Prediction system, method and device for predicting efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG, processor and storage medium thereof

Abstract

This invention relates to a predictive system for the efficacy of tDCS treatment for obsessive-compulsive disorder (OCD) based on EEG. The system includes a data acquisition and processing module for acquiring resting-state EEG data of the subject; a data preprocessing module for filtering the acquired EEG data and removing signals containing artifacts; a data spectrum analysis and processing module for converting the EEG time-domain signal into a frequency-domain signal using Fast Fourier Transform and dividing it into different frequency bands; and an efficacy prediction processing module for determining the predicted efficacy of tDCS treatment based on the comparison between the subject's characteristic curve and the optimal critical point. This invention also relates to a corresponding method, apparatus, processor, and storage medium. The system, method, apparatus, processor, and storage medium of this invention represent the first method for predicting the efficacy of tDCS treatment for OCD based on EEG. The algorithm has high accuracy and helps solve the key problem of difficulty in selecting treatment methods in clinical diagnosis and treatment.

Description

Technical Field

[0001] This invention relates to the field of medical and nursing technology, and more particularly to the field of neural signal processing technology, specifically to a prediction system, method, device, processor, and computer-readable storage medium for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG. Background Technology

[0002] Obsessive-compulsive disorder (OCD) is a disabling disorder characterized by recurrent and persistent obsessive thoughts or compulsive behaviors, with a lifetime prevalence of 2.4% in my country. OCD typically begins at an early age, often in early adulthood, and can lead to widespread impairment of social functioning. Currently, first-line treatments for OCD primarily include medication and psychotherapy. Medication mainly consists of selective serotonin reuptake inhibitors (SSRIs), while psychotherapy primarily involves cognitive behavioral therapy (CBT). However, nearly 40% of patients do not respond to these treatments, and complete symptom remission is rare; residual symptoms and periodic exacerbations remain significant challenges in treatment. Therefore, identifying and optimizing treatment methods for OCD is of great value.

[0003] Transcranial direct current stimulation (tDCS) is a neuromodulation technique that has attracted much attention in the field of mental illness in recent years. It consists of a DC micro-stimulator, a cathode electrode, and an anode electrode. After the electrodes are placed on the surface of the brain, the stimulator outputs a weak DC current of 1-2 mA. The current flows from the anode to the cathode, forming a loop. Some of the current is diverted to the skin, skull, and cerebrospinal fluid, while some reaches the brain parenchyma. Stimulation at a maximum of 2 mA for 30 minutes is safe. It improves patients' symptoms and cognitive function by altering the excitability of the cerebral cortex. Our research group's study shows that the effectiveness of tDCS in treating obsessive-compulsive disorder is approximately 30%, and the treatment cycle is 2 weeks. Considering the time-consuming nature of tDCS treatment, finding reliable indicators to predict its efficacy before treatment could improve treatment efficiency and avoid additional suffering and burden for patients due to ineffective treatment. Currently, some studies have explored predictive indicators for tDCS treatment of other mental illnesses. For example, baseline excitability in the left dorsolateral prefrontal cortex can predict the efficacy of tDCS treatment for depression; the ratio of glutamate to creatine at the left temporoparietal junction can predict the efficacy of tDCS treatment for auditory hallucinations in schizophrenia. However, there are currently no studies on predictive indicators for the efficacy of tDCS treatment for obsessive-compulsive disorder.

[0004] Electroencephalography (EEG), a commonly used neurological function testing technique, can record the electrical activity of neurons. It can non-invasively record transient brain activity across the entire brain surface, offering the advantage of high temporal resolution. Compared to techniques like magnetic resonance imaging (MRI), it provides a simpler method for detecting thresholds. Patent application CN109924973A discloses "A Method and Cloud System for Identifying Pre-Epileptic EEG Signals Based on a GBDT Model," which uses EEG signals and machine learning methods to predict whether a patient is in a pre-epileptic state. However, there is currently no method for using EEG to predict the efficacy of tDCS (tight DCS) treatment for obsessive-compulsive disorder. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a predictive system, method, device, processor and computer-readable storage medium based on EEG to predict the efficacy of tDCS treatment for obsessive-compulsive disorder, which can conveniently and quickly identify the efficacy of tDCS treatment.

[0006] To achieve the above objectives, the present invention provides a prediction system, method, apparatus, processor, and computer-readable storage medium for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG, as well as the following:

[0007] This predictive system based on EEG to predict the efficacy of tDCS in treating obsessive-compulsive disorder is characterized by the following features:

[0008] The data acquisition and processing module is used to collect resting-state EEG data of subjects under specific conditions;

[0009] The data preprocessing module, connected to the data acquisition and processing module, is used to filter the acquired EEG data and remove EEG signals containing artifacts.

[0010] The data spectrum analysis and processing module, connected to the data preprocessing module, is used to convert the EEG time-domain signal into a frequency-domain signal using a Fast Fourier Transform, divide the frequency-domain signal into different frequency bands, and obtain the power of the region of interest by calculating the average value according to the electrodes named by the International Leading System (ITS).

[0011] The efficacy prediction processing module is connected to the data spectrum analysis processing module. It is used to extract the average power of the region of interest in different frequency bands and to determine the efficacy prediction of tDCS treatment based on the comparison between the subject characteristic curve and the optimal critical point.

[0012] Preferably, the frequency domain signal in the data spectrum analysis and processing module is divided according to the following frequency bands:

[0013] It includes five frequency bands: delta (1-4Hz), theta (5-7Hz), alpha (8-13Hz), beta (14-30Hz), and gamma (30-60Hz).

[0014] Preferably, the electrodes named by the International Leading System specifically include:

[0015] Electrodes FP1, FPZ, FP2, AF3, AF4, AF7 and AF8.

[0016] The method for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG using the aforementioned system is characterized by the following steps:

[0017] (1) Collect resting-state EEG data of subjects under specific sampling conditions in a specific environment;

[0018] (2) Perform artifact removal data preprocessing on the collected resting-state EEG data to obtain artifact-free individual EEG signals;

[0019] (3) Use Fast Fourier Transform to convert the EEG time-domain signal into a frequency-domain signal distributed according to different frequency bands, and obtain the power value of the region of interest;

[0020] (4) Extract the power value of the calculated region of interest and input it into the efficacy prediction processing module to perform tDCS treatment efficacy prediction processing.

[0021] Preferably, step (1) specifically includes the following steps:

[0022] (1.1) Set the data sampling rate to 1000Hz, the online reference electrode to CPz, the resistance reduction standard to below 10KΩ, and the acquisition time to 5 minutes;

[0023] (1.2) Electrode data of the 64-channel EEG cap corresponding to the 10-20 international EEG system were collected while the subject was in a quiet state.

[0024] Preferably, step (2) specifically includes the following steps:

[0025] (2.1) Remove the electrooculography (EOG) electrode signals contained in the 64-channel EEG cap;

[0026] (2.2) Use a 1Hz high-pass filter and a 100Hz low-pass filter, as well as a 48-52Hz notch filter to remove power frequency interference from the system.

[0027] (2.3) The resting-state EEG data is divided into 2-second segments, and segments containing obvious artifacts are manually checked and removed. Interpolation calculations are performed on leads with high noise.

[0028] (2.4) Independent component analysis was used to obtain independent statistical components of resting-state EEG data, and non-neuronal signals including blinking, horizontal eye movement, ECG, and muscle artifacts were removed to obtain artifact-free individual EEG signals.

[0029] More preferably, step (3) specifically includes the following steps:

[0030] (3.1) The EEG time-domain signal is converted into a frequency domain signal divided into five frequency bands: delta (1-4Hz), theta (5-7Hz), alpha (8-13Hz), beta (14-30Hz), and gamma (30-60Hz) using fast Fourier transform.

[0031] (3.2) The prefrontal electrode is taken as the region of interest, and the average power of the prefrontal electrode is obtained by calculating the average value of the FP1, FP2, AF3, AF4, AF7 and AF8 electrodes.

[0032] Preferably, step (4) specifically includes the following steps:

[0033] (4.1) The average power of the frontal electrode is input into the therapeutic effect prediction processing module for data processing;

[0034] (4.2) Compare the output value of the efficacy prediction processing module with the system critical point;

[0035] (4.3) Based on the comparison results, the efficacy of tDCS treatment can be judged.

[0036] The predictive device for realizing EEG-based prediction of the efficacy of tDCS treatment for obsessive-compulsive disorder is characterized in that the device comprises:

[0037] A processor is configured to execute computer-executable instructions;

[0038] The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction.

[0039] The predictive processor for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG is characterized in that the processor is configured to execute computer-executable instructions, which, when executed by the processor, implement the various steps of the aforementioned predictive method for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG.

[0040] The computer-readable storage medium is characterized in that it stores a computer program that can be executed by a processor to implement the various steps of the above-described predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction.

[0041] This invention utilizes an EEG-based predictive system, method, device, processor, and computer-readable storage medium to predict the efficacy of tDCS treatment for obsessive-compulsive disorder (OCD). It is the first method to predict the efficacy of tDCS treatment for OCD using EEG, achieving a sensitivity of 71.43% and a specificity of 100.00%. The algorithm demonstrates high accuracy, providing a more practical clinical tool for selecting OCD treatment methods and helping to address the key challenge of choosing the right treatment in clinical practice. Furthermore, since EEG is an objective and stable biomarker, it is not influenced by the assessor's subjective attitude compared to other rating scales; and compared to self-rating scales, it eliminates the need for patients to recall past symptoms, avoiding recall bias and facilitating wider application and promotion.

[0042] Meanwhile, the model construction uses spectral analysis to analyze EEG data, which corresponds to neuropsychological processes. By combining the algorithm with clinical significance, EEG is more direct and convenient for threshold detection than other detection methods such as MRI, increasing its clinical usability and clinical application value. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the analysis path for predicting the efficacy of tDCS in treating obsessive-compulsive disorder using electroencephalography (EEG) according to the present invention.

[0044] Figure 2 The electrode names and distribution diagrams for the electroencephalogram (EEG) acquisition of this invention are shown below. Detailed Implementation

[0045] To more clearly describe the technical content of the present invention, the following description is provided in conjunction with specific embodiments.

[0046] Before describing the embodiments of the present invention in detail, it should be noted that, in the following, the terms “comprising,” “including,” or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0047] Please see Figure 1 As shown, this predictive system for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction includes:

[0048] The data acquisition and processing module is used to collect resting-state EEG data of subjects under specific conditions;

[0049] The data preprocessing module, connected to the data acquisition and processing module, is used to filter the acquired EEG data and remove EEG signals containing artifacts.

[0050] The data spectrum analysis and processing module, connected to the data preprocessing module, is used to convert the EEG time-domain signal into a frequency-domain signal using a Fast Fourier Transform, divide the frequency-domain signal into different frequency bands, and obtain the power of the region of interest by calculating the average value according to the electrodes named by the International Leading System (ITS).

[0051] The efficacy prediction processing module is connected to the data spectrum analysis processing module. It is used to extract the average power of the region of interest in different frequency bands and to determine the efficacy prediction of tDCS treatment based on the comparison between the subject characteristic curve and the optimal critical point.

[0052] In a preferred embodiment of the present invention, the frequency domain signal in the data spectrum analysis and processing module is divided according to the following frequency bands:

[0053] It includes five frequency bands: delta (1-4Hz), theta (5-7Hz), alpha (8-13Hz), beta (14-30Hz), and gamma (30-60Hz).

[0054] In a preferred embodiment of the present invention, the electrodes named by the International Leading System specifically include:

[0055] Electrodes FP1, FPZ, FP2, AF3, AF4, AF7 and AF8.

[0056] This invention utilizes the aforementioned system to implement a predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction. The method includes the following steps:

[0057] (1) Collect resting-state EEG data of subjects under specific sampling conditions in a specific environment;

[0058] (2) Perform artifact removal data preprocessing on the collected resting-state EEG data to obtain artifact-free individual EEG signals;

[0059] (3) Use Fast Fourier Transform to convert the EEG time-domain signal into a frequency-domain signal distributed according to different frequency bands, and obtain the power value of the region of interest;

[0060] (4) Extract the power value of the calculated region of interest and input it into the efficacy prediction processing module to perform tDCS treatment efficacy prediction processing.

[0061] In a preferred embodiment of the present invention, step (1) specifically includes the following steps:

[0062] (1.1) Set the data sampling rate to 1000Hz, the online reference electrode to CPz, the resistance reduction standard to below 10KΩ, and the acquisition time to 5 minutes;

[0063] (1.2) Electrode data of the 64-channel EEG cap corresponding to the 10-20 international EEG system were collected while the subject was in a quiet state.

[0064] In a preferred embodiment of the present invention, step (2) specifically includes the following steps:

[0065] (2.1) Remove the electrooculography (EOG) electrode signals contained in the 64-channel EEG cap;

[0066] (2.2) Use a 1Hz high-pass filter and a 100Hz low-pass filter, as well as a 48-52Hz notch filter to remove power frequency interference from the system.

[0067] (2.3) The resting-state EEG data is divided into 2-second segments, and segments containing obvious artifacts are manually checked and removed. Interpolation calculations are performed on leads with high noise.

[0068] (2.4) Independent component analysis was used to obtain independent statistical components of resting-state EEG data, and non-neuronal signals including blinking, horizontal eye movement, ECG, and muscle artifacts were removed to obtain artifact-free individual EEG signals.

[0069] In a preferred embodiment of the present invention, step (3) specifically includes the following steps:

[0070] (3.1) The EEG time-domain signal is converted into a frequency domain signal divided into five frequency bands: delta (1-4Hz), theta (5-7Hz), alpha (8-13Hz), beta (14-30Hz), and gamma (30-60Hz) using fast Fourier transform.

[0071] (3.2) The prefrontal electrode is taken as the region of interest, and the average power of the prefrontal electrode is obtained by calculating the average value of the FP1, FP2, AF3, AF4, AF7 and AF8 electrodes.

[0072] In a preferred embodiment of the present invention, step (4) specifically includes the following steps:

[0073] (4.1) The average power of the frontal electrode is input into the therapeutic effect prediction processing module for data processing;

[0074] (4.2) Compare the output value of the efficacy prediction processing module with the system critical point;

[0075] (4.3) Based on the comparison results, the efficacy of tDCS treatment can be judged.

[0076] The predictive device for realizing EEG-based prediction of the efficacy of tDCS treatment for obsessive-compulsive disorder, wherein the device comprises:

[0077] A processor is configured to execute computer-executable instructions;

[0078] The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction.

[0079] The predictive processor for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG is configured to execute computer-executable instructions, which, when executed by the processor, implement the various steps of the aforementioned predictive method for predicting the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG.

[0080] The computer-readable storage medium contains a computer program that can be executed by a processor to implement the various steps of the above-described predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction.

[0081] In one specific embodiment of the present invention, the specific process of the method for treating obsessive-compulsive disorder based on EEG prediction tDCS is as follows:

[0082] 1. EEG Data Acquisition: Five minutes of resting-state EEG data were recorded in a quiet, secluded room using ANTNeuro equipment, including a WaveGuard CA-200 64-channel EEG electrode cap, an Eego signal amplifier, and a laptop computer with Eego software for recording the EEG signals. The sampling rate was 1000Hz, the online reference electrode was CPz, and the impedance reduction standard was below 10KΩ.

[0083] The 64-channel EEG electrode cap specifically refers to the 64-channel EEG cap of the 10-20 International EEG System. The locations and names of the electrodes are as follows: Figure 2 As shown.

[0084] 2. EEG Data Preprocessing: Electrooculogram (EOG) electrode signals were removed, and the data was rereferenced to the whole-brain average level. A 1Hz high-pass filter and a 100Hz low-pass filter, along with a 48–52Hz notch filter, were used to remove power line interference. Resting-state EEG data was segmented into 2-second intervals. Segments containing obvious artifacts were manually inspected and removed. Interpolation was performed on leads with high noise levels. Independent component analysis was used to obtain independent statistical components, removing non-neuronal signals such as blinking, horizontal eye movement, ECG, and muscle artifacts, ultimately yielding an artifact-free EEG signal.

[0085] 3. EEG Spectrum Analysis: The EEG time-domain signal was converted into a frequency-domain signal using Fast Fourier Transform (FFT), and divided into five frequency bands: delta (1–4 Hz), theta (5–7 Hz), alpha (8–13 Hz), beta (14–30 Hz), and gamma (30–60 Hz). Prefrontal cortex electrodes were selected, namely FP1, FP2, AF3, AF4, AF7, and AF8 (electrode names are based on the 10-20 International Lead System, see appendix). Figure 2 The region of interest (ROI) is calculated from the average power of the seven electrodes for each frequency band.

[0086] 4. Efficacy prediction: Using the power of different frequency bands of the prefrontal electrode as input and the efficacy after tDCS treatment as output, a predictive model was constructed. The effectiveness of the model was evaluated using the receiver operating characteristic curve and the area under the curve. The sensitivity of the prefrontal electrode alpha power as a predictor was 71.43%, the specificity was 100.00%, the area under the curve was 0.865, and the optimal critical point was 0.714.

[0087] The process is as follows: the average power of the extracted prefrontal electrode is input into the efficacy prediction processing module, and the output value is compared with the optimal critical point to determine the possible efficacy of tDCS treatment.

[0088] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0089] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution device.

[0090] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0091] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0092] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0093] In the description of this specification, references to terms such as "an embodiment," "some embodiments," "example," "specific example," or "embodiment," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0094] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0095] This invention utilizes an EEG-based predictive system, method, device, processor, and computer-readable storage medium to predict the efficacy of tDCS treatment for obsessive-compulsive disorder (OCD). It is the first method to predict the efficacy of tDCS treatment for OCD using EEG, achieving a sensitivity of 71.43% and a specificity of 100.00%. The algorithm demonstrates high accuracy, providing a more practical clinical tool for selecting OCD treatment methods and helping to address the key challenge of choosing the right treatment in clinical practice. Furthermore, since EEG is an objective and stable biomarker, it is not influenced by the assessor's subjective attitude compared to other rating scales; and compared to self-rating scales, it eliminates the need for patients to recall past symptoms, avoiding recall bias and facilitating wider application and promotion.

[0096] Meanwhile, the model construction uses spectral analysis to analyze EEG data, which corresponds to neuropsychological processes. By combining the algorithm with clinical significance, EEG is more direct and convenient for threshold detection than other detection methods such as MRI, increasing its clinical usability and clinical application value.

[0097] In this specification, the invention has been described with reference to specific embodiments thereof. However, it will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. Therefore, the specification and drawings should be considered illustrative rather than restrictive.

Claims

1. A predictive system based on EEG to predict the efficacy of tDCS in treating obsessive-compulsive disorder, characterized in that, The system includes: The data acquisition and processing module is used to collect resting-state EEG data of subjects under specific conditions; The data preprocessing module, connected to the data acquisition and processing module, is used to filter the acquired EEG data and remove EEG signals containing artifacts. The data spectrum analysis and processing module, connected to the data preprocessing module, is used to convert the EEG time-domain signal into a frequency-domain signal using a Fast Fourier Transform, divide the frequency-domain signal into different frequency bands, and obtain the power of the region of interest by calculating the average value according to the electrodes named by the International Leading System (ITS). The efficacy prediction processing module, connected to the data spectrum analysis processing module, is used to extract the average power of the region of interest in different frequency bands. The acquired average power is input to the efficacy prediction processing module for data processing. The output value of the efficacy prediction processing module is then compared with the optimal critical point to determine the efficacy prediction of tDCS treatment. Specifically: Using the power of different frequency bands of the frontal electrode as input and the efficacy of tDCS treatment as output, a predictive model was constructed, and the effect of the model was evaluated by the subject characteristic curve and the area under the curve. The electrodes named by the International Leading System specifically include: Electrodes FP1, FPZ, FP2, AF3, AF4, AF7 and AF8.

2. The predictive system for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction according to claim 1, characterized in that, The frequency domain signals in the data spectrum analysis and processing module are divided according to the following frequency bands: It includes five frequency bands: delta (1–4 Hz), theta (5–7 Hz), alpha (8–13 Hz), beta (14–30 Hz), and gamma (30–60 Hz).

3. A predictive device for realizing EEG-based prediction of the efficacy of tDCS treatment for obsessive-compulsive disorder, characterized in that, The device includes: A processor is configured to execute computer-executable instructions; A memory storing one or more computer-executable instructions, which, when executed by the processor, implement the following steps of a predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction: (1) Collect resting-state EEG data of subjects under specific sampling conditions in a specific environment; (1.1) Set the data sampling rate to 1000Hz, the online reference electrode to CPz, the resistance reduction standard to below 10KΩ, and the acquisition time to 5 minutes; (1.2) While the subject was in a quiet state, electrode data of the 64-channel EEG cap corresponding to the 10-20 international EEG system were collected; (2) Perform artifact removal data preprocessing on the collected resting-state EEG data to obtain artifact-free individual EEG signals; (2.1) Remove the electrooculography (EOG) electrode signals contained in the 64-channel EEG cap; (2.2) Use a 1Hz high-pass filter and a 100Hz low-pass filter, as well as a 48-52Hz notch filter to remove power frequency interference from the system; (2.3) The resting-state EEG data is divided into 2-second segments, and segments containing obvious artifacts are manually checked and removed. Interpolation calculations are performed on leads with high noise. (2.4) Independent component analysis was used to obtain independent statistical components of resting-state EEG data, and non-neuronal signals including blinking, horizontal eye movement, ECG, and muscle artifacts were removed to obtain artifact-free individual EEG signals; (3) Use Fast Fourier Transform to convert the EEG time-domain signal into a frequency-domain signal distributed according to different frequency bands, and obtain the power value of the region of interest; (3.1) The EEG time-domain signal is converted into a frequency domain signal divided into five frequency bands: delta (1-4 Hz), theta (5-7 Hz), alpha (8-13 Hz), beta (14-30 Hz), and gamma (30-60 Hz) using fast Fourier transform. (3.2) The prefrontal electrode is taken as the region of interest, and the average power of the prefrontal electrode is obtained by calculating the average values ​​of the FP1, FP2, AF3, AF4, AF7 and AF8 electrodes. (4) Extract the power value of the region of interest and input it into the efficacy prediction processing module to perform tDCS treatment efficacy prediction processing; (4.1) The average power of the frontal electrode is input into the therapeutic effect prediction processing module for data processing; (4.2) Compare the output value of the efficacy prediction processing module with the optimal critical point; (4.3) Based on the comparison results, the efficacy of tDCS treatment can be judged.

4. A predictive processor based on EEG prediction of the efficacy of tDCS in treating obsessive-compulsive disorder, characterized in that, The processor is configured to execute computer-executable instructions, which, when executed by the processor, are used to implement the following steps of a predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG prediction: (1) Collect resting-state EEG data of subjects under specific sampling conditions in a specific environment; (1.1) Set the data sampling rate to 1000Hz, the online reference electrode to CPz, the resistance reduction standard to below 10KΩ, and the acquisition time to 5 minutes; (1.2) While the subject was in a quiet state, electrode data of the 64-channel EEG cap corresponding to the 10-20 international EEG system were collected; (2) Perform artifact removal data preprocessing on the collected resting-state EEG data to obtain artifact-free individual EEG signals; (2.1) Remove the electrooculography (EOG) electrode signals contained in the 64-channel EEG cap; (2.2) Use a 1Hz high-pass filter and a 100Hz low-pass filter, as well as a 48-52Hz notch filter to remove power frequency interference from the system; (2.3) The resting-state EEG data is divided into 2-second segments, and segments containing obvious artifacts are manually checked and removed. Interpolation calculations are performed on leads with high noise. (2.4) Independent component analysis was used to obtain independent statistical components of resting-state EEG data, and non-neuronal signals including blinking, horizontal eye movement, ECG, and muscle artifacts were removed to obtain artifact-free individual EEG signals; (3) Use Fast Fourier Transform to convert the EEG time-domain signal into a frequency-domain signal distributed according to different frequency bands, and obtain the power value of the region of interest; (3.1) The EEG time-domain signal is converted into a frequency domain signal divided into five frequency bands: delta (1-4 Hz), theta (5-7 Hz), alpha (8-13 Hz), beta (14-30 Hz), and gamma (30-60 Hz) using fast Fourier transform. (3.2) The prefrontal electrode is taken as the region of interest, and the average power of the prefrontal electrode is obtained by calculating the average values ​​of the FP1, FP2, AF3, AF4, AF7 and AF8 electrodes. (4) Extract the power value of the region of interest and input it into the efficacy prediction processing module to perform tDCS treatment efficacy prediction processing; (4.1) The average power of the frontal electrode is input into the therapeutic effect prediction processing module for data processing; (4.2) Compare the output value of the efficacy prediction processing module with the optimal critical point; (4.3) Based on the comparison results, the efficacy of tDCS treatment can be judged.

5. A computer-readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the following steps of a predictive method for the efficacy of tDCS treatment for obsessive-compulsive disorder based on EEG: (1) Collect resting-state EEG data of subjects under specific sampling conditions in a specific environment; (1.1) Set the data sampling rate to 1000Hz, the online reference electrode to CPz, the resistance reduction standard to below 10KΩ, and the acquisition time to 5 minutes; (1.2) While the subject was in a quiet state, electrode data of the 64-channel EEG cap corresponding to the 10-20 international EEG system were collected; (2) Perform artifact removal data preprocessing on the collected resting-state EEG data to obtain artifact-free individual EEG signals; (2.1) Remove the electrooculography (EOG) electrode signals contained in the 64-channel EEG cap; (2.2) Use a 1Hz high-pass filter and a 100Hz low-pass filter, as well as a 48-52Hz notch filter to remove power frequency interference from the system; (2.3) The resting-state EEG data is divided into 2-second segments, and segments containing obvious artifacts are manually checked and removed. Interpolation calculations are performed on leads with high noise. (2.4) Independent component analysis was used to obtain independent statistical components of resting-state EEG data, and non-neuronal signals including blinking, horizontal eye movement, ECG, and muscle artifacts were removed to obtain artifact-free individual EEG signals; (3) Use Fast Fourier Transform to convert the EEG time-domain signal into a frequency-domain signal distributed according to different frequency bands, and obtain the power value of the region of interest; (3.1) The EEG time-domain signal is converted into a frequency domain signal divided into five frequency bands: delta (1-4 Hz), theta (5-7 Hz), alpha (8-13 Hz), beta (14-30 Hz), and gamma (30-60 Hz) using fast Fourier transform. (3.2) The prefrontal electrode is taken as the region of interest, and the average power of the prefrontal electrode is obtained by calculating the average values ​​of the FP1, FP2, AF3, AF4, AF7 and AF8 electrodes. (4) Extract the power value of the region of interest and input it into the efficacy prediction processing module to perform tDCS treatment efficacy prediction processing; (4.1) The average power of the frontal electrode is input into the therapeutic effect prediction processing module for data processing; (4.2) Compare the output value of the efficacy prediction processing module with the optimal critical point; (4.3) Based on the comparison results, the efficacy of tDCS treatment can be judged.

Images