A rehabilitation effect evaluation method and system based on electroencephalogram and electromyogram signals

Abstract

The present application relates to a kind of rehabilitation effect evaluation method and system based on electroencephalogram electromyogram signal, belong to electroencephalogram electromyogram signal analysis processing field.Method includes: the multi-channel electroencephalogram signal and multi-channel electromyogram signal of rest period and imagination period are collected and analyzed, obtain the rehabilitation effect evaluation index based on electroencephalogram signal and based on electromyogram signal;The multi-channel electroencephalogram signal and multi-channel electromyogram signal of rest period and imagination period are fused, and brain muscle transmission information effectiveness analysis is carried out, obtain the rehabilitation effect evaluation index based on electroencephalogram electromyogram signal;According to rehabilitation effect evaluation index, the rehabilitation state and effect of patient are evaluated, obtain rehabilitation state and effect evaluation result.The present application method is processed by the multi-channel electroencephalogram electromyogram signal of rest period and imagination period, objective quantification analysis is carried out to the whole closed-loop neural circuit of motor function automatically, so that the evaluation efficiency is higher, and the rehabilitation state and rehabilitation effect evaluated are more comprehensive, accurate.

Description

Technical Field

[0001] This invention relates to the field of electroencephalogram (EEG) and electromyogram (EMG) signal analysis and processing technology, and in particular to a method and system for evaluating rehabilitation effects based on EEG and EMG signals. Background Technology

[0002] The number of stroke patients is large and growing rapidly, and the recovery from sequelae is slow, seriously threatening patients' physical and mental health. Current rehabilitation methods for stroke patients are relatively traditional, relying heavily on passive, muscle-stretching exercises or stimulation to maintain or enhance muscle function; these methods also require a high level of expertise and full-time guidance and supervision from a treating physician.

[0003] In recent years, novel brain-computer interface (BCI)-based rehabilitation devices have begun to be applied clinically. For example, Ipsihand, certified by the FDA in 2021, uses electroencephalography (EEG) to recognize patients' motor intentions and drive assistive devices to complete their execution. Chinese companies Haitian Intelligent and Shenzhen Ruihan have also released related devices for clinical rehabilitation of stroke patients. These devices employ active training to reconstruct neural motor circuits, not only improving muscle function but also assisting in reshaping brain function, thus providing fundamental rehabilitation. However, this type of rehabilitation is still underdeveloped. The evaluation of rehabilitation effects and the formulation of rehabilitation plans require physicians to rely on years of clinical experience and apply corresponding quantitative scoring scales for subjective evaluation. Limited by the knowledge system and experience level of rehabilitation treatment, evaluation results show individual differences, lacking objective quantitative evaluation methods and standards. This significantly reduces the effectiveness of clinical rehabilitation and even poses safety risks.

[0004] The generation of movement involves a closed loop from the brain's induction of motor intention to the control of muscles to execute the movement and feedback. A problem in any link of this loop will lead to the failure of motor execution. Currently, there are patents that indirectly assess patients' rehabilitation status using methods such as brain-muscle coherence, muscle ability, and brain topography / region mapping. However, these methods are limited to assessing the function of two terminals—the brain regions or muscles related to movement—to indirectly reflect the patient's rehabilitation status. They lack a complete and systematic evaluation of information transmission between the brain's intention and the muscle execution unit, the motor feedback loop, muscle synergy, and the brain's ability to respond to movement, making the evaluation of rehabilitation status incomplete. Summary of the Invention

[0005] To address or at least alleviate the aforementioned problems, this invention proposes a rehabilitation effect evaluation method and system based on electroencephalogram (EEG) and electromyogram (EMG) signals. This method can automatically and objectively quantify the entire closed-loop neural circuit of motor function through the processing of EEG and EMG signals, resulting in higher evaluation efficiency and a more comprehensive and accurate assessment of rehabilitation status and effects. This provides a strong basis for developing appropriate and reasonable rehabilitation plans.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A method for assessing rehabilitation effects based on electroencephalogram (EEG) and electromyogram (EMG) signals, comprising:

[0008] Collect multichannel EEG and multichannel EMG signals during resting and imagination periods;

[0009] The multi-channel EEG signals from the resting and imagination periods were analyzed and processed to obtain rehabilitation effect evaluation indicators based on EEG signals. The rehabilitation effect evaluation indicators based on EEG signals include the EEG signal energy change index and three brain function evaluation indicators.

[0010] The multi-channel electromyography (EMG) signals from the resting and visualization periods are analyzed and processed to obtain rehabilitation effect evaluation indicators based on EMG signals. The rehabilitation effect evaluation indicators based on EMG signals include EMG signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level.

[0011] By integrating multi-channel EEG and multi-channel EMG signals from the resting and imagination periods, an effectiveness analysis of brain-muscle transmission information is performed to obtain rehabilitation effect evaluation indicators based on EEG and EMG signals. These rehabilitation effect evaluation indicators based on EEG and EMG signals include bidirectional EEG-EMG transmission entropy and transmission lag time.

[0012] The rehabilitation status and effect of the patient are evaluated based on the rehabilitation effect evaluation indicators based on electroencephalogram (EEG) signals, the rehabilitation effect evaluation indicators based on electromyogram (EMG) signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals, and the rehabilitation status and effect evaluation results are obtained.

[0013] Optionally, the acquisition of multi-channel EEG and multi-channel EMG signals during resting and imagination periods specifically includes:

[0014] When the patient is at rest, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the resting period.

[0015] When the patient is in a state of motor imagination, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the imagination period.

[0016] When the patient is at rest, multi-channel electromyography (EMG) signals from the patient's upper limb and its extremities or lower limb and its extremities are collected to obtain multi-channel EMG signals during the resting period.

[0017] When the patient is in a state of motor imagery, multi-channel electromyographic signals from the patient's upper limbs and their extremities or lower limbs and their extremities are collected to obtain multi-channel electromyographic signals during the imagery period.

[0018] Optionally, the analysis and processing of multi-channel EEG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indicators based on EEG signals specifically includes:

[0019] Energy analysis was performed on the multichannel EEG signals during the resting and imagination periods to obtain the energy change index of EEG signals before and after the execution of the imagined movement;

[0020] Brain functional connectivity analysis was performed on the multichannel EEG signals during the resting and imagination periods to obtain three brain function evaluation indicators: spectral coherence, transfer entropy, and Granger causality analysis.

[0021] Optionally, the analysis and processing of multi-channel electromyographic signals during the resting and visualization periods to obtain rehabilitation effect evaluation indicators based on electromyographic signals specifically includes:

[0022] Time-domain and frequency-domain analyses were performed on the multi-channel electromyographic signals during the resting and imaginary periods to obtain the electromyographic signal energy change index, muscle tremor intensity, and muscle control ability before and after the execution of the imagined movement.

[0023] Muscle coordination pattern analysis was performed on the multichannel electromyographic signals during the resting and imagination periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels.

[0024] Optionally, the step of evaluating the patient's rehabilitation status and effect based on the rehabilitation effect evaluation indicators based on electroencephalogram (EEG) signals, the rehabilitation effect evaluation indicators based on electromyography (EMG) signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals to obtain the rehabilitation status and effect evaluation results specifically includes:

[0025] Based on the rehabilitation effect evaluation indicators based on EEG signals, the rehabilitation effect evaluation indicators based on EMG signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals, the patient's rehabilitation status and effect are evaluated using a threshold determination method or a model training method to obtain the rehabilitation status and effect evaluation results; the rehabilitation status and effect evaluation results are divided into primary, intermediate, and advanced levels from poor to excellent.

[0026] A rehabilitation effect assessment system based on electroencephalogram (EEG) and electromyogram (EMG) signals, comprising:

[0027] A multi-channel physiological signal acquisition module is used to acquire multi-channel electroencephalogram (EEG) signals and multi-channel electromyogram (EMG) signals during resting and imagination periods.

[0028] The EEG signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EEG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EEG signals; the rehabilitation effect evaluation indexes based on EEG signals include the EEG signal energy change index and three brain function evaluation indicators.

[0029] The electromyography (EMG) signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EMG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EMG signals. The rehabilitation effect evaluation indexes based on EMG signals include EMG signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level.

[0030] The EEG / EMG signal rehabilitation effect evaluation index calculation module is used to integrate multi-channel EEG signals and multi-channel EMG signals from the resting and imagination periods to perform brain-muscle information transmission effectiveness analysis and obtain rehabilitation effect evaluation indexes based on EEG / EMG signals; the rehabilitation effect evaluation indexes based on EEG / EMG signals include bidirectional EEG / EMG transmission entropy and transmission lag time.

[0031] The rehabilitation status and effect assessment module is used to assess the patient's rehabilitation status and effect based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyography (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and obtain the rehabilitation status and effect assessment results.

[0032] Optionally, the multi-channel physiological signal acquisition module specifically includes:

[0033] The resting-time EEG signal acquisition unit is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a resting state, so as to obtain multi-channel EEG signals during the resting period.

[0034] The EEG signal acquisition unit for the imagination period is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a state of motor imagination, so as to obtain multi-channel EEG signals during the imagination period.

[0035] The resting period electromyography signal acquisition unit is used to acquire multi-channel electromyography signals from the patient's upper limb and its extremities or lower limb and its extremities when the patient is in a resting state, so as to obtain multi-channel electromyography signals during the resting period.

[0036] The imagery-time electromyography (EMG) signal acquisition unit is used to acquire multi-channel EMG signals from the patient's upper limbs and their extremities or lower limbs and their extremities when the patient is in a state of motor imagery, thus obtaining multi-channel EMG signals during the imagery time.

[0037] Optionally, the EEG signal rehabilitation effect evaluation index calculation module specifically includes:

[0038] The EEG signal energy change index calculation unit is used to perform energy analysis on the multi-channel EEG signals during the resting period and the imagination period to obtain the EEG signal energy change index before and after the execution of the imagined movement.

[0039] The brain function evaluation index calculation unit is used to perform brain function connectivity analysis on the multi-channel EEG signals during the resting and imagination periods to obtain three brain function evaluation indices; the three brain function evaluation indices include spectral coherence, transfer entropy, and Granger causality analysis.

[0040] Optionally, the electromyographic signal rehabilitation effect evaluation index calculation module specifically includes:

[0041] The time-frequency domain analysis and calculation unit is used to perform time-domain and frequency-domain analysis on the multi-channel electromyographic signals during the resting period and the imagination period to obtain the electromyographic signal energy change index, muscle tremor intensity and muscle control ability before and after the execution of the imagined movement.

[0042] The muscle coordination pattern analysis and calculation unit is used to perform muscle coordination pattern analysis on the multi-channel electromyographic signals during the resting and imaginary periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels.

[0043] Optionally, the rehabilitation status and effect assessment module specifically includes:

[0044] The rehabilitation status and effect assessment unit is used to assess the patient's rehabilitation status and effect using the threshold judgment method or model training method based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyogram (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and to obtain the rehabilitation status and effect assessment results; the rehabilitation status and effect assessment results are divided into primary, intermediate, and advanced levels from poor to excellent.

[0045] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0046] This invention provides a method and system for evaluating rehabilitation effects based on electroencephalogram (EEG) and electromyogram (EMG) signals. The method includes: acquiring multi-channel EEG signals and multi-channel EMG signals during resting and visualization periods; analyzing and processing the multi-channel EEG signals during the resting and visualization periods to obtain rehabilitation effect evaluation indicators based on EEG signals; the rehabilitation effect evaluation indicators based on EEG signals include an EEG signal energy change index and three brain function evaluation indicators; analyzing and processing the multi-channel EMG signals during the resting and visualization periods to obtain rehabilitation effect evaluation indicators based on EMG signals; the rehabilitation effect evaluation indicators based on EMG signals include an EMG signal energy change index, The method analyzes the intensity of muscle tremors, muscle control ability, muscle activation patterns, muscle activation levels, and muscle coordination levels. It integrates multi-channel EEG and EMG signals from resting and imaginary periods to analyze the effectiveness of brain-muscle transmission, obtaining rehabilitation effect evaluation indicators based on EEG and EMG signals. These indicators include bidirectional EEG-EMG transmission entropy and transmission lag time. The patient's rehabilitation status and effectiveness are assessed based on these three indicators, yielding the rehabilitation status and effectiveness evaluation results. This invention, through processing multi-channel EEG and EMG signals from resting and imaginary periods, automatically and objectively quantifies the entire closed-loop neural circuit of motor function, resulting in higher evaluation efficiency and a more comprehensive and accurate assessment of rehabilitation status and effectiveness, providing a strong basis for developing appropriate and reasonable rehabilitation plans. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a rehabilitation effect evaluation method based on electroencephalogram (EEG) and electromyogram (EMG) signals according to the present invention.

[0049] Figure 2 This is a schematic diagram of a rehabilitation effect evaluation framework based on electroencephalogram (EEG) and electromyogram (EMG) signals according to the present invention.

[0050] Figure 3 A schematic diagram of a multi-channel EEG and EMG signal acquisition experiment provided in an embodiment of the present invention for resting and imaginary periods. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] The purpose of this invention is to propose a method and system for evaluating rehabilitation effects based on electroencephalogram (EEG) and electromyogram (EMG) signals. This method can automatically and objectively quantify the entire closed-loop neural circuit of motor function by processing EEG and EMG signals, thereby improving the evaluation efficiency and making the evaluated rehabilitation status and effects more comprehensive and accurate, thus providing a strong basis for formulating appropriate and reasonable rehabilitation plans.

[0053] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] Figure 1 This is a flowchart of a rehabilitation effect evaluation method based on electroencephalogram (EEG) and electromyogram (EMG) signals according to the present invention. Figure 2 This is a schematic diagram of a rehabilitation effect evaluation framework based on electroencephalogram (EEG) and electromyogram (EMG) signals according to the present invention. See also... Figure 2 This invention aims to analyze motor intention and evaluate rehabilitation effects using EEG and EMG signals. The rehabilitation effect evaluation framework based on EEG and EMG signals mainly includes signal acquisition and transmission, signal preprocessing, signal processing and analysis, assessment and judgment of rehabilitation status and effects, and program customization. First, multi-channel EEG and multi-channel EMG signals are collected from the patient in both resting and imagined states. Then, based on human EEG and EMG signals, by analyzing the dynamic characteristics of limb movement clusters, neuromuscular electrical properties, and biodynamic characteristics, evaluation indicators for motor rehabilitation efficacy (including rehabilitation effect evaluation indicators based on EEG and EMG signals) are proposed. This objectively and quantitatively evaluates the rehabilitation status and effects of stroke patients, overcoming the limitations of traditional subjective scoring methods for rehabilitation effect evaluation, improving evaluation efficiency and accuracy. Therefore, reasonable rehabilitation training programs can be personalized and adjusted in a timely manner based on the rehabilitation status and effect evaluation results, improving the patient's clinical treatment experience and motor rehabilitation effects.

[0055] See Figure 1 This invention provides a method for evaluating rehabilitation effects based on electroencephalogram (EEG) and electromyogram (EMG) signals, specifically including:

[0056] Step 1: Collect multi-channel EEG and multi-channel EMG signals during resting and imagination periods.

[0057] The electroencephalogram (EEG) signals acquired in this invention can be multi-channel EEG signals from different regions of the motor cortex and somatosensory cortex of the patient's (or user's) brain, including at least two channels, C3 and C4. The electromyographic (EMG) signals acquired can be multi-channel EMG signals from different regions of the patient's (or user's) upper limb and its extremities, or lower limb and its extremities.

[0058] The data acquisition process includes both resting and visualization states. During both states, EEG and EMG signals are simultaneously acquired. The resting phase requires the user to be in a resting state for signal acquisition, while the visualization phase requires the user to be in a state of motor visualization for signal acquisition. The resting state refers to a state where all parts of the user's body are at rest, and the brain is not engaged in any imaginative activity; the motor visualization state refers to a state where the user's brain is engaged in imaginary activities of performing specific actions according to instructions, or an attempt to move the upper or lower limbs. For example... Figure 3 As shown, a total of N trials were conducted. Each trial included two resting periods and one imagination period. The length of the resting period was t1 and the length of the imagination period was t2. Multichannel EEG and multichannel EMG signals were collected during the resting and imagination periods.

[0059] Therefore, step 1, which involves acquiring multi-channel EEG and multi-channel EMG signals during resting and imagination periods, specifically includes:

[0060] When the patient is at rest, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the resting period.

[0061] When the patient is in a state of motor imagination, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the imagination period.

[0062] When the patient is at rest, multi-channel electromyography (EMG) signals from the patient's upper limb and its extremities or lower limb and its extremities are collected to obtain multi-channel EMG signals during the resting period.

[0063] When the patient is in a state of motor imagery, multi-channel electromyographic signals from the patient's upper limbs and their extremities or lower limbs and their extremities are collected to obtain multi-channel electromyographic signals during the imagery period.

[0064] Step 2: Analyze and process the multi-channel EEG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indicators based on EEG signals.

[0065] The rehabilitation effect evaluation index calculated by this invention based on electroencephalogram (EEG) signals includes the EEG signal energy change index and three brain function evaluation indicators; the three brain function evaluation indicators include spectral coherence, transfer entropy, and Granger causality analysis.

[0066] Step 2 involves analyzing and processing the multi-channel EEG signals from the resting and visualization periods to obtain rehabilitation effect evaluation indicators based on EEG signals, specifically including:

[0067] Step 2.1: Perform energy analysis on the multi-channel EEG signals during the resting and imaginary periods to obtain the energy change index of the EEG signals before and after the imaginary movement.

[0068] Step 2.1 involves energy analysis of the EEG signal to obtain the changes in signal energy intensity and region before and after the imagined movement, thereby outputting an energy change index.

[0069] Specifically, the energy intensity of an electroencephalogram (EEG) signal can be expressed as energy spectral density G. x (f) means that:

[0070] G x (f)≡|X(f)| 2 (1)

[0071] Where X(f) is the Fourier transform of the EEG signal x(t); x(t) is the EEG signal of a certain channel during the resting or imagination period t; G x (f) represents the corresponding EEG signal energy intensity.

[0072] The energy intensity of EEG signals in different channels can be calculated using formula (1) to obtain the energy intensity of EEG signals in different regions. The energy intensity of EEG signals in different regions during the resting and imagination periods is calculated separately to obtain the energy intensity difference and ratio between the two periods, which are used as the energy change index.

[0073] In this invention, different channels correspond to different regions in spatial location, and different states of the user (resting and imaginative states) correspond to different time periods in the time dimension. The energy intensity G of the EEG signal in different channels (regions) during different time periods (resting and imaginative periods) is calculated. x (f) The energy difference is obtained by subtracting the energy intensity of the resting period from the energy intensity of the imagination period, and the energy ratio is obtained by comparing the energy intensity of the resting period with the energy intensity of the imagination period. The calculated EEG signal energy difference and EEG signal energy ratio are used as the EEG signal energy change index before and after the execution of the imagination movement.

[0074] Step 2.2: Perform brain function connectivity analysis on the multi-channel EEG signals during the resting and imagination periods to obtain three brain function evaluation indicators.

[0075] This invention performs brain functional connectivity analysis on electroencephalogram (EEG) signals to obtain evaluation indicators such as spectral coherence, transfer entropy, and Granger causality, thus outputting three corresponding brain function evaluation indicators.

[0076] The formula for calculating spectral coherence is as follows:

[0077]

[0078] Where P(f) is the power spectrum; specifically, P xx (f) is the autopower spectrum of the EEG signal x, P yy (f) is the autopower spectrum of the EEG signal y, P xy (f) is the cross-power spectrum of EEG signal x and EEG signal y; C xy (f) is the spectral coherence coefficient.

[0079] The formula for calculating mutual information---transfer entropy is as follows:

[0080]

[0081] Where p is the probability; specifically, i is the number of signal segments used to calculate mutual information, p(x) is the probability of x, p(y) is the probability of y, and p(x,y) is the joint probability of x and y; MI xy This refers to mutual information, specifically the transfer of entropy.

[0082] The Granger causality analysis formula is as follows:

[0083]

[0084] Where V represents the mean square error of the expected value of the signal sequence; specifically, The error is the correlation between x and x itself. The error is the correlation between x and y with respect to x. Granger causality value.

[0085] The three brain function evaluation indicators calculated in this invention—spectral coherence, transfer entropy, and Granger causality analysis—analyze brain functional connectivity from the perspectives of spectral coherence, information correlation between signals, and causal relationship between signals, respectively, and can reflect the brain's ability to cope with event stimuli.

[0086] Step 3: Analyze and process the multi-channel electromyographic signals during the resting and imaginary periods to obtain rehabilitation effect evaluation indicators based on electromyographic signals.

[0087] The rehabilitation effect evaluation indicators calculated by this invention based on electromyographic signals include electromyographic signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level.

[0088] Step 3 involves analyzing and processing the multi-channel electromyographic signals from the resting and visualization periods to obtain rehabilitation effect evaluation indicators based on electromyographic signals, specifically including:

[0089] Step 3.1: Perform time-domain and frequency-domain analysis on the multi-channel electromyographic signals during the resting and imaginary periods to obtain the electromyographic signal energy change index, muscle tremor intensity, and muscle control ability before and after the execution of the imagined movement.

[0090] This invention, through time-domain and frequency-domain analysis of electromyographic signals, can obtain the energy change index, muscle twitching intensity, and muscle control ability of electromyographic signals before and after the execution of imagined movement. The specific process may include:

[0091] (3.1.1) The energy intensity of electromyographic signals can be expressed as energy spectral density G. y (f) means that:

[0092] G y (f)≡|Y(f)| 2 (5)

[0093] Where Y(f) is the Fourier transform of the electromyographic signal y(t); y(t) is the electromyographic signal of a certain channel during the resting or imagined time period t; G y (f) represents the corresponding electromyographic signal energy intensity.

[0094] The energy intensity of electromyographic signals in different channels can be calculated using formula (5) to obtain the energy intensity of electromyographic signals in different regions. The energy intensity of electromyographic signals in different regions during the resting and imagination periods is calculated separately to obtain the energy intensity difference and ratio between the two periods, which are used as the electromyographic signal energy change index. The calculation process of the electromyographic signal energy change index is the same as that of the electroencephalogram (EEG) signal, and will not be repeated here.

[0095] (3.1.2) Muscle twitching intensity can be understood as an assessment of muscle spasm, which can be obtained by calculating the root mean square of electromyography over a period of time:

[0096]

[0097] Where x i This represents the i-th electromyographic signal within a certain time period, during which a total of n electromyographic signals are collected; x rms This represents the root mean square, which is the intensity of muscle tremor during that time period.

[0098] (3.1.3) Muscle control ability is represented by the relative proportion of agonist and antagonist muscles used to complete the movement, i.e.:

[0099]

[0100] Where A-RMS represents the root mean square of the agonist muscle, which can be calculated using Equation (6) based on the electromyographic signals collected from the location of the agonist muscle; Ant-RMS represents the root mean square of the antagonist muscle, which can be calculated using Equation (6) based on the electromyographic signals collected from the location of the antagonist muscle; and A-ApA represents muscle control ability.

[0101] Step 3.2: Perform muscle coordination pattern analysis on the multi-channel electromyographic signals during the resting and imaginary periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels.

[0102] Step 3.2 aims to analyze the muscle synergy patterns of electromyographic signals to obtain muscle activation patterns, levels, and muscle coordination levels. The muscle synergy analysis model used in this invention is as follows:

[0103] E = W * C + e (8)

[0104] Where E represents the initial data matrix, W represents the muscle synergy pattern vector matrix, C represents the synergy correlation coefficient matrix, and e represents the residual after decomposition. E is a p*n matrix, where p is the number of muscles involved in the movement and n is the number of data points collected; W is a p*s matrix, where s is the number of muscle synergies; C is an s*n matrix, and e is a p*n matrix. Matrix W and C are constrained to be non-negative. Starting from a random matrix, through continuous iteration, when the residual e is minimized, W and C are the non-negative matrix decomposition results of the original data matrix E.

[0105] The row vectors of matrix E implicitly contain positional information between muscles, while the column vectors contain temporal information about the measurements. The final decomposition matrices W and C adhere to the same spatial and temporal constraints as the original matrix E, meaning that W and C can reflect the activation patterns and levels of muscles.

[0106] The ratio of the nonnegative matrix decomposition of agonist muscles to antagonist muscles can be used to represent the level of muscle coordination.

[0107] Step 4: Integrate the multi-channel EEG and multi-channel EMG signals from the resting and imagination periods to analyze the effectiveness of brain-muscle communication and obtain rehabilitation effect evaluation indicators based on EEG and EMG signals.

[0108] Step 4 aims to integrate EEG and EMG signals to analyze the effectiveness of brain-muscle information transmission, and obtain the bidirectional transmission entropy and transmission lag time of EEG and EMG signals as indicators for evaluating rehabilitation effects.

[0109] The formula for calculating the bidirectional transfer entropy of electroencephalography and electromyography is as follows:

[0110]

[0111] Where p is the probability, and u is the relative delay time of electroencephalography (EEG) and electromyography (EMG). Specifically, y t+u The electromyographic signal sequence at time t+u; y t Here is the electromyography signal sequence at time t; x t p(y) is the EEG signal sequence at time t. t+u y t x t p(y) represents the joint probability of the electromyography (EMG) signal sequence at time t, the electroencephalography (EEG) signal sequence at time t+u, and the EMG signal sequence at time t+u; t p(y) represents the probability of the electromyographic signal sequence at time t; t+u y t p(y) represents the joint probability of the electromyographic signal sequences at time t and time t+u; t x t ) represents the joint probability of the electromyography (EMG) signal sequence and the electroencephalography (EEG) signal sequence at time t; This represents the entropy of bidirectional transmission of electroencephalography and electromyography.

[0112] The method for determining the transmission lag time is as follows: Calculate the bidirectional transmission entropy of EEG and EMG at different lag times u; when the bidirectional transmission entropy of EEG and EMG reaches its maximum value, the corresponding time u is recorded as the transmission lag time.

[0113] Step 5: Evaluate the patient's rehabilitation status and effect based on the rehabilitation effect evaluation indicators based on EEG signals, the rehabilitation effect evaluation indicators based on EMG signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals to obtain the rehabilitation status and effect evaluation results.

[0114] The rehabilitation effect evaluation indicators calculated by this invention include the rehabilitation effect evaluation indicators based on electroencephalogram (EEG) signals, the rehabilitation effect evaluation indicators based on electromyography (EMG) signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals. By comprehensively considering the superiority or inferiority of the above different rehabilitation effect evaluation indicators, the evaluation results of the patient's rehabilitation status and effect are given. The rehabilitation status and effect evaluation results can be divided into primary, intermediate, and advanced stages from poor to excellent.

[0115] In practical applications, threshold judgment method or model training method can be used to evaluate the patient's rehabilitation status and effect, and obtain the rehabilitation status and effect evaluation results; the rehabilitation status and effect evaluation results are divided into primary, intermediate and advanced levels from poor to excellent.

[0116] Among them, the threshold determination method is used to evaluate the rehabilitation status and effect, and the method for distinguishing different levels is as follows: For each index X calculated in the above steps 2 to 4 (such as the electroencephalogram signal energy change index, spectral coherence, transfer entropy, Granger causality analysis, electromyogram signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, muscle coordination level, electroencephalogram-electromyogram bidirectional transfer entropy or transfer lag time), set the corresponding threshold [d1, d2] for determination; if X >= d2, it indicates that this index X is better and is divided into the advanced stage; if d2 > X >= d1, it indicates that this index X is relatively good and is divided into the intermediate stage; if X < d1, it indicates that this index X is poor and is divided into the primary stage.

[0117] The model training method is used to evaluate the rehabilitation status and effect, and the method for distinguishing different levels is as follows: Input all the indexes calculated in the above steps 2 to 4 (including the electroencephalogram signal energy change index, spectral coherence, transfer entropy, Granger causality analysis, electromyogram signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, muscle coordination level, electroencephalogram-electromyogram bidirectional transfer entropy, and transfer lag time) into the support vector machine SVM model, and the corresponding classification results, namely primary, intermediate, and advanced, can be obtained. The SVM model training process is as follows: Use the support vector machine SVM model with the kernel function being RBF; use the indexes in the above steps 2 to 4 as the input features of the model; use the results of the clinical Fugl-Meyer assessment scale (Fugl-Meyer assessment scale, FMA) divided into three levels of primary, intermediate, and advanced as labels; train the model to obtain the SVM model coefficients; use the trained SVM model to evaluate the rehabilitation status and effect and distinguish different levels.

[0118] The rehabilitation status and effect evaluation results obtained by using the method of the present invention can provide a strong basis for formulating a suitable and reasonable rehabilitation plan, and improve the patient's clinical treatment experience and motor rehabilitation effect. According to different rehabilitation status and effect evaluation results, the corresponding rehabilitation treatment plan can be output. For example, if the rehabilitation status and effect are primary, the main focus is on exercise rehabilitation to activate and restore muscle and joint abilities, such as functional electrical stimulation. If the rehabilitation status and effect are intermediate, the main focus is on improving muscle strength, joint flexibility, and neuromuscular control ability, such as mechanical exoskeleton-assisted limb movement based on motion intention recognition control. If the rehabilitation status and effect are advanced, the main focus is on improving muscle coordination, neuromuscular fine movements, and precise control, such as intensive auxiliary training for limb terminal movement and control of movement force, displacement, and speed based on electroencephalogram-electromyogram motion intention recognition.

[0119] Current methods typically assess motor rehabilitation indirectly by utilizing two endpoints: brain regions related to movement or muscle function. However, this approach lacks a comprehensive and systematic evaluation of information transmission between brain regions and muscle execution units, motor feedback loops, muscle synergy, and the brain's response to movement. This invention proposes objective and quantifiable evaluation indicators for motor rehabilitation efficacy, analyzing from three dimensions: EEG signal assessment of brain-related motor functions such as functional connectivity; EMG assessment of muscle-related motor functions such as muscle synergy and muscle tremors; and a fusion of EEG and EMG assessment of related neuromuscular circuits, including information transmission between brain regions and muscle execution units, motor feedback loops (bidirectional transfer entropy), and the brain's response to movement (lag time). Through physiological signal processing (including EEG and EMG signals), the entire closed-loop neural circuit of motor function is automatically and objectively quantified, resulting in higher assessment efficiency and a more comprehensive and accurate assessment of rehabilitation status and effects. This provides a strong basis for developing appropriate and reasonable rehabilitation plans, contributing to improved patient experience and the effectiveness of motor rehabilitation.

[0120] Based on the method provided by this invention, this invention also provides a rehabilitation effect evaluation system based on electroencephalogram (EEG) and electromyogram (EMG) signals, the system comprising:

[0121] A multi-channel physiological signal acquisition module is used to acquire multi-channel electroencephalogram (EEG) signals and multi-channel electromyogram (EMG) signals during resting and imagination periods.

[0122] The EEG signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EEG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EEG signals; the rehabilitation effect evaluation indexes based on EEG signals include the EEG signal energy change index and three brain function evaluation indicators.

[0123] The electromyography (EMG) signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EMG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EMG signals. The rehabilitation effect evaluation indexes based on EMG signals include EMG signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level.

[0124] The EEG / EMG signal rehabilitation effect evaluation index calculation module is used to integrate multi-channel EEG signals and multi-channel EMG signals from the resting and imagination periods to perform brain-muscle information transmission effectiveness analysis and obtain rehabilitation effect evaluation indexes based on EEG / EMG signals; the rehabilitation effect evaluation indexes based on EEG / EMG signals include bidirectional EEG / EMG transmission entropy and transmission lag time.

[0125] The rehabilitation status and effect assessment module is used to assess the patient's rehabilitation status and effect based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyography (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and obtain the rehabilitation status and effect assessment results.

[0126] The multi-channel physiological signal acquisition module specifically includes:

[0127] The resting-time EEG signal acquisition unit is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a resting state, so as to obtain multi-channel EEG signals during the resting period.

[0128] The EEG signal acquisition unit for the imagination period is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a state of motor imagination, so as to obtain multi-channel EEG signals during the imagination period.

[0129] The resting period electromyography signal acquisition unit is used to acquire multi-channel electromyography signals from the patient's upper limb and its extremities or lower limb and its extremities when the patient is in a resting state, so as to obtain multi-channel electromyography signals during the resting period.

[0130] The imagery-time electromyography (EMG) signal acquisition unit is used to acquire multi-channel EMG signals from the patient's upper limbs and their extremities or lower limbs and their extremities when the patient is in a state of motor imagery, thus obtaining multi-channel EMG signals during the imagery time.

[0131] The brainwave signal rehabilitation effect evaluation index calculation module specifically includes:

[0132] The EEG signal energy change index calculation unit is used to perform energy analysis on the multi-channel EEG signals during the resting period and the imagination period to obtain the EEG signal energy change index before and after the execution of the imagined movement.

[0133] The brain function evaluation index calculation unit is used to perform brain function connectivity analysis on the multi-channel EEG signals during the resting and imagination periods to obtain three brain function evaluation indices; the three brain function evaluation indices include spectral coherence, transfer entropy, and Granger causality analysis.

[0134] The electromyography signal rehabilitation effect evaluation index calculation module specifically includes:

[0135] The time-frequency domain analysis and calculation unit is used to perform time-domain and frequency-domain analysis on the multi-channel electromyographic signals during the resting period and the imagination period to obtain the electromyographic signal energy change index, muscle tremor intensity and muscle control ability before and after the execution of the imagined movement.

[0136] The muscle coordination pattern analysis and calculation unit is used to perform muscle coordination pattern analysis on the multi-channel electromyographic signals during the resting and imaginary periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels.

[0137] The rehabilitation status and effect assessment module specifically includes:

[0138] The rehabilitation status and effect assessment unit is used to assess the patient's rehabilitation status and effect using the threshold judgment method or model training method based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyogram (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and to obtain the rehabilitation status and effect assessment results; the rehabilitation status and effect assessment results are divided into primary, intermediate, and advanced levels from poor to excellent.

[0139] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0140] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for evaluating rehabilitation effects based on electroencephalogram (EEG) and electromyogram (EMG) signals, characterized in that, include: Collect multichannel EEG and multichannel EMG signals during resting and imagination periods; The multi-channel EEG signals from the resting and imagination periods are analyzed and processed to obtain rehabilitation effect evaluation indicators based on EEG signals. These indicators include an EEG signal energy change index and three brain function evaluation indicators. Specifically, the analysis and processing of the multi-channel EEG signals from the resting and imagination periods to obtain these indicators includes: energy analysis of the multi-channel EEG signals from the resting and imagination periods to obtain an EEG signal energy change index before and after the execution of the imagined movement; brain function connectivity analysis of the multi-channel EEG signals from the resting and imagination periods to obtain three brain function evaluation indicators; these indicators include spectral coherence, transfer entropy, and Granger causality analysis; subtracting the energy intensity of the resting period from the energy intensity of the imagination period to obtain the energy difference; and comparing the energy intensity of the resting period with the energy intensity of the imagination period to obtain the energy ratio; the calculated EEG signal energy difference and energy ratio are used as the EEG signal energy change index before and after the execution of the imagined movement. The multi-channel electromyography (EMG) signals from the resting and visualization periods are analyzed and processed to obtain rehabilitation effect evaluation indicators based on EMG signals. These indicators include the EMG signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level. The EMG signal energy intensity in different regions during the resting and visualization periods is calculated to obtain the energy intensity difference and ratio between the two periods. The energy intensity difference and ratio are used as the EMG signal energy change index. The analysis and processing of multi-channel electromyography (EMG) signals during the resting and visualization periods yields rehabilitation effect evaluation indicators based on EMG signals. Specifically, this includes: performing time-domain and frequency-domain analysis on the multi-channel EMG signals during the resting and visualization periods to obtain the EMG signal energy change index, muscle tremor intensity, and muscle control ability before and after the execution of the imagined movement; performing muscle synergy pattern analysis on the multi-channel EMG signals during the resting and visualization periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels; and using a muscle synergy analysis model to analyze and obtain muscle activation patterns and activation levels. The muscle synergy analysis model used is as follows: E = W C + e； in, E Represents the initial data matrix. W Represents the muscle coordination pattern vector matrix. C Represents the co-correlation coefficient matrix, e Represents the residual after decomposition. E For one p n A matrix of size p The number of muscles involved in exercise. n The number of data points collected; W For one p s A matrix of size s For muscle synergy; C for s n A matrix of size e for p n Matrix of size, matrix W , C Given a non-negative matrix, starting with a random matrix and iterating continuously, the residual... e At its minimum, W and C That is, the original data matrix E The result of nonnegative matrix factorization, matrix W and C It reflects the activation pattern and activation level of muscles; it calculates the ratio of the non-negative matrix factorization of agonist muscles to antagonist muscles to represent the level of muscle coordination. By integrating multi-channel EEG and multi-channel EMG signals from the resting and imagination periods, an effectiveness analysis of brain-muscle transmission information is performed to obtain rehabilitation effect evaluation indicators based on EEG and EMG signals. These indicators include bidirectional EEG / EMG transmission entropy and transmission lag time. The formula for calculating the bidirectional EEG / EMG transmission entropy is as follows: ； in p For probability, u The relative lag time of electroencephalography (EEG) and electromyography (EMG) The electromyographic signal sequence at time t+u; The electromyographic signal sequence at time t; The sequence of EEG signals at time t; Let be the joint probability of the electromyography (EMG) signal sequence at time t, the electroencephalogram (EEG) signal sequence at time t, and the EMG signal sequence at time t+u; Let be the probability of the electromyographic signal sequence at time t; Let be the joint probability of the electromyographic signal sequences at time t and time t+u; Let be the joint probability of the electromyography (EMG) signal sequence and the electroencephalography (EEG) signal sequence at time t; This represents the entropy value of bidirectional transmission between the brain and muscle. EEG and EMG at different lag times u The following steps are performed: Calculate the bidirectional transmission entropy of EEG and EMG; when the bidirectional transmission entropy of EEG and EMG reaches its maximum value, the corresponding time is... u Let this be the transmission delay time; The rehabilitation status and effect of the patient are evaluated based on the rehabilitation effect evaluation indicators based on electroencephalogram (EEG) signals, the rehabilitation effect evaluation indicators based on electromyogram (EMG) signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals, and the rehabilitation status and effect evaluation results are obtained.

2. The method according to claim 1, characterized in that, The acquisition of multi-channel EEG and multi-channel EMG signals during resting and imagination periods specifically includes: When the patient is at rest, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the resting period. When the patient is in a state of motor imagination, multi-channel EEG signals from the patient’s motor cortex and somatosensory cortex are collected to obtain multi-channel EEG signals during the imagination period. When the patient is at rest, multi-channel electromyography (EMG) signals from the patient's upper limb and its extremities or lower limb and its extremities are collected to obtain multi-channel EMG signals during the resting period. When the patient is in a state of motor imagery, multi-channel electromyographic signals from the patient's upper limbs and their extremities or lower limbs and their extremities are collected to obtain multi-channel electromyographic signals during the imagery period.

3. The method according to claim 1, characterized in that, The process of evaluating the patient's rehabilitation status and effectiveness based on the rehabilitation effect evaluation indicators based on electroencephalogram (EEG) signals, the rehabilitation effect evaluation indicators based on electromyography (EMG) signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals, to obtain the rehabilitation status and effectiveness evaluation results, specifically includes: Based on the rehabilitation effect evaluation indicators based on EEG signals, the rehabilitation effect evaluation indicators based on EMG signals, and the rehabilitation effect evaluation indicators based on EEG and EMG signals, the patient's rehabilitation status and effect are evaluated using a threshold determination method or a model training method to obtain the rehabilitation status and effect evaluation results; the rehabilitation status and effect evaluation results are divided into primary, intermediate, and advanced levels from poor to excellent.

4. A rehabilitation effect evaluation system based on electroencephalogram (EEG) and electromyogram (EMG) signals, characterized in that, include: A multi-channel physiological signal acquisition module is used to acquire multi-channel electroencephalogram (EEG) signals and multi-channel electromyogram (EMG) signals during resting and imagination periods. The EEG signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EEG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EEG signals; the rehabilitation effect evaluation indexes based on EEG signals include the EEG signal energy change index and three brain function evaluation indicators. The EEG signal rehabilitation effect evaluation index calculation module specifically includes: an EEG signal energy change index calculation unit, used to perform energy analysis on the multi-channel EEG signals during the resting and imagination periods to obtain the EEG signal energy change index before and after the execution of the imagined movement; and a brain function evaluation index calculation unit, used to perform brain function connectivity analysis on the multi-channel EEG signals during the resting and imagination periods to obtain three brain function evaluation indicators; the three brain function evaluation indicators include spectral coherence, transmission entropy, and Granger causality analysis; the energy difference is obtained by subtracting the energy intensity of the resting period from the energy intensity of the imagination period, and the energy ratio is obtained by comparing the energy intensity of the resting period with the energy intensity of the imagination period; the calculated EEG signal energy difference and EEG signal energy ratio are used as the EEG signal energy change index before and after the execution of the imagined movement. The electromyography (EMG) signal rehabilitation effect evaluation index calculation module is used to analyze and process the multi-channel EMG signals during the resting and imagination periods to obtain rehabilitation effect evaluation indexes based on EMG signals. The rehabilitation effect evaluation indexes based on EMG signals include EMG signal energy change index, muscle tremor intensity, muscle control ability, muscle activation pattern, muscle activation level, and muscle coordination level. The electromyography (EMG) signal rehabilitation effect evaluation index calculation module specifically includes: a time-frequency domain analysis calculation unit, which is used to perform time-domain and frequency-domain analysis on the multi-channel EMG signals during the resting period and the imagination period to obtain the EMG signal energy change index, muscle tremor intensity and muscle control ability before and after the execution of the imagined movement; The muscle coordination pattern analysis and calculation unit is used to perform muscle coordination pattern analysis on the multi-channel electromyographic signals during the resting and imaginary periods to obtain muscle activation patterns, muscle activation levels, and muscle coordination levels. The analysis is performed using a muscle coordination analysis model to obtain muscle activation patterns and activation levels. The muscle coordination analysis model used is as follows: E = W C + e； in, E Represents the initial data matrix. W Represents the muscle coordination pattern vector matrix. C Represents the co-correlation coefficient matrix, e Represents the residual after decomposition. E For one p n A matrix of size p The number of muscles involved in exercise. n The number of data points collected; W For one p s A matrix of size s For muscle synergy; C for s n A matrix of size e for p n Matrix of size, matrix W , C Given a non-negative matrix, starting with a random matrix and iterating continuously, the residual... e At its minimum, W and C That is, the original data matrix E The result of nonnegative matrix factorization, matrix W and C It reflects the activation pattern and activation level of muscles; it calculates the ratio of the non-negative matrix factorization of agonist muscles to antagonist muscles to represent the level of muscle coordination. The EEG / EMG signal rehabilitation effect evaluation index calculation module is used to fuse multi-channel EEG and multi-channel EMG signals from the resting and imagination periods to analyze the effectiveness of brain-muscle transmission information and obtain rehabilitation effect evaluation indexes based on EEG / EMG signals. These evaluation indexes include bidirectional EEG / EMG transmission entropy and transmission lag time. The formula for calculating the bidirectional EEG / EMG transmission entropy is as follows: ； in p For probability, u The relative lag time of electroencephalography (EEG) and electromyography (EMG) The electromyographic signal sequence at time t+u; The electromyographic signal sequence at time t; The sequence of EEG signals at time t; Let be the joint probability of the electromyography (EMG) signal sequence at time t, the electroencephalogram (EEG) signal sequence at time t, and the EMG signal sequence at time t+u; Let be the probability of the electromyographic signal sequence at time t; Let be the joint probability of the electromyographic signal sequences at time t and time t+u; Let be the joint probability of the electromyography (EMG) signal sequence and the electroencephalography (EEG) signal sequence at time t; This represents the entropy value of bidirectional transmission between the brain and muscle. EEG and EMG at different lag times u The following steps are performed: Calculate the bidirectional transmission entropy of EEG and EMG; when the bidirectional transmission entropy of EEG and EMG reaches its maximum value, the corresponding time is... u Let this be the transmission delay time; The rehabilitation status and effect assessment module is used to assess the patient's rehabilitation status and effect based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyography (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and obtain the rehabilitation status and effect assessment results.

5. The system according to claim 4, characterized in that, The multi-channel physiological signal acquisition module specifically includes: The resting-time EEG signal acquisition unit is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a resting state, so as to obtain multi-channel EEG signals during the resting period. The EEG signal acquisition unit for the imagination period is used to acquire multi-channel EEG signals from the motor cortex and somatosensory cortex of the patient's brain when the patient is in a state of motor imagination, so as to obtain multi-channel EEG signals during the imagination period. The resting period electromyography signal acquisition unit is used to acquire multi-channel electromyography signals from the patient's upper limb and its extremities or lower limb and its extremities when the patient is in a resting state, so as to obtain multi-channel electromyography signals during the resting period. The imagery-time electromyography (EMG) signal acquisition unit is used to acquire multi-channel EMG signals from the patient's upper limbs and their extremities or lower limbs and their extremities when the patient is in a state of motor imagery, thus obtaining multi-channel EMG signals during the imagery time.

6. The system according to claim 4, characterized in that, The rehabilitation status and effect assessment module specifically includes: The rehabilitation status and effect assessment unit is used to assess the patient's rehabilitation status and effect using the threshold judgment method or model training method based on the rehabilitation effect assessment indicators based on electroencephalogram (EEG) signals, the rehabilitation effect assessment indicators based on electromyogram (EMG) signals, and the rehabilitation effect assessment indicators based on EEG and EMG signals, and to obtain the rehabilitation status and effect assessment results; the rehabilitation status and effect assessment results are divided into primary, intermediate, and advanced levels from poor to excellent.

Images