A treatment monitoring system for anhedonia in patients with depression

Abstract

The present invention discloses a treatment monitoring system for anhedonia in depressive patients, belonging to the field of treatment monitoring for anhedonia in depressive patients, and comprising an acquisition module, a test module, a source localization module, an analysis module and a treatment module; the acquisition module is used for acquiring patient information and electrophysiological signals of the patient's brain; the test module is used for testing the patient by applying a gambling task with doors to obtain an analysis result of the gambling task with doors; the source localization module is used for localizing abnormal brain regions related to anhedonia according to the electrophysiological signals and the analysis result of the gambling task with doors, and organizing and labeling them as source localization data; the analysis module is used for monitoring and analyzing the source localization data to generate a dynamic brain region map; determining each abnormal brain region, identifying the brain region characteristics of each abnormal brain region, merging each abnormal brain region to obtain a monitored brain region; integrating each corresponding data into a monitoring result; the treatment module is used for formulating and adjusting a treatment plan in combination with the monitoring result, and treating the patient based on the treatment plan.

Description

Technical Field

[0001] The present invention belongs to the field of treatment monitoring for anhedonia in depressive patients, and specifically relates to a treatment monitoring system for anhedonia in depressive patients. Background Art

[0002] Anhedonia is one of the most destructive symptoms in depression, manifested as the patient losing interest or pleasure in usually pleasant activities. It is not only a core symptom of depression but also generally shows extremely poor response to traditional antidepressant treatments, becoming a major problem in treatment. Although anhedonia seriously affects the quality of life of patients, existing clinical assessment methods have significant deficiencies in identifying and quantifying this symptom. Especially during individual treatment, dynamically and accurately monitoring the changes in anhedonia is crucial for optimizing treatment strategies. Anhedonia is closely related to the abnormal function of the brain reward system. To effectively treat depression, there is an urgent need for a method that can precisely locate specific brain regions related to anhedonia in the brains of depressive patients and dynamically monitor them. By precisely locating and real-time monitoring the functional changes in these brain regions, clinicians can better evaluate the treatment effect, formulate individualized treatment plans, and significantly improve the accuracy and effectiveness of treatment.

[0003] Based on this, to solve the above problems, the present invention provides a treatment monitoring system for anhedonia in depressive patients. Summary of the Invention

[0004] To solve the problems existing in the above solutions, the present invention provides a treatment monitoring system for anhedonia in depressive patients.

[0005] The object of the present invention can be achieved through the following technical solutions:

[0006] A treatment monitoring system for anhedonia in depressive patients, comprising an acquisition module, a test module, a source localization module, an analysis module, and a treatment module;

[0007] The acquisition module is used to acquire patient information and the electrophysiological signals of the patient's brain.

[0008] Further, the acquisition method of the electrophysiological signals is: real-time acquisition through an EEG of a 128-electrode array to obtain the corresponding electrophysiological signals.

[0009] The test module is used to test the patient using the Iowa Gambling Task to obtain the analysis result of the Iowa Gambling Task; the Iowa Gambling Task is a decision-making task.

[0010] Further, the test method includes:

[0011] The subject patients face two doors, behind each of which there is a reward or a loss; the reward is that in the corresponding round, the patient's choice brings a virtual reward, which is used to evaluate the patient's brain response to pleasure; the punishment is that in the corresponding round, the patient's choice leads to a virtual loss, which is used to detect the neural response to punishment or pain;

[0012] The subject patients need to choose one door, and then the reward result behind the door chosen by the patient is presented; the test task includes a certain number of trials, and the probability and quantity of the reward vary randomly among the trials.

[0013] Furthermore, during the process of the patient performing the door gambling task, the test module records the patient's behavioral data in real time. The behavioral data includes the door selection, reaction time, and reward result of each trial.

[0014] The source localization module is used to localize the abnormal brain regions related to anhedonia according to the electrophysiological signals and the analysis results of the door gambling task, and organize and label them as source localization data.

[0015] The analysis module is used to monitor and analyze the source localization data, perform data preprocessing on the source localization data, and generate a dynamic brain region map based on the preprocessed source localization data; the dynamic brain region map should display the activity patterns of each key brain region at different time points; determine each abnormal brain region, identify the brain region characteristics of each abnormal brain region, including spatial location, activity intensity, and functional connection; merge each abnormal brain region to obtain the monitored brain region; integrate the corresponding data into the monitoring result.

[0016] Furthermore, the method for determining the monitored brain region includes:

[0017] Monitor and evaluate each abnormal brain region according to the source localization data to obtain the corresponding monitoring and evaluation results. The monitoring and evaluation results include the lack of corresponding electrophysiological characteristics and normal monitoring;

[0018] Merge the adjacent abnormal brain regions with the monitoring and evaluation results of lacking corresponding electrophysiological characteristics to obtain the monitored brain region.

[0019] Furthermore, the method for monitoring and evaluating each abnormal brain region according to the source localization data includes:

[0020] Establish a monitoring and evaluation model, and the expression of the monitoring and evaluation model is: ;

[0021] In the formula: q is the input data, the input data is the corresponding source localization data, and the output data is the monitoring and evaluation value YG(q);

[0022] Analyze the source localization data through the monitoring and evaluation model to obtain the monitoring and evaluation values corresponding to the positions of each brain region;

[0023] Determine the monitoring and evaluation results based on each monitoring and evaluation value.

[0024] The treatment module is used to formulate and adjust the treatment plan in combination with the monitoring results, and treat the patient based on the treatment plan.

[0025] Furthermore, the method for formulating and adjusting the treatment plan includes:

[0026] Set the initial treatment plan according to the monitoring results; treat the patient according to the initial treatment plan; during the treatment process, monitor the changes in the brain region activities and task performances of the patient in real time, integrate them into monitoring data, compare the monitoring data with the preset treatment goals, and evaluate the immediate treatment effect;

[0027] After the end of each treatment cycle, evaluate the treatment effect of the patient to obtain treatment evaluation data;

[0028] Dynamically adjust the initial treatment plan according to the treatment evaluation data, and the adjustment contents include stimulation parameters, treatment cycle, and frequency.

[0029] Furthermore, the method for evaluating the treatment effect of the patient includes:

[0030] Obtain the treatment expectation, and determine each treatment index according to the treatment expectation; obtain the change data of the patient after the treatment cycle;

[0031] Extract the features of the change data according to each treatment index to obtain the completion index corresponding to each treatment index;

[0032] Evaluate each treatment index according to each completion index to determine the completion degree of each treatment index;

[0033] According to the formula Calculate the corresponding comprehensive evaluation value;

[0034] In the formula: PW is the comprehensive evaluation value; i represents the corresponding treatment index, i = 1, 2,..., n, and n is a positive integer; βi is the proportional coefficient of the corresponding treatment index, and the value range is 0 < βi < 1; WDi is the completion degree of the corresponding treatment index;

[0035] Integrate the comprehensive evaluation value and the completion degree of each treatment index into the treatment evaluation data.

[0036] Furthermore, the treatment evaluation data also includes supplementary evaluation data, and the method for determining the supplementary evaluation data includes:

[0037] Determine each change item, establish a change evaluation model according to each change item, and the expression of the change evaluation model is: ;

[0038] Where: cj is the input data, j represents the corresponding change item, j = 1, 2, ……, m, and m is a positive integer; the input data is variable data; the output data is the change evaluation value PB(cj) of the corresponding change item.

[0039] Identify each treatment index, and screen each change item according to each treatment index.

[0040] Analyze the variable data through a change evaluation model to obtain the change evaluation values of each change item after screening.

[0041] Mark the change items with non-zero change evaluation values as index supplement items; determine the supplement results of each index supplement item according to the change evaluation values; integrate each index supplement item and the corresponding supplement results into supplement evaluation data.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] Through the mutual cooperation among the acquisition module, the test module, the source localization module, the analysis module and the treatment module, intelligent monitoring of the anhedonia treatment of depressive patients is realized.

[0044] The source localization technology of EEG has been applied in research, but mostly for offline analysis, rather than real-time feedback to the treatment system. Most relevant patents and research focus on the monitoring of the overall brain wave activity, and do not involve the real-time application of source localization. The present invention can accurately locate the brain region activities related to the anhedonia symptoms of depression through high-density EEG and source localization algorithms, providing higher spatial resolution than traditional methods; capture the neural electrical activities related to the reward mechanism in real time, quantify and monitor anhedonia by using the ERP components in the go / no-go gambling experiment, and provide direct biomarkers for individualized treatment; through analyzing the changes in the EEG activities of patients during the treatment process, dynamically adjust the treatment plan to improve the treatment effect.

[0045] Although EEG is used for the evaluation of treatment effects, most existing systems are based on fixed monitoring modes and cannot adjust the treatment plan in real time according to the brain region activities of individual patients. This system adjusts the treatment plan according to the changes in brain region activities and the ERP signals of the go / no-go gambling task, especially for physical treatments such as rTMS. This personalized feedback mechanism enables the treatment process of each patient to be dynamically adjusted to maximize the curative effect, and is especially suitable for the individualized treatment optimization of anhedonia patients. After understanding the specific brain regions with abnormal neural activities, neuroregulation techniques can be more effectively applied to specifically regulate the brain regions with abnormal activities and restore the normal reward processing function to relieve the symptoms of depression. It can not only improve the treatment effect, but also reduce unnecessary drug use, and has broad market prospects. Brief Description of the Drawings

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0047] Figure 1 This is the principle block diagram of the present invention. Specific implementation manners

[0048] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0049] As Figure 1 shown, a monitoring system for treating anhedonia in patients with depression includes an acquisition module, a test module, a source localization module, an analysis module, and a treatment module;

[0050] The acquisition module is used to acquire patient information and electrophysiological signals of the patient's brain;

[0051] Acquire patient information:

[0052] Personal basic information: Acquire basic information such as the patient's name, gender, age, height, weight, and occupation to ensure adaptive adjustment according to individual differences in personalized treatment.

[0053] Privacy protection mechanism: The system ensures the secure storage and transmission of the patient's privacy data through encryption technology and strictly complies with data protection regulations.

[0054] Medical history and medical background: The system acquires the patient's complete medical history, including past mental health status, duration of anhedonia, course of disease, past treatment history (such as drug treatment, electrostimulation treatment, etc.), and past electroencephalogram or brain imaging data (such as MRI, fMRI).

[0055] Family medical history: Record the patient's family mental illness history and related chronic diseases (such as depression, anxiety disorder, etc.) to understand whether the patient has genetic factors.

[0056] Psychological assessment tools and scales: The psychological assessment acquisition unit integrates a variety of standardized psychological assessment tools to comprehensively evaluate the patient's mental health status and the severity of anhedonia. These assessment tools can be used regularly during the acquisition process to dynamically track changes in the patient's mental state.

[0057] Anhedonia assessment: Snaith-Hamilton Pleasure Scale (SHAPS): It is used to evaluate the degree of loss of daily pleasant experiences in patients. This scale can be used to quantitatively assess the severity of anhedonia and serve as a reference point for treatment effects. Anhedonia Symptoms Checklist (ASC): It is used to further refine the assessment of anhedonia symptoms and distinguish between social anhedonia and physical anhedonia. Depression and anxiety assessment: Hamilton Depression Scale (HAM-D), Beck Depression Inventory (BDI). Generalized Anxiety Disorder 7-item Scale (GAD-7): It assesses whether patients have anxiety symptoms and their severity, and understands the potential impact of anxiety on brain electrical activity and anhedonia. Other psychological state assessments: Montreal Cognitive Assessment (MoCA): It screens cognitive function and assesses the possible impact of depression and anhedonia on cognitive abilities such as memory, attention, and executive function. Quality of life assessment: Use the World Health Organization Quality of Life Assessment Scale (WHOQOL-BREF) to understand the impact of anhedonia on the overall quality of life of patients.

[0058] Electrophysiological signals:

[0059] Acquisition is performed using 128 electrodes to ensure high spatial resolution to capture the complex activity patterns of the brain.

[0060] During the acquisition process, filtering and denoising are carried out to exclude the interference of electrocardiogram, electromyogram, and environmental noise, thereby extracting clear electroencephalogram signals.

[0061] The acquisition module should also integrate signal preprocessing functions, including time-frequency analysis, artifact detection and correction, to ensure the accuracy of the data.

[0062] The test module is used to test patients using the Door Gambling Task;

[0063] 1. The Door Gambling Task is a classic decision-making task that can effectively activate brain regions related to pleasure and reward, such as the ventral striatum, orbitofrontal cortex, etc. In the task, the subject faces two doors, and behind each door is hidden a reward (positive feedback) or a loss (negative feedback). The subject needs to choose a door, and then the system will present the reward result behind that door. The task contains a certain number of trials (such as 100 trials), and the probability and quantity of rewards vary randomly between trials.

[0064] Reward and punishment settings:

[0065] Reward: In some rounds, the patient's choice will bring virtual rewards (such as point rewards), and this positive feedback is used to evaluate the patient's brain response to pleasure.

[0066] Punishment: In other rounds, the patient's choices may lead to virtual losses, and this negative feedback is used to detect neural responses to punishment or pain.

[0067] Feedback randomness: Rewards and punishments occur randomly, and this uncertainty aims to mimic real-life decision-making situations and make the patient's neural responses more natural.

[0068] 2. Neural responses and ERP signal capture:

[0069] The test module quantifies the patient's neural responses to pleasure or aversion by capturing ERP components related to task feedback, particularly the feedback negativity (FRN) and P300 waveforms.

[0070] Feedback negativity (FRN): When the patient receives negative feedback (i.e., losses or punishments), the FRN is typically generated within 200 - 300 milliseconds after the feedback appears. It mainly reflects the brain's response when realizing an error or negative outcome and is an important signal for evaluating anhedonia.

[0071] Abnormality of FRN: Depressed patients tend to be relatively insensitive or lack corresponding neural activities to negative feedback. Therefore, by capturing the FRN, the degree of anhedonia in patients can be evaluated.

[0072] P300 wave: The P300 wave is typically generated within 300 - 600 milliseconds after the appearance of a reward or positive feedback. It reflects the brain's attention to novel events and positive emotional responses and is an indicator of neural responses to pleasure.

[0073] Abnormality of P300: Anhedonic patients tend to lack a strong response to rewards, with a reduced amplitude or delay of the P300 wave, which is a key signal for the system to evaluate the patient's response to positive feedback.

[0074] 3. Data acquisition and real-time synchronization:

[0075] Signal acquisition process:

[0076] EEG acquisition: During the door gambling task, the system real-time acquires EEG data through a high-density EEG of 128 electrode arrays to ensure capturing ERP signals related to task feedback.

[0077] Trigger synchronization: The system ensures the matching of the presentation of each feedback with the acquisition of EEG signals through a timestamp synchronization mechanism. Whenever the task provides positive or negative feedback, the trigger signal is immediately marked to facilitate the precise positioning of the starting point of the ERP waveform in subsequent data analysis.

[0078] Data annotation: After each round of the task, the system annotates the feedback of each task round (reward / punishment) and the corresponding EEG responses. These data are used for source localization and input to the subsequent analysis module.

[0079] 4. Anhedonia assessment:

[0080] Assessment mechanism:

[0081] ERP analysis: The test module preprocesses the recorded EEG data (such as filtering, artifact removal, etc.), and then conducts ERP analysis. ERP reflects the electrophysiological response of the brain to specific events or stimuli and is closely related to the cognitive processing process. The key events in the door gambling task include the presentation of the door, the selection of the door, the presentation of the reward, etc. Analyzing the ERP components related to these events (such as P300, FRN, etc.) can evaluate the cognitive functions of patients such as attention allocation, decision-making, and hedonic processing.

[0082] Collection of ERP data: After completing the collection of clinical data, the participants were required to complete the door gambling experiment in a dimly lit, soundproof, and electrically shielded room. The specific experimental procedure is as follows:

[0083] Formal experiment:

[0084] (1) The subject sits in a quiet shielded room, wears an electrode cap, adjusts the seat height and screen distance, and maintains a comfortable posture.

[0085] (2) Start the gambling task program, and the tested patient completes the gambling task according to the instructions:

[0086] The door task consists of three blocks of 20 trials each (60 trials in total). At the beginning of each trial, images of two identical doors are presented. The participants are instructed to select the left or right door by clicking the left or right button. For example, the participants are told that they can win 1 point or lose 0.5 points in each trial, and they will receive a reward corresponding to the total points at the end of the task. The images of the doors will be continuously displayed until the participants select a door. Subsequently, a fixed cross is displayed for 1000 milliseconds, and then a feedback stimulus is displayed for 2000 milliseconds. The feedback stimulus uses a green arrow pointing up to indicate winning a reward and a red arrow pointing down to indicate losing. Then, another fixed cross is displayed for 1500 milliseconds, and then it prompts "Click to enter the next round" until the participants click the button to start the next trial. The trials of winning a reward and losing have the same probability and are presented in a pseudo-random manner.

[0087] (3) During the gambling task, the ERP instrument continuously records the electroencephalogram activity of the subject and marks the time points of stimulus presentation and response.

[0088] (4) After the task is completed, the subjective feelings of the tested patient are asked to understand whether they are aware of the winning probability and to evaluate the task difficulty, reward attractiveness, etc.

[0089] Data processing and analysis:

[0090] (1) Preprocess the EEG data using ERP analysis software, including steps such as filtering, segmentation, baseline correction, and averaging, to obtain the ERP waveforms under each condition.

[0091] (2) Extract the amplitude and latency indexes of ERP components, such as FRN, P300, etc., according to appropriate time windows and electrode points.

[0092] (3) Conduct statistical analysis on the behavioral data and ERP data, compare the differences in behavioral performance and EEG activities between the depressive group and the control group, and explore the relationship between depressive symptoms and reward processing.

[0093] The system evaluates the response intensity and time of the patient to rewards and punishments by comparing the patient's ERP waveforms (especially FRN and P300) with the typical neural responses of the normal population.

[0094] Quantitative evaluation index: The system calculates the amplitudes, latencies, and frequency changes of FRN and P300, and quantitatively evaluates the degree of anhedonia of the patient by comparing with the patient's previous data or the data of the control group.

[0095] Neural abnormality identification: When the system detects a decrease in the P300 wave when the patient faces a reward, or a decrease in the FRN wave when the patient faces a punishment, combined with the brain region activation situation of source localization, the neural activity abnormal regions related to anhedonia can be identified.

[0096] Monitoring of mental health changes: Through long-term task tests, the system can dynamically track the changes in the patient's anhedonia, provide a basis for follow-up for doctors, and judge whether the treatment effect is significant.

[0097] Recording of behavioral data: During the patient's performance of the door gambling task, the test module records the patient's behavioral data in real time, including the door selection, reaction time, reward result, etc. of each trial. These behavioral data can be used to evaluate the patient's decision-making ability, reward sensitivity, and hedonic experience, and provide a reference for the subsequent evaluation of the treatment effect.

[0098] Data quality control: To ensure the quality of the test data, the test module sets a series of quality control measures. For example, conduct EEG electrode impedance inspection before the task starts to ensure that the impedance of each electrode is within an appropriate range; monitor the EEG signal quality in real time during the task, and if there are large-amplitude artifacts or signal loss, prompt to re-collect in time; monitor the patient's behavioral performance, such as too long or too short reaction time, and prompt the patient to stay focused and cooperate, etc.

[0099] This module supports longitudinal analysis of multiple test results.

[0100] The source localization module is the core component of the present invention, which is mainly used to locate abnormal brain areas related to anhedonia, and provide key neurophysiological basis for subsequent treatment monitoring and effect evaluation. The source localization module is based on high-density EEG data and ERP analysis results of the gated gambling task, and adopts source localization algorithm and brain area merging technology.

[0101] The source localization module uses a standardized template and the low-resolution electromagnetic tomography (LORETA) function of Brain Vision Analyzer 2.2 to perform source tracing analysis on the pre-processed EEG data.

[0102] The steps of source analysis are as follows: 1) Establish regions of interest (ROI): The establishment of ROI depends on the source analysis file provided by Brain Vision Analyzer 2.2. 2) Calculate the current source density of each ROI: Select current density in the LORETA interface and calculate the current density value in each ROI; 3) Output: Select the general data export module on the LORETA node to export the current density value of each ROI at each time point; 4) Import into MATLAB: The source data after the above steps are imported into MATLAB using the EEGLAB toolbox based on MATLAB R2023a for subsequent ERP and functional connectivity analysis.

[0103] The analysis module is the core component of the system. Its main function is to determine the brain areas related to anhedonia and their dynamic changes through long-term monitoring and comparative analysis of source location data, and to help doctors make personalized adjustments to treatment plans. The following is a detailed description of the analysis module:

[0104] 1. Data preprocessing:

[0105] Perform quality control on the data output by the source localization module to remove artifacts and noise data.

[0106] Data standardization was performed to ensure comparability between different patients.

[0107] Align data in time and space to allow long-term monitoring and comparative analysis.

[0108] 2. Dynamic brain area map generation:

[0109] Generate individualized dynamic brain area maps based on the preprocessed source localization data.

[0110] The atlas should include key brain regions related to anhedonia, such as the ventromedial prefrontal cortex (BA11) and the insula (BA13), etc.

[0111] The dynamic brain region atlas should show the activity patterns of each key brain region at different time points (such as different stages of the door gambling task).

[0112] Provide an intuitive visual report to facilitate doctors' quick understanding of the changes in the patient's brain region activities.

[0113] 3. Statistical analysis:

[0114] Conduct statistical analysis on the source localization results to determine the abnormal brain regions related to anhedonia. Use non-parametric statistical methods based on permutation tests, such as the threshold-free cluster enhancement (TFCE) algorithm, to perform voxel-by-voxel comparisons on the source space activity maps of the patient group and the normal control group, and obtain brain regions with significant differences. These brain regions may show increased or decreased activities, reflecting the neural basis of anhedonia in depressed patients.

[0115] Feature extraction:

[0116] Extract brain region features related to anhedonia from the source localization results, such as the spatial location, activity intensity, functional connectivity, etc. of the abnormal brain regions. Use graph theory analysis methods to calculate network properties such as centrality, clustering coefficient, and efficiency of each brain region, and characterize the importance and interconnection patterns of brain regions in the anhedonia processing network. In addition, temporal and frequency domain features of brain region activities, such as amplitude, latency, power spectrum, etc., can also be extracted to comprehensively characterize the spatio-temporal dynamics of brain region activities.

[0117] Feature selection:

[0118] Use machine learning algorithms, such as recursive feature elimination (RFE) or regularization methods (such as Lasso, Ridge), to select the most discriminative and stable feature subsets from high-dimensional brain region features. These features show significant differences between the patient group and the control group, and have good repeatability under different datasets and test conditions, and can be used as potential biomarkers for anhedonia.

[0119] Abnormal brain region identification:

[0120] Based on the selected feature subsets, train machine learning models, such as support vector machines (SVM) or random forests (RF), to achieve automatic identification of brain regions related to anhedonia. Use methods such as cross-validation to evaluate the generalization performance of the model, and ensure that abnormal brain regions can be accurately identified on new patient data. The identification results of abnormal brain regions can be used to guide subsequent treatment monitoring and efficacy evaluation.

[0121] 4. Merging and classification of monitored brain regions:

[0122] According to the characteristics of brain region activities, adjacent and functionally similar brain regions are merged to simplify the analysis.

[0123] The determination method of the monitored brain regions includes:

[0124] Based on the source localization data, each abnormal brain region is monitored and evaluated, that is, to evaluate whether the electrophysiological characteristics related to anhedonia are missing in the corresponding brain region location, that is, to determine whether it is lacking according to the change of ERP signal during the door gambling task; obtain the corresponding monitoring and evaluation results, and the monitoring and evaluation results include the lack of corresponding electrophysiological characteristics and normal monitoring;

[0125] Adjacent abnormal brain regions with monitoring and evaluation results showing the lack of corresponding electrophysiological characteristics are merged to obtain the monitored brain regions.

[0126] The above data is sorted into monitoring results, which are different from the monitoring and evaluation results, and mainly include the relevant data required in the subsequent treatment module.

[0127] In one embodiment, the method for monitoring and evaluating each abnormal brain region based on the source localization data includes:

[0128] Establish a monitoring and evaluation model, which is used to evaluate each abnormal brain region to determine whether it lacks the corresponding electrophysiological characteristics. If it does not lack, it is regarded as meeting the monitoring requirements; the expression of the monitoring and evaluation model is ; where: q is the input data, the input data is the corresponding source localization data, and the output data is the monitoring and evaluation value YG(q);

[0129] Analyze the source localization data through the monitoring and evaluation model to obtain the monitoring and evaluation values corresponding to the positions of each brain region;

[0130] Determine the monitoring and evaluation results according to each monitoring and evaluation value.

[0131] The treatment module is an important part of the system. Its main function is to formulate and adjust the treatment plan in combination with the monitoring results, especially the personalized treatment plan for physical therapy (such as rTMS). The following is a detailed description of the treatment module:

[0132] Treatment plan formulation:

[0133] According to the individualized brain region activity pattern and comprehensive evaluation results provided by the analysis module, an initial treatment plan is formulated for the patient.

[0134] The treatment plan includes drugs, rTMS, etc. The stimulation parameters of rTMS (such as stimulation location, frequency, intensity, and duration, etc.), as well as the treatment cycle and frequency

[0135] 2. Real-time monitoring:

[0136] During the treatment process, the changes in the brain region activities and task performance of the patient are monitored in real time.

[0137] The monitored data is compared with the preset treatment goals to evaluate the immediate effect of the treatment.

[0138] 3. Evaluation of treatment effect:

[0139] After the end of each treatment cycle, a comprehensive evaluation of the patient's treatment effect is carried out.

[0140] The evaluation indicators should include the changes in brain region activities, the improvement of task performance, and the degree of remission of clinical symptoms.

[0141] A multi-dimensional evaluation model is adopted, comprehensively considering objective electroencephalogram physiological indicators and subjective clinical scores, to generate a quantitative treatment effect evaluation report.

[0142] The treatment effect of the patient is compared with that of the normal population or other patients to determine the relative effectiveness of the treatment.

[0143] The methods for evaluating the treatment effect of the patient include:

[0144] Obtain the treatment expectation, that is, the treatment goal corresponding to the corresponding treatment plan, which is set by the doctor; determine each treatment index according to the treatment expectation; obtain the change data after the patient's treatment cycle, and the change data is the change data related to the treatment before and after, mainly collected according to each treatment index; extract the features of the change data according to each treatment index to obtain the completion index corresponding to each treatment index, and the completion index is the completion situation corresponding to the treatment index; evaluate the corresponding treatment index according to each completion index to determine the completion degree of each treatment index, marked as the completion degree, no change or no effect, the completion degree is 0; the completion degree is 90%, then the completion degree is 0.9, and so on;

[0145] According to the formula Calculate the corresponding comprehensive evaluation value;

[0146] In the formula: PW is the comprehensive evaluation value; i represents the corresponding treatment index, i = 1, 2,..., n, and n is a positive integer; βi is the proportionality coefficient of the corresponding treatment index, and the value range is 0 < βi < 1; WDi is the completion degree of the corresponding treatment index;

[0147] Integrate the comprehensive evaluation value and the completion degree of each treatment index into treatment evaluation data.

[0148] In one embodiment, during the actual treatment process, the change data may have treatment effects beyond expectations. If not analyzed, it will lead to incomplete treatment evaluation, especially for treatments involving brain regions, which have more uncertainties; therefore, the treatment evaluation data also includes supplementary evaluation data, and the determination method of the supplementary evaluation data is:

[0149] Determine various changes in the monitored brain regions that may occur to the patient after treatment based on the treatment records in the current field, conduct statistical analysis, determine various change items, that is, the index items with changes compared with those before treatment, that is, conduct statistical analysis using existing historical data, or the professional personnel can directly set each change item; summarize the historical change data according to each change item to form the material data of each change item, determine the recognition and judgment methods corresponding to no change, adverse change, and favorable change for each change item according to the material data, and then establish a change evaluation model. The change evaluation model is used to evaluate each change item according to the change data to obtain that the change item is in a state of no change, adverse change, or favorable change; the expression of the change evaluation model is ; where: cj is the input data, j represents the corresponding change item, j = 1, 2,..., m, m is a positive integer; it is used to indicate which change item to evaluate, and the input data is the change data; the output data is the change evaluation value PB(cj) of the corresponding change item;

[0150] Identify each treatment index, and screen each change item according to each treatment index, that is, eliminate the change items corresponding to the treatment index; reduce the amount of data analysis;

[0151] Analyze the change data through the change evaluation model to obtain the change evaluation values corresponding to each change item after screening;

[0152] Mark each variable item with a non-zero change evaluation value as an index supplement item; determine the supplement result of each index supplement item according to the change evaluation value, that is, favorable change or adverse change; integrate each index supplement item and the corresponding supplement result into supplement evaluation data.

[0153] 4. Treatment plan adjustment:

[0154] Dynamically adjust the patient's treatment plan according to the treatment evaluation data.

[0155] The adjusted content may include the stimulation parameters of rTMS, treatment cycle, frequency, etc.

[0156] The doctor can modify and confirm the automatically adjusted plan according to his own experience and the patient's feedback.

[0157] The analysis module comprehensively analyzes the long-term monitoring data of the patient to evaluate the changes in anhedonia symptoms and treatment effects during the treatment process. Adopt methods such as the mixed effect model to establish a quantitative relationship between brain region activities and clinical symptoms, and depict the dynamic change trend of brain region activities during the treatment process. At the same time, combined with the patient's subjective reports and behavioral performances, conduct multi-dimensional evaluations of the treatment effects, such as the degree of symptom relief, improvement of quality of life, etc.

[0158] Prognosis prediction:

[0159] Adopt survival analysis or time series prediction algorithms, such as Cox regression or long short-term memory network (LSTM), to predict the long-term prognosis and treatment response of patients based on their baseline characteristics and early treatment responses. Identify high-risk patients with poor prognosis or non-response to treatment, and formulate more aggressive and individualized treatment plans for them. At the same time, discover protective factors related to good prognosis to guide clinicians in optimizing treatment strategies.

[0160] In one embodiment, the system can be an independent medical device and be applied in psychiatric hospitals, psychological clinics or research institutions. In addition, the system can also be integrated with existing EEG devices in the form of a software platform for wider applications.

[0161] Application scenarios:

[0162] At the initial diagnosis of patients, collect baseline high-density EEG data and let patients perform a gambling task to activate brain regions related to anhedonia; EEG data are electrophysiological signals.

[0163] Use source localization to determine the source of ERP signals, and according to the corresponding preset map, localize the source of ERP signals to 88 ROIs; the preset map is an existing brain region map.

[0164] Extract ERP components related to reward and punishment during the experiment, and perform time-frequency analysis to identify electrophysiological characteristics related to anhedonia and find the most relevant regions.

[0165] Generate an individualized treatment monitoring report for each patient based on the results of source localization and ERP analysis, providing objective evaluation indicators for treatment effects.

[0166] During the treatment process, regularly repeat the above tests and analyses, monitor the treatment effects, and adjust the treatment plan according to the results.

[0167] The above formulas are all calculated by removing the dimension and taking their numerical values. The formula is obtained by collecting a large amount of data and performing software simulation to get a formula closest to the real situation. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained by simulating a large amount of data.

[0168] The above embodiments are only used to illustrate the technical methods 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 of ordinary skill in the art should understand that the technical methods of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A treatment monitoring system for anhedonia in patients with depression, characterized in that, It includes an acquisition module, a test module, a source localization module, an analysis module, and a treatment module; The acquisition module is used to acquire patient information and the electrophysiological signals of the patient's brain; The test module is used to test the patient using a gambling task with gates, and obtain the analysis results of the gambling task with gates; the gambling task with gates is a decision-making task; The source localization module is used to localize the abnormal brain regions related to anhedonia according to the electrophysiological signals and the analysis results of the gambling task with gates, and organize and label them as source localization data; The source localization module uses the low-resolution electromagnetic tomography imaging function to perform source analysis on the preprocessed EEG data; The steps of source analysis include: Establish regions of interest; Calculate the current source density of each region of interest, select the current density in the LORETA interface, where LORETA is low-resolution electromagnetic tomography imaging, and calculate the current density values in each region of interest; Select the general data export module on the LORETA nodes to export the current density values of each region of interest at each time point; The analysis module is used to monitor and analyze the source localization data, perform data preprocessing on the source localization data, and generate a dynamic brain region map based on the preprocessed source localization data; the dynamic brain region map should display the activity patterns of each key brain region at different time points; determine each abnormal brain region, identify the brain region characteristics of each abnormal brain region, including spatial position, activity intensity, and functional connection; merge each abnormal brain region to obtain the monitored brain region; integrate the corresponding data into the monitoring results; The treatment module is used to formulate and adjust the treatment plan in combination with the monitoring results, and treat the patient based on the treatment plan.

2. The anhedonia treatment monitoring system for depressive patients according to claim 1, characterized in that, The electrophysiological signals are acquired using 128 electrodes.

3. The anhedonia treatment monitoring system for depressive patients according to claim 1, wherein The test method using the gambling task with gates includes: The subject patient faces two gates, and behind each gate is hidden a reward or a loss; the reward is that in the corresponding round, the patient's choice brings a virtual reward, which is used to evaluate the patient's brain's response to pleasure; the punishment is that in the corresponding round, the patient's choice results in a virtual loss, which is used to detect the neural response to punishment or pain; The subject patient needs to choose a gate, and then the reward result behind the gate selected by the patient is presented; the test task contains a certain number of trials, and the probability and quantity of the rewards vary randomly between trials.

4. The anhedonia treatment monitoring system for depressive patients according to claim 3, characterized in that, During the process of the patient performing the gambling task with gates, the test module records the patient's behavioral data in real time, and the behavioral data includes the gate selection, reaction time, and reward result of each trial.

5. The anhedonia treatment monitoring system for depressive patients according to claim 1, wherein The method for determining the monitored brain region includes: Monitor and evaluate each abnormal brain region according to the source localization data to obtain the corresponding monitoring and evaluation results, and the monitoring and evaluation results include the lack of corresponding electrophysiological characteristics and normal monitoring; Merge the adjacent abnormal brain regions with the monitoring and evaluation results of lacking corresponding electrophysiological characteristics to obtain the monitored brain region.

6. The anhedonia treatment monitoring system for depressive patients according to claim 5, characterized in that, The method for monitoring and evaluating each abnormal brain region according to the source localization data includes: Establish a monitoring and evaluation model, and the expression of the monitoring and evaluation model is: ； In the formula: q is the input data, the input data is the corresponding source localization data, and the output data is the monitoring and evaluation value YG(q); Analyze the source localization data through the monitoring and evaluation model to obtain the monitoring and evaluation values corresponding to the positions of each brain region; Determine the monitoring and evaluation results based on each monitoring and evaluation value.

7. The anhedonia treatment monitoring system for depressive patients according to claim 1, characterized in that, The methods for formulating and adjusting treatment plans include: Set an initial treatment plan according to the monitoring results; treat the patient according to the initial treatment plan; during the treatment process, monitor the changes in the patient's brain region activities and task performance in real time, integrate them into monitoring data, compare the monitoring data with the preset treatment goals, and evaluate the immediate treatment effect; After each treatment cycle, evaluate the treatment effect of the patient to obtain treatment evaluation data; Dynamically adjust the initial treatment plan according to the treatment evaluation data, and the adjustment contents include stimulation parameters, treatment cycles, and frequencies.

8. A treatment monitoring system for anhedonia in depressive patients according to claim 7, characterized in that, The methods for evaluating the treatment effect of the patient include: Obtain treatment expectations, and determine each treatment index according to the treatment expectations; obtain the change data of the patient after the treatment cycle; Extract features from the change data according to each treatment index to obtain the completion indexes corresponding to each treatment index; Evaluate each treatment index according to each completion index to determine the completion degree of each treatment index; Calculate the corresponding comprehensive evaluation value according to the formula ​ Where: PW is the comprehensive evaluation value; i represents the corresponding treatment index, i = 1, 2,..., n, n is a positive integer; βi is the proportionality coefficient of the corresponding treatment index, and the value range is 0 < βi < 1; WDi is the completion degree of the corresponding treatment index; Integrate the comprehensive evaluation value and the completion degrees of each treatment index into treatment evaluation data.

9. A treatment monitoring system for anhedonia in depressive patients according to claim 8, characterized in that, The treatment evaluation data also includes supplementary evaluation data, and the determination method of the supplementary evaluation data includes: Determine each change item, and establish a change evaluation model according to each change item. The expression of the change evaluation model is: ； Where: cj is the input data, j represents the corresponding change item, j = 1, 2,..., m, m is a positive integer; the input data is the change data; the output data is the change evaluation value PB(cj) of the corresponding change item; Identify each treatment index, and screen each change item according to each treatment index; Analyze the change data through the change evaluation model to obtain the change evaluation values of each screened change item; Mark each change item with a non-zero change evaluation value as an index supplementary item; determine the supplementary results of each index supplementary item according to the change evaluation value; integrate each index supplementary item and the corresponding supplementary results into supplementary evaluation data.

Images