Real-time evaluation method and system for transcranial electrical stimulation effect

Abstract

The invention discloses a real-time evaluation method for a transcranial electrical stimulation effect, and relates to the technical field of brain electrical stimulation effects, and the real-time evaluation method comprises the following steps: fusing MRI modeling, HD-tDCS electrode optimization, electric field simulation and genetic algorithm parameter configuration, combining multi-modal nerve response collection, multi-task brain state prediction based on an attention mechanism, and Granger causal path modeling. And a real-time evaluation mechanism oriented to a full chain of'stimulation-nerve-behavior 'is constructed. Compared with an existing evaluation mode which only depends on electroencephalogram change or a single behavior index, the method has the advantages that the space targeting, the nerve activation specificity, the behavior improvement degree and the causal connection strength of stimulation can be quantified at the same time, and parameter self-feedback optimization is driven through comprehensive scores; and the instantaneity, the accuracy and the individualized regulation and control capability of transcranial electrical stimulation effect evaluation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of brain electrical stimulation effect evaluation, and in particular to a real-time evaluation method and system for transcranial electrical stimulation effect. Background Art

[0002] With the rapid development of non-invasive neuromodulation technology, transcranial direct current stimulation has been widely used in intervention studies of various neurological and psychiatric diseases such as depression, aphasia, chronic pain, and Parkinson's disease due to its high safety, simple operation, and potential for regulating brain function. In recent years, thanks to the development of high-density electrode technology, the spatial resolution and targeting of stimulation have been improved. At the same time, combined with multimodal brain imaging and simulation modeling, the transition from "group uniform parameters" to "individualized stimulation configuration" has been achieved. At present, most HD-tDCS systems support the implementation of three-dimensional electric field simulation on the structural MRI head model through electrode layout optimization, current intensity adjustment, etc., so as to achieve precise control of the stimulation area. In addition, the physiological signals such as EEG, fNIRS, and EDA collected by the subjects during the stimulation process also provide a basis for the analysis of neural response patterns during electrical stimulation. However, despite the continuous optimization of stimulation parameters and the improvement of acquisition equipment, existing studies generally use offline analysis or single-dimensional indicators (such as power spectrum changes and reaction time improvements) to evaluate the effects, and fail to achieve a "real-time, multi-dimensional, and feedback-enabled" dynamic evaluation closed loop. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing real-time evaluation method and system for transcranial electrical stimulation effect, the present invention is proposed.

[0004] Therefore, the present invention provides a real-time evaluation method and system for transcranial electrical stimulation effects to solve the problem that although stimulation parameters are continuously optimized and acquisition equipment is becoming more and more perfect, existing studies generally use offline analysis or single-dimensional indicators (such as power spectrum changes, reaction time improvements) to evaluate the effects, and fail to achieve a "real-time, multi-dimensional, and feedback-enabled" dynamic evaluation closed loop.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for real-time evaluation of transcranial electrical stimulation effects, comprising: Obtain the MRI data of the subject's head to construct a multi-tissue three-dimensional head model, and place HD-tDCS needle-shaped composite electrodes on the head model, targeting the key functional areas of the brain. Use the finite element method to simulate the electric field distribution, and obtain the modulation spectrum of multiple sets of electrode current combinations. Use a genetic algorithm to optimize the electrode configuration and current parameters with the goal of maximizing the modulation intensity within the ROI and minimizing the diffusion of non-target areas. Implement tDCS stimulation based on electrode configuration and parameters, collect test data in real time and construct neural response vector R after preprocessing; Construct a multi-task prediction network based on the attention mechanism to obtain the prediction value; Guide the subjects to perform the task feedback test, record the behavioral output B, and form a three-variable time series data stream with the stimulus injection intensity S, neural response R, and behavioral performance B. Use Granger causal analysis to quantify the causal path strength of S→R→B; The EEG response enhancement rate and behavior improvement rate were calculated, and the comprehensive score of the stimulation effect was calculated based on the calculation results, the predicted value, and the causal path strength to conduct a real-time evaluation of the stimulation effect.

[0006] As a preferred embodiment of the real-time evaluation method of the transcranial electrical stimulation effect of the present invention, the method of acquiring the head MRI data of the subject to construct a multi-tissue three-dimensional head model, arranging HD-tDCS needle-shaped composite electrodes on the head model, targeting the key functional areas of the brain, and using the finite element method to simulate the electric field distribution, and obtaining the modulation spectrum of multiple sets of pole current combinations includes: Collect T1-weighted structural images of the subject's head, output DICOM format image sequences, convert DICOM format to NIfTI format, unify the spatial resolution, start SPM12 software, select the "Segment" module to output five types of tissue label maps, and merge the label maps of each channel into a single label file; The label map is imported into ScanIP for voxel reconstruction and tissue-level meshing to generate a complete three-dimensional finite element model of the head with conductive properties. Activate the triangular patch mesh of the scalp area as the electrode layout surface, initialize the MNI space standard reference point, automatically project the international 10-10 system electrode points onto the scalp surface according to the head model space coordinates, use the normal projection algorithm to record the three-dimensional coordinates of each electrode, and assign a unique number to each electrode point , establish an electrode-coordinate index table, select TP9 as the reference electrode, and the remaining 60 electrode numbers constitute the excitation electrode candidate set; At each electrode point The center creates a circular surface electrode model, sets the electrode material to silver, and defines it as the "current injection boundary". The reference electrode TP9 is set as the "current reference boundary". All electrode models are merged with the head mold surface mesh to form a complete simulation geometry model. Start the COMSOL Multiphysics simulation platform and import the simulation geometry model; Two independent excitation electrode pairs are activated in the COMSOL model. The current amplitude and the AC current with different injection frequencies are set for electrode pair 1 and electrode pair 2. The reference electrode TP9 is fixed as the common return electrode. During simulation, the two pairs of electrodes are independently and simultaneously injected with currents of different frequencies. In the simulation software COMSOL, the solver is started to calculate the electric field vector distribution formed by electrode pair 1 and electrode pair 2 in the brain tissue, which are recorded as , ; The solver automatically traverses all the head model voxel grid points, outputs the values ​​of the two electric field vectors at each voxel coordinate, and saves them as three-dimensional field distribution data; For all voxel positions, the modulation amplitude of each voxel position is calculated based on the electric field vector obtained by simulation, and a color visualization of the three-dimensional electric field intensity distribution is generated.

[0007] As a preferred embodiment of the real-time evaluation method of the transcranial electrical stimulation effect of the present invention, the genetic algorithm is used to optimize the electrode configuration and current parameters with the goal of maximizing the modulation intensity within the ROI and minimizing the diffusion in the non-target area, including: The standard brain space is used to spatially register the MRI images of the subject's head model, and a mapping relationship between the physical coordinates and the standard template space is established in the simulation model, and the spatial coordinates of the electric field distribution grid voxels are mapped to the template brain structure; Extract the mask of the right hippocampus from the standard brain template, match and extract all voxel indexes within the hippocampus mask according to the spatial registration coordinate table, record the grid number and spatial coordinates corresponding to the voxel, and form the ROI voxel set P; The ROI focusing ratio objective function D is constructed based on the electric field modulation amplitude data; Randomly select 4 non-repeating numbers from the electrode candidate set, assign the electrode numbers 1 to 4 in sequence, generate current injection values ​​for electrode pair 1 and pair 2 respectively and sample them according to uniform distribution, merge the electrode numbers and current injection values ​​into chromosomes, generate all chromosomes and store them as the initial population matrix; Configure electrode numbers and injection parameters for each chromosome, solve the electric fields generated by the two sets of electrode injections, calculate the amplitude of the interference modulation field, extract the electric field modulation value and voxel volume of each voxel point, calculate the total amount of modulation field energy in the ROI area and non-ROI area, and substitute it into formula D to obtain the fitness score of the current chromosome; All individual results form a complete chromosome library, sort them in descending order of fitness value, retain the first M chromosomes, and define the retained individuals as the next generation population and the elite subset Q, which does not participate in crossover and mutation; Through roulette wheel selection, non-elite individuals are selected as crossover parents according to fitness probability and offspring chromosomes are generated to obtain the offspring chromosome set A generated after crossover; Randomly select W individuals from the offspring for mutation. For each individual to be mutated, randomly select a strategy to adjust the parameters to obtain the offspring set Z after mutation. Combine Q, A and Z to construct a new generation of complete population, perform electric field simulation and fitness calculation on each chromosome in the new generation, stop evolution after reaching the preset maximum number of iterations, and obtain the last generation of population. Select the chromosome with the highest fitness in the last generation of population, extract the corresponding simulated electric field modulation map, and obtain the optimal electrode combination number and injection current parameters.

[0008] As a preferred embodiment of the real-time evaluation method of the transcranial electrical stimulation effect of the present invention, the subject is guided to perform the task feedback test, the behavioral output B is recorded, the stimulation injection intensity S, the neural response R, and the behavioral performance B constitute a three-variable time series data stream, and Granger causal analysis is used to quantify the causal path strength of S→R→B, including: Guide the subjects to perform the Go / No-Go visual recognition task, record the subjects' reaction time and judgment correctness, and construct the temporal behavior vector B(t); After obtaining the behavioral feedback B(t), the stimulus injection intensity sequence S(t) and the neural response sequence R(t) in the corresponding time window are immediately extracted; The three types of data are aligned and standardized at a unified sampling frequency to form a three-variable time series Y(t). Each component of the three-variable time series Y(t) is decomposed separately using a trous wavelet filter to obtain a detailed sequence of each variable at s scales. The detail components of the three variables at each scale are recombined to obtain the joint sequence C(t) at each scale s. From the joint sequence C(t), extract and , construct a two-layer Granger causal path model of "stimulus → nerve → behavior", including first-stage modeling and second-stage modeling; Calculate the final path validity score based on the first-stage model and the second-stage model results ; The scores at all scales are integrated to obtain the final cross-scale main path score .

[0009] As a preferred solution of the real-time evaluation method of the transcranial electrical stimulation effect described in the present invention, wherein: the tDCS stimulation is implemented based on the electrode configuration and parameters, and the test data is collected in real time and preprocessed to construct the neural response vector R, including: the stimulation system is configured according to the determined optimal electrode pair combination and injection parameters, and EEG, HbO / HbR dynamic concentration, EDA and pupil change data are collected in real time and preprocessed. After the preprocessing is completed, the processing results of each modality at each moment are combined into a structured neural response vector R.

[0010] As a preferred embodiment of the real-time evaluation method of the transcranial electrical stimulation effect of the present invention, wherein: the multi-task prediction network based on the attention mechanism is constructed, and the prediction value obtained refers to the neural response vector sequence within the acquisition time window C , choose the standard Encoder-only Transformer architecture, The trained Transformer model is input to obtain the cognitive response prediction value, emotional fluctuation prediction value and stimulation tolerance prediction value, and the obtained prediction values ​​are weighted and summed to obtain the neural state prediction score I.

[0011] As a preferred embodiment of the method for real-time evaluation of transcranial electrical stimulation effect of the present invention, wherein: the calculation of EEG response enhancement rate and behavior improvement rate, the calculation of stimulation effect comprehensive score based on the calculation result and the predicted value and causal path strength, and the real-time evaluation of stimulation effect refers to the calculation of EEG response enhancement rate O and behavior improvement rate F; The obtained EEG response enhancement rate O, behavior improvement rate F and path strength score The weighted sum of the predicted score of the neural state I is used to obtain the real-time score J of the current stimulation effect; Set the threshold K and , and K> , compare the real-time score J with the set threshold, obtain the current stimulation effect and formulate corresponding measures.

[0012] In a second aspect, the present invention provides a real-time evaluation system for transcranial electrical stimulation effects, comprising: A 3D modeling module, which is used to construct an individual 3D head tissue model based on MRI images and perform electrode positioning and mapping; The electric field simulation module is used to perform electric field simulation based on the built head mold and electrode layout and use genetic algorithm to search for the optimal injection configuration; A signal acquisition module, used to implement tDCS stimulation and simultaneously collect multimodal physiological signals; The prediction module is used to construct a Transformer network for the collected neural response sequences to achieve multi-dimensional brain state prediction; The causal analysis module is used to guide the subjects to perform task feedback, extract the stimulus-response-behavior triple data flow, and perform Granger causal path modeling; The effect evaluation module is used to integrate EEG response enhancement, behavior improvement, state prediction value and causal path score to calculate the comprehensive effect score of the current stimulation.

[0013] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the real-time evaluation method of transcranial electrical stimulation effect as described in the first aspect of the present invention is implemented.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for real-time evaluation of transcranial electrical stimulation effects as described in the first aspect of the present invention is implemented.

[0015] The beneficial effects of the present invention are: by integrating MRI modeling, HD-tDCS electrode optimization, electric field simulation and genetic algorithm parameter configuration, combined with multimodal neural response acquisition, multi-task brain state prediction based on attention mechanism and Granger causal path modeling, a real-time evaluation mechanism for the entire chain of "stimulation → nerves → behavior" is constructed. Compared with the existing evaluation method that only relies on EEG changes or a single behavioral indicator, the present invention can simultaneously quantify the spatial targeting of stimulation, neural activation specificity, degree of behavioral improvement and causal connectivity strength, and through comprehensive scoring to drive parameter self-feedback optimization, it significantly improves the real-time, accuracy and individualized regulation ability of transcranial electrical stimulation effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 Schematic diagram of the process of the real-time evaluation method of transcranial electrical stimulation effect in Example 1; Figure 2 Schematic diagram of the structure of the real-time evaluation system of transcranial electrical stimulation effect in Example 1. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0021] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a real-time evaluation method for transcranial electrical stimulation effect, the real-time evaluation method for transcranial electrical stimulation effect comprises the following steps: S1. Obtain the MRI data of the subject's head to construct a multi-tissue three-dimensional head model, arrange HD-tDCS needle-shaped composite electrodes on the head model, target the key functional areas of the brain, use the finite element method to simulate the electric field distribution, obtain the modulation spectrum of multiple sets of pole current combinations, and use the genetic algorithm to optimize the electrode configuration and current parameters with the goal of maximizing the modulation intensity within the ROI and minimizing the diffusion of non-target areas; Specifically, we obtained the head MRI data of the subjects to construct a multi-tissue three-dimensional head model, arranged HD-tDCS needle-shaped composite electrodes on the head model, targeted the key functional areas of the brain, and used the finite element method to simulate the electric field distribution, and obtained the modulation spectra of multiple sets of electrode current combinations, including: Use a 3T magnetic resonance imaging system (such as Siemens Prisma) to collect T1-weighted structural images of the subject's head, output DICOM format image sequences, use the MRIcron tool to convert the DICOM format to NIfTI format, and unify the spatial resolution, start the SPM12 software, select the "Segment" module to output five types of tissue label maps, including gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), bone (Skull) and Scalp (skin), merge the label maps of each channel into a single label file, the label values ​​are as follows: 1 = skin, 2 = skull, 3 = CSF, 4 = gray matter, 5 = white matter; Import the label map into ScanIP (an advanced software platform developed by Simpleware, which is mainly used to process, analyze and visualize 3D image data, especially data obtained from medical imaging technologies such as computed tomography (CT) and magnetic resonance imaging (MRI)), perform voxel reconstruction and tissue-level meshing, and generate a complete 3D finite element model of the head with conductive properties (such as gray matter 0.276 S / m, CSF 1.79 S / m, etc.); Activate the triangular mesh of the scalp area as the electrode layout surface, initialize the MNI space standard reference points: nose tip (Nz), occipital point (Iz), left ear (A1), right ear (A2), vertex (Cz), complete the head model coordinate alignment through automatic registration methods (such as three-point least squares method), automatically project the international 10-10 system electrode points onto the scalp surface according to the head model space coordinates, use the normal projection algorithm to ensure that each electrode center point falls orthogonally on the scalp surface, record the three-dimensional coordinates of each electrode, and assign a unique number to each electrode point. , number range =1~61, establish electrode-coordinate index table; TP9 (left mastoid) is fixedly selected as the reference electrode, and the remaining 60 electrode numbers constitute the candidate set of excitation electrodes, which will be used to construct two sets of excitation electrode pairs in the subsequent combination optimization; Use the modeling module at each electrode point The center creates a circular surface electrode model, sets the electrode material to silver, and defines it as the "current injection boundary". The reference electrode TP9 is set as the "current reference boundary". All electrode models are merged with the head mold surface mesh to form a complete simulation geometry model. Start the COMSOL Multiphysics simulation platform and import the simulation geometry model; Two independent excitation electrode pairs are activated in the COMSOL model, and the current amplitude and the AC current with different injection frequencies are set for the electrode pair 1 and the electrode pair 2. The reference electrode TP9 is fixed as the common return electrode. During the simulation, the two pairs of electrodes are independently and simultaneously injected with currents of different frequencies to produce an interferometric modulation effect. In the simulation software COMSOL, the frequency domain solver is started to calculate the electric field vector distribution formed by electrode pair 1 and electrode pair 2 in the brain tissue, which are recorded as , ; The solver automatically traverses all the head model voxel grid points, outputs the values ​​of the two electric field vectors at each voxel coordinate, and saves them as three-dimensional field distribution data; For all voxel positions, the modulation amplitude at each voxel position is calculated based on the simulated electric field vector:

[0022]

[0023] In the formula, are two electric field vectors at any point in space The angle at and There are two electrode pairs (electrode pair 1 and pair 2) at voxel points The electric field vector generated at the location is, and The electric field vector and The module length, There are two alternating electric fields in space. The maximum modulation envelope amplitude formed after mutual interference at the position represents the actual electric field interference stimulation intensity received at that position; The 3D field plotting module of the COMSOL simulation platform is used to directly map the modulation amplitude onto the 3D head model grid to generate a complete color visualization of the 3D spatial electric field intensity distribution.

[0024] HD-tDCS refers to the technology of achieving high spatial resolution brain region regulation through a combination of multiple electrodes. It has better targeting than traditional large-area electrodes. The needle-shaped composite electrode introduces a multi-point microneedle structure on the basis of traditional ring electrodes or square electrodes to form a current density focus area, which significantly improves the spatial resolution of the electric field gradient distribution on the cortical surface. MNI space is a standard registration coordinate system for neuroimaging, which is used to ensure the uniform alignment of the head structure and electrode distribution between different individuals. OMSOL Multiphysics is the most commonly used multi-physics modeling platform in the current medical simulation field, supporting electromagnetic field solutions under coupling different frequencies, boundaries and medium properties. By introducing 3T high-field magnetic resonance equipment (such as Siemens Prisma) to obtain T1-weighted images and cooperating with SPM12 and ScanIP tool chains, voxel-level grid reconstruction of multiple head tissue structures (skin, bone, CSF, gray matter, white matter) can be achieved based on medical images, providing anatomically realistic tissue boundary conditions and conductivity difference support for simulation. Secondly, the normal projection and electrode point-scalp grid automatic alignment algorithm are used to accurately map the electrode layout to the individual head model while ensuring the MNI standard electrode system, forming a complete electrode number-three-dimensional coordinate index library, providing a stable structural parameter basis for electrode optimization search. A dual-frequency AC current injection mechanism is introduced into the COMSOL platform, and the frequencies of electrode pair 1 and electrode pair 2 are set to f1 and f2 respectively. By controlling the phase and amplitude of the two sets of currents, the interference envelope in the deep modulation area of ​​the cortex is maximized. The present invention realizes the construction of the physical optimal solution for maximizing the focusing of the three-dimensional modulation target area and minimizing the diffusion of the non-target area through a composite electrode structure + high-frequency cross-injection mechanism + space vector modulation algorithm, laying a precise physical foundation for the subsequent combination of neural signal modeling and behavioral feedback to form a closed-loop evaluation control system.

[0025] Furthermore, a genetic algorithm was used to optimize the electrode configuration and current parameters with the goal of maximizing the modulation intensity within the ROI and minimizing the diffusion in the non-target area, including: Use the standard brain space (Talairach) to spatially register the subject's head model MRI image, establish a mapping relationship between the physical coordinates and the standard template space in the simulation model, and map the spatial coordinates of the electric field distribution grid voxels to the template brain structure; Extract the mask of the right hippocampus (Hippocampus_R) from a standard brain template (such as Harvard-Oxford or AAL template of FSL), match and extract all voxel indexes within the hippocampus mask according to the spatial registration coordinate table, record the grid numbers and spatial coordinates corresponding to these voxels, and form a ROI voxel set P; Traverse all the electric field simulation output voxel index sets B, exclude the voxel numbers that already belong to P, and all the remaining voxels form the non-target area set R, and also record their corresponding electric field values ​​and voxel volumes; The ROI focusing ratio objective function D is constructed based on the electric field modulation amplitude data:

[0026] In the formula, and It is the three-dimensional space coordinates of the voxel in the ROI area (index u) and the voxel in the non-ROI area (index b), usually the coordinates of the center point of the voxel in the head model, is the set of voxel numbers that fall within the right hippocampus (3D mask), indicating the target area for electrical stimulation. is the set of voxel indices that do not fall into the ROI mask area, representing the potential current diffusion area, At each voxel position in the ROI area The maximum amplitude of the interference electric field modulation envelope formed by the electrode pair after injecting current, At each voxel position in the non-ROI area The maximum amplitude of the interference electric field modulation envelope formed by the electrode pair after injecting current, and is the three-dimensional spatial volume of the voxel, D is the ratio of the electric field modulation intensity in the ROI area to the diffusion intensity in the non-ROI area, and is used as the fitness function value of the genetic algorithm; Randomly select 4 non-repeating numbers from the electrode candidate set, assign the electrode numbers 1 to 4 in sequence, generate current injection values ​​for electrode pair 1 and pair 2 respectively and sample them according to uniform distribution, where electrode numbers 1 and 2 constitute excitation electrode pair 1, and electrode numbers 3 and 4 constitute excitation electrode pair 2, merge electrode numbers 1 to 4 and current injection values ​​1 to 2 into chromosomes, and store all chromosomes as the initial population matrix after generation; Configure electrode numbers and injection parameters for each chromosome, solve the electric fields generated by the two sets of electrode injections, calculate the amplitude of the interference modulation field, use the spatial registration table to correspond the simulation result voxels with the ROI voxel index set, extract the electric field modulation value and voxel volume of each voxel point, calculate the total amount of modulation field energy in the ROI area and non-ROI area, and substitute it into formula D to obtain the fitness score of the current chromosome; The chromosome parameters and fitness are stored in the data structure together, all individual results are used to form a complete chromosome library, sorted in descending order by fitness value, and the first M chromosomes are retained. The retained individuals are used as the next generation population and defined as the elite subset Q, which does not participate in crossover and mutation; A non-elite individual is selected as the crossover parent by roulette wheel selection according to the fitness probability, and the current best individual is set. For each pair of parents, the mean and variance of each parameter position are calculated by combining the current best individual. Based on the obtained mean and variance, the daughter chromosome is generated by using normal distribution sampling. The electrode number parameter results in the daughter chromosome are rounded to integers, and the electrode number and current parameter ranges are limited to obtain the daughter chromosome set A newly generated after the crossover; Randomly select W individuals from the offspring for mutation. For each individual to be mutated, randomly select a strategy for parameter adjustment, including normal mutation, Cauchy mutation and Lévy flight mutation. After mutation, re-restrict the parameter range to obtain the offspring set Z after mutation. Combine Q, A and Z to construct a new generation of complete population, perform electric field simulation and fitness calculation on each chromosome in the new generation, stop evolution after reaching the preset maximum number of iterations, set the maximum number of iterations based on experimental tuning, and obtain the last generation of population. Select the chromosome with the highest fitness in the last generation of population, extract the corresponding simulated electric field modulation map, and obtain the optimal electrode combination number and injection current parameters (i.e., injection intensity).

[0027] The "Talairach standard brain space" is an internationally recognized three-dimensional coordinate space system, which is often used in neuroimaging registration processing. Its advantage is that individual MRI image data can be uniformly mapped to a standard template, so that the electric field simulation results have structural comparability and consistency in functional areas. "Mask" refers to a three-dimensional voxel set constructed for a specified functional area (such as Hippocampus_R) in a standard brain template, which is used to accurately extract the simulation results in the area and participate in ROI target modeling. "Electric field modulation envelope maximum amplitude" refers to the modulated electric field peak value generated by the coherent superposition of two alternating currents of different frequencies in the body under the tTIS interference mechanism, which represents the true stimulation intensity. By constructing the ROI focusing ratio objective function DDD, the present invention realizes the quantitative comparison of the total energy of electric field modulation in the target area (ROI) and the diffuse energy in the non-target area (non-ROI). Specifically, the larger the ratio, the more concentrated the stimulation energy is on the functional core. area, the smaller it is, the more significant diffusion or offset there is. This feature is set as the fitness function value of the genetic algorithm, so that the entire optimization process has a clear physical goal-driven basis, thereby enhancing the scientificity and explanatory nature of electrode selection and injection flow strategy. In the optimization process, each set of "chromosome" encoding represents a specific set of electrode number combinations and injection current values. Its initial population is constructed by number sampling and injection flow uniform sampling, which has coverage. The elite retention strategy ensures that the local optimal solution is not eliminated, the roulette parent selection mechanism introduces the diversity guidance of fitness probability control, and the crossover process adopts parameter distribution fitting based on the current optimal body, so as to achieve iterative convergence of the fitness center without destroying the spatial distribution of the current structural solution. In addition, the three mutation strategies of normal mutation, Cauchy mutation and Lévy flight mutation can form a synergy between local perturbation and global jumping ability, which improves the convergence speed of the algorithm and the ability to jump out of the local optimal trap.

[0028] S2, implement tDCS stimulation based on electrode configuration and parameters, collect test data in real time and construct neural response vector R after preprocessing; Specifically, tDCS stimulation is implemented based on the electrode configuration and parameters, and the test data is collected in real time and preprocessed to construct the neural response vector R. This includes configuring the stimulation system based on the determined optimal electrode pair combination and injection parameters using a multi-channel HD-tDCS stimulation system (such as Starstim 64). During the stimulation process, an integrated physiological signal acquisition system (such as BIOPAC+NIRx) is used to collect EEG, HbO / HbR dynamic concentration, EDA, and pupil change data in real time. The EEG signal is filtered out using a bandpass filter (0.5–70 Hz) to remove DC drift and electromyographic interference, and then independent component analysis (ICA) is used to eliminate eye movement and blink artifacts, effectively removing interference components such as eye movement and electromyography, so that the retained EEG data has a higher signal-to-noise ratio and explanatory validity. After sliding window filtering and differential enhancement, the HbO / HbR signal can reflect the dynamics of cerebral blood flow in the target area in real time, which is helpful to judge the regulatory effect of neural regulation on metabolism and blood oxygen coupling mechanism. The target channel data is retained, and the dynamic concentration of HbO / HbR is filtered based on the sliding window mean to remove low-frequency drift and perform differential enhancement. The EDA and pupil change data are first processed by linear interpolation and then Z-score normalization to ensure that they have equal weight participation in the global modeling process. After the preprocessing is completed, the processing results of each modality at each moment are combined into a structured neural response vector R.

[0029] S3. Build a multi-task prediction network based on the attention mechanism to obtain the prediction value; Specifically, we construct a multi-task prediction network based on the attention mechanism, and obtain the prediction value by using a sliding time window mechanism. We set the input window length to C, so each input contains a response vector of C time steps. , select the standard Encoder-only Transformer architecture, and the input is The model includes an input embedding layer, a position encoding layer, a multi-head attention layer, a feedforward network, and a multi-task output head. The loss function and the Adam optimizer are defined to iteratively optimize the model parameters. When the preset maximum number of iterations is reached during continuous iterations, the iteration output model parameters are stopped to update the Transformer model. After the model training is completed, the neural response vector sequence obtained in real time is collected. The trained Transformer model is input, and the multi-head attention mechanism is used to process the time series features. The three types of brain states of the subjects are predicted through three output branches, including cognitive response prediction value, emotional fluctuation prediction value and stimulation tolerance prediction value. The obtained prediction values ​​are weighted and summed to obtain the neural state prediction score I.

[0030] By introducing the Transformer-based attention neural network structure in the real-time tDCS evaluation process, not only the parallel modeling and prediction of the multidimensional state of neural response is achieved, but also an interpretable and controllable scoring mechanism is constructed, which provides an intelligent, dynamic and quantifiable decision-making basis for the individualized regulation of the electrical stimulation effect, and is highly innovative and engineering feasible.

[0031] S4, guide the subjects to perform the task feedback test, record the behavioral output B, and form a three-variable time series data stream with the stimulus injection intensity S, neural response R, and behavioral performance B. Use Granger causal analysis to quantify the causal path strength of S→R→B; Specifically, the subjects were guided to perform the task feedback test, the behavioral output B was recorded, the stimulus injection intensity S, the neural response R, and the behavioral performance B were constructed into a three-variable time series data stream, and Granger causal analysis was used to quantify the causal path strength of S→R→B, including: Guide the subjects to perform a Go / No-Go visual recognition task. An image is presented every y seconds. The image types include target images and interference images. The subjects need to make a judgment within U seconds and respond by pressing a key. The reaction time and judgment correctness of the subjects are recorded and the temporal behavior vector B(t) is constructed. After obtaining the behavioral feedback B(t), the stimulus injection intensity sequence S(t) and the neural response sequence R(t) in the corresponding time window are immediately extracted. S(t) and R(t) are constructed by extracting the corresponding stimulus injection intensity and neural response combination in the time window. The three types of data are aligned and standardized at a unified sampling frequency to form a three-variable time series Y(t). Each component of the three-variable time series Y(t) is decomposed separately using a trous wavelet filter to obtain a detailed sequence of each variable at s scales. The detail components of the three variables at each scale are recombined to obtain the joint sequence C(t) at each scale s. From the joint sequence C(t), extract and , construct a two-layer Granger causal path model of "stimulus → nerve → behavior", including first-stage modeling and second-stage modeling; The first stage is modeled as: Granger causality analysis of stimulation on neural response was conducted, and two lagged regression models were constructed, including a model with stimulation terms and a model without stimulation terms for residual comparison:

[0032]

[0033] In the formula, and is the neural response at scale s, p is the lag order of the neural response, which is automatically selected using the AIC criterion. is the regression coefficient (historical term weight), obtained by linear fitting using the least squares method, The neural response value at scale s at the past i-th time step, is the model residual (error term), q is the stimulus lag order, is the regression coefficient of the stimulus lag term, solved by the least squares method, is the residual term of the stimulus prediction model, is the electrical stimulation current intensity signal component at the jth lag time step under scale s; Granger causal strength of stimulus on neural response according to the change in residual variance for:

[0034] In the formula, and It is a model and The residual variance of The second stage is modeled as: Granger causal analysis of neural response on behavioral performance was performed, and two behavioral regression models were constructed, including a model without neural response and a model with neural response:

[0035]

[0036] In the formula, and is the detail component of the behavioral response variable (such as RT) at scale s, and is the regression coefficient of the behavioral variable and the neural response variable, obtained through regression model training. and is the model residual term, v is the lag order of the behavioral data, determined by the Akaike information criterion, p is the lag order of the neural response, is the wavelet detail component of the behavioral response variable (such as reaction time RT) at scale s in the past i-th time step, is the wavelet detail component of the neural response (such as EEG Δf frequency band power) at the jth lag point at scale s, Calculating the Granger strength of neural responses to behavior for:

[0037] The final path validity score is calculated based on the results of the first and second stage models:

[0038] In the formula, is the effectiveness score of the closed path; The scores at all scales are integrated to obtain the final cross-scale main path score :

[0039] Where S is the number of scale layers obtained by a trous wavelet decomposition, is the most significant pathway score at multiple scales.

[0040] The standardized three-variable time series data stream is constructed by unifying the sampling frequency and standardization processing to ensure that the three types of variables have the same time scale and dimension analysis basis, which is conducive to the accuracy and stability of subsequent causal modeling. The a trous wavelet filter is used to perform multi-scale decomposition on each type of signal, which can capture the potential stimulus response characteristics layer by layer from low-frequency trends to high-frequency details, retaining both the instantaneous changes caused by high-frequency stimulation and the delayed regulatory effects within a longer time window, providing a time-frequency dual-channel information structure for causal modeling. In the first stage model, neural response regression models with and without stimulation terms are established respectively. By comparing the residual variances of the two models, the Granger causal strength of stimulation on nerves is defined, which not only determines whether the stimulation effectively activates a specific neural response channel, but also quantifies its modulation intensity, thereby forming neural effect evidence beyond the spatial electric field. In the second stage model, a lagged regression model of neural response to behavioral performance is constructed to determine whether there is an explanatory power of specific neural indicators (such as the Δf frequency band in EEG) on behavioral responses. This model can reveal whether the electrical stimulation really "penetrates" the neural pathway and converts it into an improvement in the behavioral level, which is different from the "ineffective" stimulation that only produces local neural activation but is ineffective in functional output. Finally, by integrating the causal strength scores of the two stages, a closed path score S→R→B is constructed, and then a cross-scale main path score is generated through the fusion of all scales to comprehensively measure the continuity and closed-loop nature from stimulation, neural regulation to behavioral expression. The scoring results can not only be used for effect classification, but also as a quantitative input signal for the feedback control mechanism to drive the electrode layout or the adaptive adjustment of the injection parameters, thus realizing a truly closed-loop neural regulation system.

[0041] S5. Calculate the EEG response enhancement rate and behavior improvement rate, calculate the comprehensive score of the stimulation effect based on the calculation results, the predicted value and the causal path strength, and conduct real-time evaluation of the stimulation effect; Specifically, the EEG response enhancement rate and behavior improvement rate are calculated, and the comprehensive score of the stimulation effect is calculated based on the calculation results, the predicted value and the causal path strength. The real-time evaluation of the stimulation effect refers to collecting the power spectral density o of the target frequency band under the current stimulation state and the average power spectral density of the same frequency band before stimulation. Calculate the EEG response enhancement rate O (subtract o from and divided by Get O), collect the current task execution reaction time The behavioral improvement rate F was calculated by subtracting f from the average reaction time f before the task execution before stimulation. and divide by f to get F); The obtained EEG response enhancement rate O, behavior improvement rate F and path strength score The weighted sum of the predicted score of the neural state I is used to obtain the real-time score J of the current stimulation effect; Based on ROC curve analysis, the threshold K and , and K> , compare the real-time score J with the set threshold. , the current stimulation effect is significant, maintain the current stimulation parameters (electrode combination, current intensity, frequency unchanged), continue stimulation, if , the stimulation effect is at a general level, and the fine-tuning operation is automatically performed to reduce the current injection current intensity by 0.2mA, and keep other parameters unchanged to prevent tolerance from decreasing, and enter the next cycle evaluation. If , the stimulation effect is poor, and the optimal electrode pair combination and injection current scheme are searched again to replace the current configuration and enter the next round of simulation and stimulation.

[0042] The present invention specifically introduces two advanced indicators, the neural state prediction score (I) and the causal path strength score (G), to improve the comprehensiveness and mechanism explanatory power of the stimulation effect judgment. The neural state prediction score encodes the current neural response vector sequence based on the Transformer attention network, outputs three types of prediction values ​​for the subject's cognitive state, emotional fluctuations, and stimulation tolerance, and forms the indicator I through weighted summation. This score can perceive the changing trend of the subject's neural state in real time, and provide a predictive reference for "state perception-risk avoidance" during the electrical stimulation process. The causal path strength score G is derived from the Granger causal analysis model, which models the causal dependency path between the three layers of variables of "stimulation-neural response-behavioral output", reveals whether the behavioral changes caused by electrical stimulation are completed through specific neural pathways, and quantifies the stimulation effectiveness from the causal structure level. The system sets two thresholds K and , which is used to drive parameter control strategies at different levels. Through this scoring-judgment-feedback closed-loop mechanism, the present invention can dynamically adapt to the neural response characteristics of different individuals and achieve adaptive optimization and regulation of the stimulation process.

[0043] This embodiment also provides a real-time evaluation method system for transcranial electrical stimulation effects, including: A 3D modeling module, which is used to construct an individual 3D head tissue model based on MRI images and perform electrode positioning and mapping; The electric field simulation module is used to perform electric field simulation based on the built head mold and electrode layout and use genetic algorithm to search for the optimal injection configuration; A signal acquisition module, used to implement tDCS stimulation and simultaneously collect multimodal physiological signals; The prediction module is used to construct a Transformer network for the collected neural response sequences to achieve multi-dimensional brain state prediction; The causal analysis module is used to guide the subjects to perform task feedback, extract the stimulus-response-behavior triple data flow, and perform Granger causal path modeling; The effect evaluation module is used to integrate EEG response enhancement, behavior improvement, state prediction value and causal path score to calculate the comprehensive effect score of the current stimulation.

[0044] This embodiment also provides a computer device, which is suitable for the real-time evaluation method of transcranial electrical stimulation effects, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the real-time evaluation method of transcranial electrical stimulation effects proposed in the above embodiment.

[0045] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0046] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the real-time evaluation method of transcranial electrical stimulation effect proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0047] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time evaluation method for transcranial electrical stimulation effect, characterized in that: include, Obtain the MRI data of the subject's head to construct a multi-tissue three-dimensional head model, and place HD-tDCS needle-shaped composite electrodes on the head model, targeting the key functional areas of the brain. Use the finite element method to simulate the electric field distribution, and obtain the modulation spectrum of multiple sets of electrode current combinations. Use a genetic algorithm to optimize the electrode configuration and current parameters with the goal of maximizing the modulation intensity within the ROI and minimizing the diffusion of non-target areas. Implement tDCS stimulation based on electrode configuration and parameters, collect test data in real time and construct neural response vector R after preprocessing; Construct a multi-task prediction network based on the attention mechanism to obtain the prediction value; Guide the subjects to perform the task feedback test, record the behavioral output B, and form a three-variable time series data stream with the stimulus injection intensity S, neural response R, and behavioral performance B. Use Granger causal analysis to quantify the causal path strength of S→R→B; The EEG response enhancement rate and behavior improvement rate were calculated, and the comprehensive score of the stimulation effect was calculated based on the calculation results, the predicted value, and the causal path strength to conduct a real-time evaluation of the stimulation effect.

2. The real-time evaluation method of transcranial electrical stimulation effect according to claim 1, characterized in that: The method obtains the head MRI data of the subject to construct a multi-tissue three-dimensional head model, arranges HD-tDCS needle-shaped composite electrodes on the head model, targets key functional areas of the brain, and uses the finite element method to simulate the electric field distribution, and obtains modulation spectra of multiple sets of pole current combinations, including: Collect T1-weighted structural images of the subject's head, output DICOM format image sequences, convert DICOM format to NIfTI format, unify the spatial resolution, start SPM12 software, select the "Segment" module to output five types of tissue label maps, and merge the label maps of each channel into a single label file; The label map is imported into ScanIP for voxel reconstruction and tissue-level meshing to generate a complete three-dimensional finite element model of the head with conductive properties. Activate the triangular patch mesh of the scalp area as the electrode layout surface, initialize the MNI space standard reference point, automatically project the international 10-10 system electrode points onto the scalp surface according to the head model space coordinates, use the normal projection algorithm to record the three-dimensional coordinates of each electrode, and assign a unique number to each electrode point , establish an electrode-coordinate index table, select TP9 as the reference electrode, and the remaining 60 electrode numbers constitute the excitation electrode candidate set; At each electrode point Create a circular surface electrode model in the center, set the electrode material to silver, and define it as the "current injection boundary". Set the reference electrode TP9 as the "current reference boundary". Merge all electrode models with the head mold surface mesh to form a complete simulation geometry model. Start the COMSOL Multiphysics simulation platform and import the simulation geometry model; Two independent excitation electrode pairs are activated in the COMSOL model. The current amplitude and the AC current with different injection frequencies are set for electrode pair 1 and electrode pair 2. The reference electrode TP9 is fixed as the common return electrode. During simulation, the two pairs of electrodes are independently and simultaneously injected with currents of different frequencies. In the simulation software COMSOL, the solver is started to calculate the electric field vector distribution formed by electrode pair 1 and electrode pair 2 in the brain tissue, which are recorded as , ; The solver automatically traverses all the head model voxel grid points, outputs the values ​​of the two electric field vectors at each voxel coordinate, and saves them as three-dimensional field distribution data; For all voxel positions, the modulation amplitude of each voxel position is calculated based on the electric field vector obtained by simulation, and a color visualization of the three-dimensional electric field intensity distribution is generated.

3. The real-time evaluation method of transcranial electrical stimulation effect as claimed in claim 2, characterized in that: The genetic algorithm is used to maximize the modulation intensity within the ROI and minimize the diffusion in the non-target area, and the optimization of the electrode configuration and current parameters includes: The standard brain space is used to spatially register the MRI images of the subject's head model, and a mapping relationship between the physical coordinates and the standard template space is established in the simulation model, and the spatial coordinates of the electric field distribution grid voxels are mapped to the template brain structure; Extract the mask of the right hippocampus from the standard brain template, match and extract all voxel indexes within the hippocampus mask according to the spatial registration coordinate table, record the grid number and spatial coordinates corresponding to the voxel, and form the ROI voxel set P; The ROI focusing ratio objective function D is constructed based on the electric field modulation amplitude data; Randomly select 4 non-repeating numbers from the electrode candidate set, assign the electrode numbers 1 to 4 in sequence, generate current injection values ​​for electrode pair 1 and pair 2 respectively and sample them according to uniform distribution, merge the electrode numbers and current injection values ​​into chromosomes, generate all chromosomes and store them as the initial population matrix; Configure electrode numbers and injection parameters for each chromosome, solve the electric fields generated by the two sets of electrode injections, calculate the amplitude of the interference modulation field, extract the electric field modulation value and voxel volume of each voxel point, calculate the total amount of modulation field energy in the ROI area and non-ROI area, and substitute it into formula D to obtain the fitness score of the current chromosome; All individual results form a complete chromosome library, sort them in descending order of fitness value, retain the first M chromosomes, and define the retained individuals as the next generation population and the elite subset Q, which does not participate in crossover and mutation; Through roulette wheel selection, non-elite individuals are selected as crossover parents according to fitness probability and offspring chromosomes are generated to obtain the offspring chromosome set A generated after crossover; Randomly select W individuals from the offspring for mutation. For each individual to be mutated, randomly select a strategy to adjust the parameters to obtain the offspring set Z after mutation. Combine Q, A and Z to construct a new generation of complete population, perform electric field simulation and fitness calculation on each chromosome in the new generation, stop evolution after reaching the preset maximum number of iterations, and obtain the last generation of population. Select the chromosome with the highest fitness in the last generation of population, extract the corresponding simulated electric field modulation map, and obtain the optimal electrode combination number and injection current parameters.

4. The real-time evaluation method of transcranial electrical stimulation effect according to claim 3, characterized in that: The subject is guided to perform the task feedback test, the behavioral output B is recorded, the stimulus injection intensity S, the neural response R, and the behavioral performance B are formed into a three-variable time series data stream, and Granger causal analysis is used to quantify the causal path strength of S→R→B, including: Guide the subjects to perform the Go / No-Go visual recognition task, record the subjects' reaction time and judgment correctness, and construct the temporal behavior vector B(t); After obtaining the behavioral feedback B(t), the stimulus injection intensity sequence S(t) and the neural response sequence R(t) in the corresponding time window are immediately extracted; The three types of data are aligned and standardized at a unified sampling frequency to form a three-variable time series Y(t). The atrous wavelet filter is used to decompose each component of the three-variable time series Y(t) separately to obtain the detailed sequence of each variable at s scales. The detail components of the three variables at each scale are recombined to obtain the joint sequence C(t) at each scale s, and then extracted from the joint sequence C(t) and , construct a two-layer Granger causal path model of "stimulus→neuron→behavior", including first-stage modeling and second-stage modeling; Calculate the final path validity score based on the first-stage model and the second-stage model results ; The scores at all scales are integrated to obtain the final cross-scale main path score .

5. The real-time evaluation method of transcranial electrical stimulation effect according to claim 4, characterized in that: The method of implementing tDCS stimulation based on electrode configuration and parameters, collecting test data in real time and constructing a neural response vector R after preprocessing includes: configuring the stimulation system according to the determined optimal electrode pair combination and injection parameters, collecting EEG, HbO / HbR dynamic concentration, EDA and pupil change data in real time and preprocessing them, and after the preprocessing is completed, forming a structured neural response vector R with the processing results of each modality at each moment.

6. The real-time evaluation method of transcranial electrical stimulation effect according to claim 5, characterized in that: The multi-task prediction network based on the attention mechanism is constructed to obtain the prediction value, which refers to the neural response vector sequence within the acquisition time window C. , choose the standard Encoder-only Transformer architecture, The trained Transformer model is input to obtain the cognitive response prediction value, emotional fluctuation prediction value and stimulation tolerance prediction value, and the obtained prediction values ​​are weighted and summed to obtain the neural state prediction score I.

7. The real-time evaluation method of transcranial electrical stimulation effect according to claim 6, characterized in that: The calculation of the EEG response enhancement rate and the behavior improvement rate, the calculation of the comprehensive score of the stimulation effect based on the calculation results, the predicted value and the causal path strength, and the real-time evaluation of the stimulation effect refers to the calculation of the EEG response enhancement rate O and the behavior improvement rate F; The obtained EEG response enhancement rate O, behavior improvement rate F and path strength score The weighted sum of the predicted score of the neural state I is used to obtain the real-time score J of the current stimulation effect; Set the threshold K and , and K> , compare the real-time score J with the set threshold, obtain the current stimulation effect and formulate corresponding measures.

8. A real-time evaluation system for transcranial electrical stimulation effect, based on the real-time evaluation method for transcranial electrical stimulation effect according to any one of claims 1 to 7, characterized in that: include, A 3D modeling module, which is used to construct an individual 3D head tissue model based on MRI images and perform electrode positioning and mapping; The electric field simulation module is used to perform electric field simulation based on the built head mold and electrode layout and use genetic algorithm to search for the optimal injection configuration; A signal acquisition module, used to implement tDCS stimulation and simultaneously collect multimodal physiological signals; The prediction module is used to construct a Transformer network for the collected neural response sequences to achieve multi-dimensional brain state prediction; The causal analysis module is used to guide the subjects to perform task feedback, extract the stimulus-response-behavior triple data flow, and perform Granger causal path modeling; The effect evaluation module is used to integrate EEG response enhancement, behavior improvement, state prediction value and causal path score to calculate the comprehensive effect score of the current stimulation.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the real-time evaluation method of the transcranial electrical stimulation effect described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for real-time evaluation of transcranial electrical stimulation effect according to any one of claims 1 to 7 are implemented.

Images