's interview and various cognitive scales to assess the cognitive level of the subject, on the one hand, the acquisition of data is limited to the subjective description and scale filling of the subject, lacks the support of objective physiological indicators, and the data dimension is single; on the other hand, the evaluation process is easily interfered by subjective factors, resulting in a high rate of misjudgment and missed judgment. These problems make it difficult for the evaluation results to accurately reflect the true cognitive state of the subject.

[0020] The present invention introduces objective physiological data, including EEG signals and ECG signals, and performs analysis based on these objective physiological data to make the results more reliable; further, heart rate variability data is obtained based on ECG signals to determine the time-varying regulatory coupling strength of the brain on the low-frequency and high-frequency components of cardiac activity, and power spectral density information is obtained using EEG signals. Then, a fusion analysis is performed based on the obtained multi-dimensional data to capture the characteristics of the interaction between the brain and the heart, and the first coupling characteristic information of the brain corresponding to the heart of the target user is obtained, which more accurately reflects the real cognitive state of the target user and provides a more accurate basis for cognitive level assessment.

[0021] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0022] Figure 1 A flowchart of a brain-heart coupling feature extraction method provided by an embodiment of the present invention is described in detail as follows: Step 101, obtaining the EEG signal and the ECG signal of the target user, and obtaining the heart rate variability data of the target user based on the ECG signal, and obtaining the power spectrum density information of the target user based on the EEG signal.

[0023] Exemplarily, in order to make the data more accurate and less error-prone, this embodiment uses EEG and ECG synchronous acquisition equipment to acquire the EEG signals and ECG signals of the target user, namely, the electroencephalogram (EEG) and electrocardiogram (ECG).

[0024] Furthermore, this embodiment uses the Pan-Tompkins algorithm to identify the R wave peak in the ECG signal and calculate the time interval (RR interval) between adjacent R waves, thereby obtaining the heart rate data and heart rate variability data of the target user.

[0025] Furthermore, this embodiment extracts frequency domain features of the EEG signal to obtain distribution features reflecting brain neural activity energy at different frequency components, namely, power spectral density (PSD).

[0026] Step 102, based on the heart rate variability data, determine a first time-varying regulatory coupling strength of the brain for the low-frequency components of the cardiac activity and a second time-varying regulatory coupling strength of the brain for the high-frequency components of the cardiac activity.

[0027] Exemplarily, this embodiment analyzes the autonomic nervous system regulation characteristics of heart rate variability data to extract time-varying coupling parameters that reflect the target user's brain's dynamic regulation of cardiac activity through the sympathetic-parasympathetic nerves, including the brain's first time-varying regulation coupling strength for low-frequency components of cardiac activity and the brain's second time-varying regulation coupling strength for high-frequency components of cardiac activity, providing key physiological indicators for the analysis of the correlation between brain-heart interaction mechanism and cognitive function.

[0028] In one example, the first time-varying regulatory coupling strength is a sympathetic-dominant regulatory strength associated with low-frequency power, wherein the frequency range of the low-frequency power LF can be 0.04 Hz to 0.15 Hz, and the second time-varying regulatory coupling strength is a parasympathetic-dominant regulatory strength associated with high-frequency power, wherein the frequency range of the high-frequency power HF can be 0.15 Hz to 0.4 Hz.

[0029] Step 103, obtaining first coupling characteristic information of the brain to the heart corresponding to the target user according to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

[0030] Exemplarily, this embodiment fuses cross-modal information of EEG frequency domain features reflecting the energy distribution of brain neural activity with time-varying characteristics of cardiac autonomic nervous regulation reflecting the dynamic balance of sympathetic / parasympathetic nerves, for example, through regression analysis, machine learning or transfer function analysis, to establish a coupling relationship between EEG frequency domain features and cardiac regulation parameters, obtain the first coupling feature information of the brain corresponding to the heart of the target user, and quantify the cognitive function state and level of the target user.

[0031] The user's cognitive function state and level are closely related to whether the user has cognitive impairment or related degenerative diseases. Therefore, after obtaining the first coupling feature information, this embodiment can use it to evaluate whether the target user has cognitive impairment or related degenerative diseases, such as Alzheimer's disease.

[0032] In summary, the embodiments of the present invention introduce objective physiological data, including EEG signals and ECG signals, and perform analysis based on these objective physiological data, thus avoiding the limitations of subjective information, providing objective support for cognitive level assessment, and making the results more reliable; moreover, the embodiments of the present invention use EEG signals to obtain power spectrum density information, obtain heart rate variability data based on ECG signals, and further determine the time-varying regulation coupling strength of the brain on the low-frequency and high-frequency components of cardiac activity, and then perform fusion analysis based on multi-dimensional data to characterize the physiological mechanisms related to cognition, and comprehensively capture the characteristics of the interaction between the brain and the heart, so as to obtain the first coupling feature information of the brain corresponding to the heart of the target user. It can effectively reduce the misjudgment and missed judgment rates, so that the extracted first coupling feature information can more accurately reflect the real cognitive state of the target user, and provide a more accurate basis for cognitive level assessment.

[0033] In order to further improve the signal quality and reduce the analysis error, this embodiment preprocesses the EEG signal, including filtering, re-referencing and artifact removal; and refines the method of obtaining the first time-varying regulation coupling strength and the second time-varying regulation coupling strength using the constructed heartbeat model; using the first power information of the preprocessed EEG signal in the first preset frequency band and the second power information of the preprocessed EEG signal in the second preset frequency band as well as the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the high-low frequency ratio coupling characteristics of the brain to the heart and the coupling characteristics of the brain to the heart when it is active in the second preset frequency band are obtained, forming the first coupling characteristic information of the brain to the heart corresponding to the target user.

[0034] Figure 2 Another implementation flow chart of a brain-heart coupling feature extraction method provided by an embodiment of the present invention is described in detail as follows: Step 201, obtaining the EEG signal and the ECG signal of the target user, and obtaining the heart rate variability data of the target user based on the ECG signal, and obtaining the power spectrum density information of the target user based on the EEG signal.

[0035] Among them, the power spectral density information includes the first power information of the EEG signal after preprocessing in the first preset frequency band and the second power information of the EEG signal after preprocessing in the second preset frequency band; wherein the first preset frequency band is a frequency band related to the low arousal state of the brain, and the second preset frequency band is a frequency band related to the higher neural functions of the brain.

[0036] In a feasible implementation manner, step 201 includes: The EEG signal is preprocessed to obtain a preprocessed EEG signal; wherein the preprocessing includes filtering processing, re-reference processing and artifact removal processing.

[0037] The preprocessed EEG signal is integrated in the first preset frequency band and the second preset frequency band using short-time Fourier transform to obtain first power information of the preprocessed EEG signal in the first preset frequency band and second power information of the preprocessed EEG signal in the second preset frequency band.

[0038] Exemplarily, this embodiment first obtains the logarithmic power spectrum density diagram of all channels of the EEG signal, and identifies and removes bad channels caused by poor electrode contact or signal interference based on the power spectrum density diagram.

[0039]

[0040] in, The EEG signal has a frequency The power spectral density at The total duration of the time window, The original EEG signal, is the complex exponential term of the Fourier transform.

[0041] Then, a bandpass filter is used to filter the signal, retaining the EEG signal in the frequency range of 0.5 Hz to 45 Hz. The filtering formula is as follows:

[0042] in, is the EEG signal before filtering, are the coefficients of the filter, is the filter order, is the filtered signal.

[0043]

[0044] in, =45 / is the normalized high frequency cutoff frequency, is the sampling frequency), =0.5 / is the normalized low frequency cutoff frequency.

[0045] After filtering, the EEG signal is re-referenced using a whole-brain average reference method to further improve signal quality.

[0046] Independent Component Analysis (ICA) was used to identify and manually remove non-EEG artifacts in EEG signals, such as electrooculography, electromyography and other interfering components.

[0047] The EEG signal can be represented as a linear mixture of multiple independent signals as follows:

[0048] in, is the observed EEG signal matrix (size N×T, N is the number of channels, T is the number of time points), is the mixing matrix (projection of each independent component on the EEG channel), is the independent component matrix. ICA aims to find a demixing matrix So that:

[0049] in: (A is reversible) In an example, this embodiment uses short-time Fourier transform (STFT) to perform integral analysis on the ICA-processed signal in a first preset frequency band δ (0.5 Hz-4 Hz) and a second preset frequency band γ (30 Hz-45 Hz), and obtains power spectral density in the two frequency bands respectively.

[0050] In another feasible implementation manner, this embodiment can also use STFT to perform integral analysis on the ICA-processed signal in five frequency bands δ (0.5 Hz-4 Hz), θ (4 Hz-8 Hz), α (8 Hz-12 Hz), β (12 Hz-30 Hz), and γ (30 Hz-45 Hz), respectively obtaining the power spectral density in the five frequency bands, and using the power spectral density in the five frequency bands to extract brain-heart coupling features. This embodiment takes δ (0.5 Hz-4 Hz) and γ (30 Hz-45 Hz) as examples.

[0051] Among them, different frequency bands of EEG activity can be used as important indicators of central nervous system activity. (0.5Hz-4Hz), namely the Delta wave mentioned below, is mainly related to low arousal states such as deep sleep, loss of consciousness, brain damage, etc. Theta (4Hz-8Hz) waves are closely related to light sleep, emotional regulation, concentration and memory encoding. Alpha (8Hz-12Hz) wave changes are often used to assess perception, attention and task involvement. Beta (12Hz-30Hz) waves are related to motor control, alertness, and active thinking. (30Hz-45Hz), namely the Gamma wave below, involves perceptual binding, consciousness generation and high-level cognitive functions.

[0052] Among them, STFT calculates the Fourier transform of the signal through a sliding window and is defined as follows:

[0053] in: It's time The frequency distribution at (time-frequency representation), is the original EEG time series, is the sliding window function (Hanning window), is the complex exponential term of the Fourier transform, It's the frequency.

[0054] For five frequency bands ( ,θ,α,β, ) is integrated and the power spectral density (PSD) is used to represent the time-frequency energy:

[0055] For each frequency band ( ) to perform integral calculation:

[0056] in: A certain point in time The frequency band energy at It is PSD. is the frequency range of the band.

[0057] In one example, this embodiment uses a finite impulse response (FIR) bandpass filter to filter the collected ECG signal, retain the signal from 0.5 Hz to 45 Hz, and use the Pan-Tompkins method to detect the R wave to obtain the RR interval signal.

[0058]

[0059] in, is the original ECG amplitude, is the mean value of the signal, is the standard deviation of the signal, The normalized magnitude.

[0060] After obtaining the RR interval signal, this embodiment applies spline interpolation to resample the obtained RR sequence signal to ensure that the data is distributed at a constant frequency of 4 Hz, that is, one point every 0.25 seconds, to obtain heart rate variability data.

[0061] Step 202, constructing a heartbeat model corresponding to the heart rate variability data; wherein the heartbeat model is composed of an average heart rate term and an autonomic nerve activity term, and the autonomic nerve activity term is used to simulate the regulation of the heart by the autonomic nervous system.

[0062] Exemplarily, this embodiment uses an integral pulse frequency modulation (IPFM) model to parameterize the heartbeat, which calculates the occurrence of heartbeat events by superimposing two oscillators that simulate sympathetic and parasympathetic nerve activities.

[0063] The model uses the Dirac delta function to represent heartbeat events, where represents continuous time, Indicates The time when the heartbeat occurs. The heartbeat event is expressed by the following formula:

[0064] The occurrence of a heartbeat depends on an integral function. When this integral function reaches the set threshold of 1, a heartbeat is generated and the integrator is reset to 0. The integral function is defined as follows:

[0065] in, is the average heart rate (Hz), It is a simulation of autonomic nervous activity. The brain mainly controls the heart through the autonomic nervous system.

[0066] Step 203, based on the Poincare map features corresponding to the heart rate variability data, calculate the first time-varying regulatory coupling strength of the brain for the low-frequency components of the heart activity and the second time-varying regulatory coupling strength of the brain for the high-frequency components of the heart activity in the autonomic nervous activity item.

[0067] In one example, autonomic nervous system activity It is expressed by the following formula:

[0068] and is the time-varying coupling constant calculated based on the characteristics of the Poincare map.

[0069] Thus, the coupling coefficient of the brain to the heart is obtained to reflect the intensity of regulation from the brain to the heart:

[0070]

[0071] in, For a certain time Frequency in the previous time window The power of the EEG at a certain time point The intensity of brain activity in the previous time window, The brain modulates the coupling strength of the low-frequency components of cardiac activity for the first time. It is a negative value, indicating that as brain activity increases, the activity of the low-frequency heart decreases linearly, and vice versa. The level of represents the strength of the brain's regulation of the low-frequency components of cardiac activity. A second time-varying modulation of coupling strength by the brain to the high-frequency components of cardiac activity. It is a negative value, indicating that as brain activity increases, the high-frequency activity of the heart decreases linearly, and vice versa. The level of represents the strength of the brain's regulation of the high-frequency components of heart activity.

[0072] Step 204, obtaining the high-low frequency ratio coupling characteristics of the brain to the heart according to the first power information, the second power information and the first time-varying regulation coupling strength, so as to evaluate the cognitive level of the target user.

[0073] Among them, the high-low frequency ratio coupling feature represents the relative relationship between the brain's regulatory intensity on cardiac activity when the brain is active in the first preset frequency band and the second preset frequency band, and the upper frequency limit in the first preset frequency band is smaller than the lower frequency limit in the second preset frequency band.

[0074] In one example, the first preset frequency band is (0.5Hz-4Hz), which is associated with low arousal states such as deep sleep, loss of consciousness, and brain damage. The second preset frequency band is (30Hz-45Hz).

[0075] In a feasible implementation manner, step 204 includes the following steps: Determine that the value of the first time-varying regulation coupling strength at the first preset moment is the first regulation coupling strength, and determine based on the first power information that in a time window before the first preset moment, the power of the preprocessed EEG signal in a first preset frequency band is the first power, and determine based on the second power information that in a time window before the first preset moment, the power of the preprocessed EEG signal in a second preset frequency band is the second power.

[0076] The ratio between the first regulated coupling intensity and the first power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band.

[0077] The ratio between the first regulated coupling intensity and the second power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band.

[0078] The ratio of the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band to the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band is used as the high-low frequency ratio coupling feature.

[0079] Exemplarily, in this embodiment, the first time-varying regulation coupling strength of the brain for the low-frequency component of the heart activity obtained in step 203 is The second time-varying regulation coupling strength of the brain to the high-frequency components of cardiac activity Calculate the high-low frequency ratio coupling characteristics. Indicates the first preset time:

[0080] in, is the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band at the first preset moment, is the first regulatory coupling strength, is the second power.

[0081]

[0082] in, is the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band at the first preset moment, is the first regulatory coupling strength, is the first power.

[0083]

[0084] Right now

[0085] in, It is the high-low frequency ratio coupling characteristic at the first preset moment.

[0086] Since the high-to-low frequency ratio coupling feature characterizes the relative relationship between the brain's regulatory intensity on cardiac activity when the first preset frequency band and the second preset frequency band are active, that is, the brain's high-to-low frequency ratio coupling feature on the heart can reflect the dynamic balance of brain wakefulness-cognition, the high-to-low frequency ratio coupling feature is an intuitive sign of brain functional integrity and can be used to assess cognitive level.

[0087] In one example, the high-low frequency ratio coupling feature is compared with the high-low frequency ratio coupling feature corresponding to a person with normal cognition or cognitive impairment, and the cognitive level of the target user is evaluated based on their similarities or differences. For example, if the difference between the high-low frequency ratio coupling feature of the target user and the high-low frequency ratio coupling feature corresponding to a person with cognitive impairment is within a preset range, it is evaluated that the target user has cognitive impairment.

[0088] In one example, an embodiment of the present invention collects EEG signals and ECG signals of subjects with normal and abnormal cognitive levels through EEG and ECG synchronous acquisition equipment, and based on these data, obtains high-low frequency ratio coupling characteristics of 30 control groups and 8 cognitive impairment groups.

[0089] Figure 3 Schematic diagram of comparison of high-low frequency ratio coupling features provided by an embodiment of the present invention, the ordinate is the value of the high-low frequency ratio coupling feature, and the abscissa corresponds to the control group and the cognitive impairment group, such as Figure 3 As shown, there are significant differences in the high-low frequency ratio coupling features between the control group and the cognitive impairment group. In this embodiment, 6.99 is taken as the classification threshold to distinguish the control group from the cognitive impairment group, which can achieve an accuracy rate of 80%.

[0090] Step 205, based on the second power information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, obtain the coupling characteristics of the brain to the heart when it is active in the second preset frequency band, so as to evaluate the cognitive level of the target user.

[0091] In a feasible implementation manner, step 205 includes the following steps: Determine that the value of the first time-varying regulation coupling strength at the second preset moment is the second regulation coupling strength, and determine that the value of the second time-varying regulation coupling strength at the second preset moment is the third regulation coupling strength; and based on the second power information, determine that in the time window before the second preset moment, the power of the preprocessed EEG signal in the second preset frequency band is the fourth power.

[0092] The ratio between the second regulated coupling intensity and the fourth power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band.

[0093] The ratio between the third regulated coupling intensity and the fourth power is used as the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band.

[0094] The ratio between the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band and the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band is used as the coupling characteristic of the brain to the heart when the brain is active in the second preset frequency band.

[0095] Exemplarily, this embodiment is based on the obtained and Coupling characteristics of the brain to the heart during activity in the second preset frequency band:

[0096] in, is the coupling coefficient of the brain to the low frequencies of the heart when the brain is active in the second preset frequency band, is the second regulatory coupling strength, The fourth power.

[0097]

[0098] in, is the coupling coefficient of the brain to the high frequency of the heart when it is active in the second preset frequency band, The third is to regulate the coupling strength.

[0099]

[0100] That is, the coupling characteristics of the brain to the heart when it is active in the second preset frequency band are .

[0101] Exemplarily, since the second preset frequency band is closely related to advanced cognitive functions. When the cognitive level changes, the relative strength of the brain's regulation of the low and high frequencies of the heart will also change, and this change is reflected in the coupling coefficient ratio. For example, in a higher cognitive state such as concentration and active thinking, the relevant neural activity is enhanced, and the regulation of the low and high frequencies of the heart will present a specific balance relationship, so that the ratio is within a certain range; and when cognition is impaired or the level decreases, this balance is broken, and the ratio will change accordingly, so the user's cognitive level can be evaluated accordingly.

[0102] In one example, the coupling feature is compared with the coupling features corresponding to people with normal cognition or cognitive impairment, and the cognitive level of the target user is evaluated based on the similarities or differences.

[0103] For example, if the similarity between the values, value changes, and distributions of the coupling features of the target user and the coupling features corresponding to the person with cognitive impairment is greater than a preset similarity, it is assessed that the target user has cognitive impairment.

[0104] In one example, an embodiment of the present invention collects EEG signals and ECG signals of subjects with normal and abnormal cognitive levels through EEG and ECG synchronous acquisition equipment, and based on these data, obtains the coupling characteristics of the brain of 30 control groups and 8 cognitive impairment groups with respect to the heart when the brain is active in the second preset frequency band.

[0105] Figure 4 A schematic diagram of a comparison of the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band provided by an embodiment of the present invention, wherein the ordinate is the value of the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band, and the abscissa corresponds to the control group and the cognitive impairment group, such as Figure 4 As shown, there are significant differences in the coupling characteristics of the control group and the cognitive impairment group with respect to the heart when the brains are active in the second preset frequency band. In this embodiment, -0.16 is taken as the classification threshold to distinguish between the control group and the cognitive impairment group with an accuracy rate of 95%.

[0106] In summary, the embodiments of the present invention further improve the signal quality and reduce the analysis error by filtering, re-referencing and removing artifacts from the EEG signals; and obtain the first time-varying regulation coupling strength and the second time-varying regulation coupling strength through the constructed heartbeat model, which effectively quantifies the dynamic regulation process of the brain on cardiac activity and converts the abstract brain-heart interaction into obtainable physiological data; utilizes the first power information of the preprocessed EEG signal in the first preset frequency band and the second power information of the preprocessed EEG signal in the second preset frequency band, as well as the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, to obtain the high-low frequency ratio coupling characteristics of the brain to the heart and the coupling characteristics of the brain to the heart when it is active in the second preset frequency band, thereby characterizing the functional relationship between the brain and the heart from multiple dimensions, so that these characteristics can sensitively reflect changes in the cognitive state of the brain. These features constitute the first coupling characteristic information of the brain to the heart corresponding to the target user. This information breaks through the limitations of traditional single signal analysis, and provides a more comprehensive and accurate objective basis for cognitive level assessment through cross-validation of EEG and ECG signals. It significantly improves the reliability and accuracy of early screening and dynamic monitoring of cognitive impairment, and provides innovative technical means for the diagnosis and intervention of related diseases.

[0107] Figure 5 A flowchart of another brain-heart coupling feature extraction method provided by an embodiment of the present invention is described in detail as follows: Step 701, obtaining the EEG signal and ECG signal of the target user, and obtaining the heart rate variability data of the target user based on the ECG signal, and obtaining the power spectrum density information of the target user based on the EEG signal.

[0108] Exemplarily, this step refers to step 201 and will not be described in detail.

[0109] Step 702: Short-time Fourier transform is used to integrate the heart rate variability data in the low frequency band and the high frequency band to obtain low-frequency power information of the heart rate variability data in the low frequency band and high-frequency power information of the heart rate variability data in the high frequency band.

[0110] Among them, the low frequency band is a frequency band that reflects the comprehensive regulatory effect of the sympathetic nerves and parasympathetic nerves in the autonomic nervous system, and the high frequency band is a frequency band that reflects the regulatory effect of the parasympathetic nerves on cardiac activity.

[0111] Exemplarily, after obtaining the RR interval signal, this embodiment applies spline interpolation to resample the obtained RR sequence signal to ensure that the data is distributed at a constant frequency of 4 Hz (i.e., one point every 0.25 seconds). After the resampling is completed, STFT is used to perform integral analysis on the two frequency bands (LF (0.04 Hz-0.15 Hz), HF (0.15 Hz-0.4 Hz)) of the RR sequence to obtain the power spectrum density in the two frequency bands. Among them, LF represents the comprehensive regulation frequency range, and HF represents the regulation frequency range of the parasympathetic nerves. Among them, the sympathetic nerves and parasympathetic nerves are important indicators of the activity of the autonomic nervous system.

[0112] The integration processing of the heart rate variability data in this embodiment refers to step 201 and will not be described in detail.

[0113] In one example, before step 703, the method further includes: This embodiment uses an adaptive Markov process model to generate a synthetic EEG signal sequence. The model simulates the regulatory effect of the heart on the brain. The specific process is as follows: The EEG signal EEG(t) is represented as the superposition of multiple frequency components. The specific formula is:

[0114] Indicates at time Time, frequency The power of is the corresponding phase parameter.

[0115] power The estimation of follows an autoregressive model:

[0116] in, is the frequency at time t The power of the EEG signal on is the frequency of the time window before time t The power of the EEG signal on is a constant coefficient, Indicates the modulation of the brain's specific frequency band components by the heart, .

[0117] This embodiment determines the modulation information of the heart for the brain based on the autoregressive model and the power density information of the target user. .

[0118] Step 703, based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, determine the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain, the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain, and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain.

[0119] In one example, the modulation information of the heart on the brain includes the modulation of the heart on the first preset frequency band component of the brain and the modulation of the heart on the second preset frequency band component of the brain; step 303 includes the following steps: The high-frequency power of the heart rate variability data at the third preset moment in the high-frequency band is determined according to the high-frequency power information, and the low-frequency power of the heart rate variability data at the third preset moment in the low-frequency band is determined according to the low-frequency power information.

[0120] The ratio between the modulation of the heart on the first preset frequency band component of the brain and the high-frequency power at the third preset moment is used as the coupling coefficient of the heart's high-frequency activity to the first preset frequency band of the brain.

[0121] The ratio between the modulation of the heart on the second preset frequency band component of the brain and the high-frequency power at the third preset moment is used as the coupling coefficient of the heart's high-frequency activity to the second preset frequency band of the brain.

[0122] The ratio between the modulation of the heart on the first preset frequency band component of the brain and the low-frequency power at the third preset moment is used as the coupling coefficient of the heart's low-frequency activity to the first preset frequency band of the brain.

[0123] The first preset time, the second preset time and the third preset time are the same or different.

[0124] Exemplarily, this embodiment uses the modulation information of the heart to the brain , low-frequency power information of heart rate variability data in the low-frequency band High-frequency power information of heart rate variability data in the high-frequency band , the coupling coefficient of the heart to the brain is obtained to reflect the intensity of the heart's regulation of the brain:

[0125]

[0126] in, is the low-frequency power information of the heart rate variability data, It is the high-frequency power information of heart rate variability data. is the coupling coefficient of the heart's low-frequency activity to the brain. is a positive value, indicating that as the low-frequency activity of the heart increases, the brain activity increases linearly, and vice versa. The level of indicates the strength of the regulation of the heart's low-frequency activity on brain activity. is the coupling coefficient of the high-frequency activity of the heart to the brain. It is a positive value. It shows that as the high-frequency activity of the heart increases, the brain activity increases linearly, and vice versa. The level of the heart rate indicates the strength of the heart's high-frequency regulation of brain activity.

[0127] In one example, the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain, the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain, and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain.

[0128] Thus, the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain at the third preset moment can be obtained as:

[0129] in, represents the third preset time, is the modulation of the first preset frequency band component of the brain by the heart at the third preset moment, is the high frequency power at the third preset moment, Coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain.

[0130]

[0131] in, is the modulation of the second preset frequency band component of the brain by the heart at the third preset moment, The coupling coefficient of the second preset frequency band of the high frequency activity of the heart to the brain.

[0132]

[0133] in, is the modulation of the first preset frequency band component of the brain by the heart at the third preset moment, is the low-frequency power corresponding to the heart rate variability data at the third preset moment, It is the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain at the third preset moment.

[0134] Step 704, taking the ratio of the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain and the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain as the low-high frequency ratio feature of the heart to the brain, to evaluate the cognitive level of the target user.

[0135] In an example, the low-high frequency ratio feature of the heart to the brain can be expressed as:

[0136] Right now .

[0137] in, The third preset moment is the low to high frequency ratio characteristic of the heart to the brain.

[0138] In one example, the low-high frequency ratio feature is compared with the low-high frequency ratio features corresponding to people with normal cognition or abnormal cognition, and the cognitive level of the target user is evaluated based on their similarities or differences. This will not be elaborated here.

[0139] Exemplarily, the high-frequency activity of the heart will have different degrees of influence on different frequency bands of the brain, which is reflected by the coupling coefficient. When the target user's cognitive level is high, the brain's advanced cognitive functions are active, the activity of the second preset frequency band is enhanced, and the coupling effect of the high-frequency activity of the heart on it is relatively strong, while the coupling effect on the first preset frequency band is relatively weak, so that the low-high frequency ratio feature is within a certain range. When the cognitive level decreases, such as cognitive impairment, fatigue or mental illness, the functional state of the brain changes, the activity of the first preset frequency band may be relatively enhanced, and the coupling effect of the high-frequency activity of the heart on it will also increase accordingly, resulting in changes in the low-high frequency ratio feature. Therefore, this embodiment can provide an important basis for evaluating the cognitive level of the target user by analyzing the ratio of the coupling coefficients of the high-frequency activity of the heart to different frequency bands of the brain, that is, the low-high frequency ratio feature of the heart to the brain.

[0140] In one example, an embodiment of the present invention collects EEG signals and ECG signals of subjects with normal and abnormal cognitive levels through EEG and ECG synchronous acquisition equipment, and based on these data, obtains the low-to-high frequency ratio characteristics of the heart to the brain for 30 control groups and 8 cognitive impairment groups.

[0141] Figure 6 A schematic diagram for comparing low to high frequency ratio characteristics provided by an embodiment of the present invention, Figure 6 The horizontal axis corresponds to the control group and the cognitive impairment group, and the vertical axis is the value of the low-high frequency ratio feature of the heart to the brain, such as Figure 6 As shown, there are significant differences in the low-to-high frequency ratio features between the control group and the cognitive impairment group. In this embodiment, 5.63 is taken as the classification threshold to distinguish the control group from the cognitive impairment group, which can achieve an accuracy rate of 95%.

[0142] Step 705, taking the ratio of the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain as the mixing ratio feature of the heart to the brain, to evaluate the cognitive level of the target user.

[0143] Among them, the low-high frequency ratio characteristics of the heart to the brain and the mixing ratio characteristics of the heart to the brain are the second coupling characteristic information of the heart to the brain corresponding to the target user.

[0144] In an example, the mixing ratio feature of the heart to the brain can be expressed as:

[0145] in: It is the mixing frequency ratio characteristic of the heart to the brain at the third preset moment.

[0146] In one example, the mixing ratio feature is compared with the mixing ratio features corresponding to people with normal cognition or abnormal cognition, and the cognitive level of the target user is evaluated based on their similarities.

[0147] Exemplarily, the low-frequency and high-frequency activities of the heart have different effects on different frequency bands of the brain. When the target user is in a good cognitive state, the high-level cognitive function area of ​​the brain (corresponding to the second preset frequency band) is active, the coupling effect of the high-frequency activity of the heart on it is enhanced, and the coupling of the low-frequency activity of the heart to the first preset frequency band of the brain is relatively stable, so that the mixing ratio feature presents a specific range. When the user's cognitive level changes, such as cognitive decline, inattention, or certain neurological diseases, the activity patterns of different frequency bands of the brain will change, and the coupling coefficients of the low-frequency and high-frequency activities of the heart to the corresponding brain frequency bands will also change accordingly, resulting in deviations in the mixing ratio characteristics. Therefore, by analyzing the ratio of the coupling coefficients of the high-frequency activity of the heart to the second preset frequency band of the brain and the low-frequency activity of the heart to the first preset frequency band of the brain, that is, the mixing ratio characteristics of the heart to the brain, the cognitive level of the target user can be effectively evaluated.

[0148] In one example, an embodiment of the present invention collects EEG signals and ECG signals of subjects with normal and abnormal cognitive levels through EEG and ECG synchronous acquisition equipment, and based on these data, obtains the mixing ratio characteristics of the heart to the brain for 30 control groups and 8 cognitive impairment groups.

[0149] Figure 7 A schematic diagram for comparing mixing ratio characteristics provided by an embodiment of the present invention, Figure 7 The horizontal axis corresponds to the control group and the cognitive impairment group, and the vertical axis is the value of the mixing ratio feature, such as Figure 7As shown, there are significant differences in the mixing ratio features between the control group and the cognitive impairment group. In this embodiment, 0.21 is taken as the classification threshold to distinguish the control group from the cognitive impairment group, which can achieve an accuracy rate of 95%.

[0150] In summary, the embodiment of the present invention uses short-time Fourier transform to obtain low-frequency power information of heart rate variability data in a low-frequency band and high-frequency power information of heart rate variability data in a high-frequency band, thereby realizing a refined frequency domain analysis of the state of cardiac autonomic nervous activity, and effectively separating the low-frequency components dominated by the sympathetic nerves from the high-frequency components dominated by the parasympathetic nerves; and further, based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain, the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain, and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain are determined, and the dynamic interaction intensity between cardiac activity and different functional states of the brain is quantified from multiple dimensions, breaking through the limitation that traditional single signal analysis cannot capture bidirectional physiological associations; thereby, based on this, the low-high frequency ratio characteristics of the heart to the brain and the mixing ratio characteristics of the heart to the brain are obtained to evaluate the cognitive level of the target user, and a cognitive level evaluation system with the heart-brain interaction relationship as the core is constructed. This system significantly improves the objectivity and accuracy of cognitive level assessment by converting the coupling characteristics of cardiac autonomic nervous activity and brain functional state into quantifiable physiological indicators, and achieves over 90% accuracy in distinguishing between cognitively normal and cognitively impaired groups in clinical experiments. At the same time, this method has dynamic monitoring and real-time feedback capabilities, which can timely capture subtle changes in cognitive state, providing a new technical path for early warning of neurodegenerative diseases such as Alzheimer's disease and evaluation of rehabilitation treatment effects, and effectively filling the gaps in existing cognitive assessment technologies in terms of physiological mechanism relevance and clinical practicality.

[0151] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0152] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0153] Figure 8 The schematic diagram of the structure of the brain-heart coupling feature extraction device provided by the embodiment of the present invention only shows the part related to the embodiment of the present invention for the convenience of explanation, which is described in detail as follows: like Figure 8 As shown, the brain-heart coupling feature extraction device includes: The first processing unit 111 acquires the EEG signal and the ECG signal of the target user, obtains the heart rate variability data of the target user based on the ECG signal, and obtains the power spectrum density information of the target user based on the EEG signal.

[0154] The second processing unit 112 is used to determine a first time-varying regulatory coupling strength of the brain for the low-frequency components of the cardiac activity and a second time-varying regulatory coupling strength of the brain for the high-frequency components of the cardiac activity based on the heart rate variability data.

[0155] The third processing unit 113 is used to obtain the first coupling characteristic information of the brain to the heart corresponding to the target user according to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

[0156] In a possible implementation, the power spectrum density information includes first power information of the preprocessed EEG signal in a first preset frequency band and second power information of the preprocessed EEG signal in a second preset frequency band; wherein the first preset frequency band is a frequency band associated with a low arousal state of the brain, and the second preset frequency band is a frequency band associated with a high-level neural function of the brain; the first processing unit 111 is specifically used to: The EEG signal is preprocessed to obtain a preprocessed EEG signal; wherein the preprocessing includes filtering processing, re-reference processing and artifact removal processing.

[0157] The preprocessed EEG signal is integrated in the first preset frequency band and the second preset frequency band using short-time Fourier transform to obtain first power information of the preprocessed EEG signal in the first preset frequency band and second power information of the preprocessed EEG signal in the second preset frequency band.

[0158] In a possible implementation, the first coupling feature information includes a high-low frequency ratio coupling feature of the brain to the heart and a coupling feature of the brain to the heart when the brain is active in the second preset frequency band; the third processing unit 113 is specifically configured to: Based on the first power information, the second power information and the first time-varying regulation coupling strength, the high-to-low frequency ratio coupling characteristics of the brain to the heart are obtained; wherein the high-to-low frequency ratio coupling characteristics characterize the relative relationship between the regulation intensity of the brain on heart activity when the brain is active in the first preset frequency band and the second preset frequency band, and the upper frequency limit in the first preset frequency band is less than the lower frequency limit in the second preset frequency band.

[0159] According to the second power information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band are obtained.

[0160] In a possible implementation, the third processing unit 113 is specifically configured to: Determine that the value of the first time-varying regulation coupling strength at the first preset moment is the first regulation coupling strength, and determine based on the first power information that in a time window before the first preset moment, the power of the preprocessed EEG signal in a first preset frequency band is the first power, and determine based on the second power information that in a time window before the first preset moment, the power of the preprocessed EEG signal in a second preset frequency band is the second power.

[0161] The ratio between the first regulated coupling intensity and the first power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band.

[0162] The ratio between the first regulated coupling intensity and the second power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band.

[0163] The ratio of the coupling coefficient of the brain to the cardiac low frequency when the brain is active in the second preset frequency band to the coupling coefficient of the brain to the cardiac low frequency when the brain is active in the first preset frequency band is used as the high-low frequency ratio coupling feature.

[0164] In a possible implementation, the third processing unit 113 is further specifically configured to: Determine that the value of the first time-varying regulation coupling strength at the second preset moment is the second regulation coupling strength, and determine that the value of the second time-varying regulation coupling strength at the second preset moment is the third regulation coupling strength; and based on the second power information, determine that in the time window before the second preset moment, the power of the preprocessed EEG signal in the second preset frequency band is the fourth power.

[0165] The ratio between the second regulated coupling intensity and the fourth power is used as the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band.

[0166] The ratio between the third regulated coupling intensity and the fourth power is used as the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band.

[0167] The ratio between the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band and the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band is used as the coupling characteristic of the brain to the heart when the brain is active in the second preset frequency band.

[0168] In a possible implementation, the second processing unit 112 is specifically configured to: A heartbeat model corresponding to the heart rate variability data is constructed; wherein the heartbeat model is composed of an average heart rate term and an autonomic nervous activity term, and the autonomic nervous activity term is used to simulate the regulation of the heart by the autonomic nervous system.

[0169] Based on the Poincare map features corresponding to the heart rate variability data, the first time-varying regulatory coupling strength of the brain for the low-frequency components of cardiac activity and the second time-varying regulatory coupling strength of the brain for the high-frequency components of cardiac activity in the autonomic nervous activity item are calculated.

[0170] In a possible implementation, after the first processing unit 111, the device further includes: a fourth processing unit, specifically configured to: Short-time Fourier transform is used to integrate the heart rate variability data in the low-frequency band and the high-frequency band, respectively, to obtain the low-frequency power information of the heart rate variability data in the low-frequency band and the high-frequency power information of the heart rate variability data in the high-frequency band; wherein, the low-frequency band is a frequency band reflecting the comprehensive regulatory effect of the sympathetic nerves and the parasympathetic nerves in the autonomic nervous system, and the high-frequency band is a frequency band reflecting the regulatory effect of the parasympathetic nerves on cardiac activity.

[0171] Based on the low-frequency power information, high-frequency power information and the modulation information of the heart to the brain, the second coupling characteristic information of the heart to the brain corresponding to the target user is obtained; wherein the modulation information of the heart to the brain is determined based on the power density information of the target user, and the second coupling characteristic information is used to evaluate the cognitive level of the target user.

[0172] In a possible implementation, the second coupling feature information includes a low-high frequency ratio feature of the heart to the brain and a mixing frequency ratio feature of the heart to the brain; the fourth processing unit is further configured to: Based on the low-frequency power information, high-frequency power information and the modulation information of the heart to the brain, the coupling coefficient of the heart's high-frequency activity to the brain's first preset frequency band, the coupling coefficient of the heart's high-frequency activity to the brain's second preset frequency band, and the coupling coefficient of the heart's low-frequency activity to the brain's first preset frequency band are determined.

[0173] The ratio between the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain and the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain is used as the low-high frequency ratio feature of the heart to the brain.

[0174] The ratio between the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain is used as the mixing ratio characteristic of the heart to the brain.

[0175] Fig. 9 Schematic diagram of an electronic device provided by an embodiment of the present invention. Fig. 9 As shown, the electronic device of this embodiment includes: a processor 20 and a memory 21. The memory 21 stores a computer program 22. When the processor 20 executes the computer program 22, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 20 executes the computer program 22, the functions of each unit in the above-mentioned device embodiments are implemented.

[0176] Exemplarily, the computer program 22 may be divided into one or more modules / units, which are stored in the memory 21 and executed by the processor 20 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 22 in the electronic device.

[0177] The electronic device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will appreciate that Fig. 9 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0178] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0179] The memory 21 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. The memory 21 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Furthermore, the memory 21 may also include both an internal storage unit of the electronic device and an external storage device. The memory 21 is used to store the computer program 22 and other programs and data required by the electronic device. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0180] For the convenience and simplicity of description, only the division of the above functional modules / units is used as an example for illustration. In actual applications, the above functions can be assigned to different functional modules / units as needed. The above modules / units can be implemented in the form of hardware, software, or a combination of hardware and software.

[0181] The embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0182] The embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0183] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0184] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. If there is no special explanation or logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form a new embodiment according to their internal logical relationship.

[0185] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those 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. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A brain-heart coupling feature extraction method, characterized in that: The method comprises: Acquire an EEG signal and an ECG signal of a target user, and obtain heart rate variability data of the target user based on the ECG signal, and obtain power spectrum density information of the target user based on the EEG signal; Based on the heart rate variability data, determining a first time-varying regulatory coupling strength of the brain for the low-frequency component of the heart activity and a second time-varying regulatory coupling strength of the brain for the high-frequency component of the heart activity; According to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the first coupling characteristic information of the brain to the heart corresponding to the target user is obtained; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

2. The brain-heart coupling feature extraction method according to claim 1, characterized in that: The power spectrum density information includes first power information of the preprocessed EEG signal in a first preset frequency band and second power information of the preprocessed EEG signal in a second preset frequency band; wherein the first preset frequency band is a frequency band associated with a low arousal state of the brain, and the second preset frequency band is a frequency band associated with a high-level neural function of the brain; The obtaining the power spectrum density information of the target user based on the EEG signal includes: Preprocessing the EEG signal to obtain a preprocessed EEG signal; wherein the preprocessing includes filtering, re-referencing and artifact removal; The preprocessed EEG signal is integrated in the first preset frequency band and the second preset frequency band using short-time Fourier transform to obtain first power information of the preprocessed EEG signal in the first preset frequency band and second power information of the preprocessed EEG signal in the second preset frequency band.

3. The brain-heart coupling feature extraction method according to claim 2, characterized in that: The first coupling characteristic information includes a high-low frequency ratio coupling characteristic of the brain to the heart and a coupling characteristic of the brain to the heart when the brain is active in a second preset frequency band; The obtaining, according to the power spectrum density information, the first time-varying regulation coupling strength, and the second time-varying regulation coupling strength, first coupling characteristic information of the brain to the heart corresponding to the target user includes: According to the first power information, the second power information and the first time-varying regulation coupling strength, a high-to-low frequency ratio coupling feature of the brain on the heart is obtained; wherein the high-to-low frequency ratio coupling feature represents a relative relationship between the regulation strengths of the brain on the heart activity when the brain is active in the first preset frequency band and the second preset frequency band, and the upper frequency limit in the first preset frequency band is less than the lower frequency limit in the second preset frequency band; According to the second power information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, the coupling characteristics of the brain to the heart when the brain is active in the second preset frequency band are obtained.

4. The brain-heart coupling feature extraction method according to claim 3, characterized in that: The obtaining, according to the first power information, the second power information and the first time-varying regulation coupling strength, a high-low frequency ratio coupling feature of the brain to the heart includes: Determine that the value of the first time-varying regulation coupling strength at a first preset moment is a first regulation coupling strength, and determine, based on the first power information, that the power of the preprocessed EEG signal in the first preset frequency band in a time window before the first preset moment is a first power, and determine, based on the second power information, that the power of the preprocessed EEG signal in the second preset frequency band in a time window before the first preset moment is a second power; The ratio between the first regulation coupling strength and the first power is used as a coupling coefficient of the brain to the cardiac low frequency when the brain is active in the first preset frequency band; The ratio between the first regulation coupling strength and the second power is used as a coupling coefficient of the brain to the cardiac low frequency when the brain is active in the second preset frequency band; The ratio of the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band to the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the first preset frequency band is used as the high-low frequency ratio coupling feature.

5. The brain-heart coupling feature extraction method according to claim 3, characterized in that: The obtaining, according to the second power information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength, a coupling characteristic of the brain to the heart when the brain is active in the second preset frequency band includes: Determine that the value of the first time-varying regulation coupling strength at the second preset moment is the second regulation coupling strength, and determine that the value of the second time-varying regulation coupling strength at the second preset moment is the third regulation coupling strength; and determine, based on the second power information, that in a time window before the second preset moment, the power of the preprocessed EEG signal in the second preset frequency band is the fourth power; Using the ratio between the second regulated coupling strength and the fourth power as the coupling coefficient of the brain to the cardiac low frequency when the brain is active in the second preset frequency band; Using the ratio between the third regulated coupling strength and the fourth power as the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band; The ratio between the coupling coefficient of the brain to the low frequency of the heart when the brain is active in the second preset frequency band and the coupling coefficient of the brain to the high frequency of the heart when the brain is active in the second preset frequency band is used as the coupling characteristic of the brain to the heart when the brain is active in the second preset frequency band.

6. The brain-heart coupling feature extraction method according to any one of claims 1 to 5, characterized in that: The determining, based on the heart rate variability data, a first time-varying regulation coupling strength of the brain for the low-frequency component of the heart activity and a second time-varying regulation coupling strength of the brain for the high-frequency component of the heart activity comprises: Constructing a heartbeat model corresponding to the heart rate variability data; wherein the heartbeat model is composed of an average heart rate term and an autonomic nerve activity term, and the autonomic nerve activity term is used to simulate the regulation of the heart by the autonomic nervous system; Based on the Poincare map features corresponding to the heart rate variability data, the first time-varying regulatory coupling strength of the brain for the low-frequency components of cardiac activity and the second time-varying regulatory coupling strength of the brain for the high-frequency components of cardiac activity in the autonomic nervous activity item are calculated.

7. The brain-heart coupling feature extraction method according to any one of claims 1 to 5, characterized in that: After obtaining the heart rate variability data of the target user based on the electrocardiogram signal and obtaining the power spectrum density information of the target user based on the electroencephalogram signal, the method further includes: The heart rate variability data is integrated in a low frequency band and a high frequency band by using short-time Fourier transform to obtain low frequency power information of the heart rate variability data in the low frequency band and high frequency power information of the heart rate variability data in the high frequency band; wherein the low frequency band is a frequency band reflecting the comprehensive regulatory effect of the sympathetic nerves and the parasympathetic nerves in the autonomic nervous system, and the high frequency band is a frequency band reflecting the regulatory effect of the parasympathetic nerves on the cardiac activity; Based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, second coupling characteristic information of the heart to the brain corresponding to the target user is obtained; wherein the modulation information of the heart to the brain is determined based on the power density information of the target user, and the second coupling characteristic information is used to evaluate the cognitive level of the target user.

8. The brain-heart coupling feature extraction method according to claim 7, characterized in that: The second coupling characteristic information includes a low-high frequency ratio characteristic of the heart to the brain and a mixing frequency ratio characteristic of the heart to the brain; The obtaining, based on the low-frequency power information, the high-frequency power information and the modulation information of the heart to the brain, second coupling characteristic information of the heart to the brain corresponding to the target user includes: Determine, according to the low-frequency power information, the high-frequency power information, and the modulation information of the heart to the brain, a coupling coefficient of the high-frequency activity of the heart to a first preset frequency band of the brain, a coupling coefficient of the high-frequency activity of the heart to a second preset frequency band of the brain, and a coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain; The ratio between the coupling coefficient of the high-frequency activity of the heart to the first preset frequency band of the brain and the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain is used as a low-high frequency ratio feature of the heart to the brain; The ratio between the coupling coefficient of the high-frequency activity of the heart to the second preset frequency band of the brain and the coupling coefficient of the low-frequency activity of the heart to the first preset frequency band of the brain is used as the mixing ratio characteristic of the heart to the brain.

9. A brain-heart coupling feature extraction device, characterized in that: The device comprises: A first processing unit is used to obtain an EEG signal and an ECG signal of a target user, and obtain heart rate variability data of the target user based on the ECG signal, and obtain power spectrum density information of the target user based on the EEG signal; A second processing unit is used to determine a first time-varying regulatory coupling strength of the brain for the low-frequency component of the cardiac activity and a second time-varying regulatory coupling strength of the brain for the high-frequency component of the cardiac activity based on the heart rate variability data; The third processing unit is used to obtain the first coupling characteristic information of the brain to the heart corresponding to the target user according to the power spectral density information, the first time-varying regulation coupling strength and the second time-varying regulation coupling strength; wherein the first coupling characteristic information is used to evaluate the cognitive level of the target user.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the brain-heart coupling feature extraction method according to any one of claims 1 to 8.

Images