A self-monitoring system for classifying stress-related disorders

Abstract

This invention relates to a self-monitoring system for classifying stress-related disorders, belonging to the field of medical data analysis technology. The invention includes a data collection module: collecting patients' medical data, including fMRI data, questionnaires, and scales. This data is divided into stress disorder groups and non-stress disorder groups. A preprocessing module: preprocessing various types of data to improve data quality. A model training module: using deep learning to train the data to generate a stress-related disorder classification model. An evaluation module: evaluating the effectiveness of the generated stress-related disorder classification model to ensure its accuracy and reliability. The evaluation results will be used to select or optimize the optimal model. An integration module: integrating the evaluated and optimized optimal model into a complete system, enabling it to comprehensively analyze patients' fMRI data and questionnaire results, and classify patients into different types of stress-related disorders.

Description

Technical Field

[0001] This invention relates to a self-monitoring system for stress-related disorder classification, belonging to the field of medical data analysis technology. Background Technology

[0002] Stress-related disorders fall into three main categories: acute stress response, post-traumatic stress disorder (PTSD), and adjustment disorder. While physicians can usually determine whether a patient has a stress-related disorder, identifying the specific type of disorder can be challenging. Therefore, developing a classification system is crucial.

[0003] This classification system extracts key features from large amounts of clinical data and uses deep learning and medical data analytics to quantify patients' symptoms and presentations. Through in-depth analysis and pattern recognition of this data, the system can categorize patients into different types of stress-related disorders. This classification system helps physicians better develop personalized support plans, thereby providing more comprehensive support for patients. Summary of the Invention

[0004] The technical problem to be solved by this invention is: This invention provides a self-monitoring system for stress-related disorder classification, which is used to extract key features from a large amount of clinical data and to use deep learning and medical data analysis methods to quantify the symptoms and manifestations of patients. Through in-depth analysis and pattern recognition of this data, the system can classify patients into different types of stress-related disorders.

[0005] The technical solution of this invention is: a self-monitoring system for stress-related disorder classification, the system comprising:

[0006] The data collection module, preprocessing module, model training module, model evaluation module, and system integration module are described.

[0007] The data collection module includes a data filtering unit and a data grouping unit;

[0008] The preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit;

[0009] The fMRI data preprocessing unit includes basic preprocessing, time series extraction, and functional connectivity matrix construction.

[0010] The questionnaire scale data preprocessing unit includes data cleaning, encoding conversion, and normalization processing;

[0011] The model training module includes an fMRI feature extraction unit, a questionnaire scale feature extraction unit, and a feature fusion unit;

[0012] The fMRI feature extraction unit includes a graph convolutional neural network (GCN) algorithm to perform deep feature extraction on the functional connectivity matrix and output fMRI feature vectors.

[0013] The questionnaire scale feature extraction unit includes natural language processing technology and GloVe model to process questionnaire and scale data and output questionnaire scale feature vectors.

[0014] The feature fusion unit takes fMRI feature vectors and questionnaire scale feature vectors as inputs, and outputs subtype classification results by applying a multilayer perceptron (MLP).

[0015] The model evaluation module includes a testing unit, a result acquisition unit, and an evaluation unit;

[0016] The system integration module includes a system integration unit, an operation interface unit, a result presentation unit, a maintenance and update unit, and a performance monitoring and logging unit.

[0017] Furthermore, the data collection module is used to obtain fMRI data and questionnaire scale data of stress-related disorders from the clinical database of stress-related disorders, screen out data that meet the quality requirements, and divide the two types of data into post-traumatic stress disorder group, acute stress response group and adaptation disorder group according to data attributes.

[0018] Furthermore, the preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit:

[0019] The fMRI data preprocessing unit performs a series of preprocessing steps on the collected fMRI data. Preprocessing includes noise removal from the time series, spatial standardization, time series normalization, and any necessary data transformations. After preprocessing, the fMRI data is divided according to predefined brain regions, and the time series data of each region is extracted. The extracted time series data is used to calculate the functional connectivity between brain regions.

[0020] The questionnaire and scale data preprocessing unit is used to preprocess questionnaire and scale data, including data cleaning, encoding conversion, and normalization, to provide standardized input for model training.

[0021] Furthermore, the model training module includes:

[0022] The fMRI feature extraction unit is used to perform deep feature extraction on the preprocessed functional connectivity matrix using a graph convolutional neural network (GCN), identify specific brain activity patterns associated with various stress-related disorder subtypes, and output fMRI feature vectors.

[0023] The questionnaire scale feature extraction unit is used to process questionnaire and scale data using natural language processing technology and GloVe model to capture psychological and behavioral characteristics associated with stress-related disorder subtypes and output questionnaire scale feature vectors.

[0024] The feature fusion unit is used to integrate feature vectors from different data sources. By applying a multilayer perceptron (MLP), it considers various features and their interactions to improve the accuracy of stress-related disorder subtype identification.

[0025] Furthermore, the model evaluation module includes:

[0026] The testing unit is used to run the model trained by the model training module on an independent test dataset to simulate the model's performance in real-world application scenarios, ensuring the accuracy and practicality of the evaluation.

[0027] The results acquisition unit is used to collect the test unit's running results, including the model's prediction accuracy, recall, and F1 score as key performance indicators, in order to fully understand the model's performance.

[0028] The evaluation unit is used to comprehensively analyze the performance data collected by the result acquisition unit, compare different models or different configurations of the same model, and determine the optimal model configuration and parameters. In addition, this unit is also responsible for identifying potential problems in model performance, such as overfitting or underfitting, and proposing corresponding optimization suggestions.

[0029] Furthermore, the system integration module includes:

[0030] The system integration unit is used to integrate the various modules into a unified operating system to ensure the automation and seamless operation of the process from data input to diagnostic output;

[0031] The user interface unit provides an intuitive and user-friendly interface, including data upload, result query, and system settings functions;

[0032] The results presentation unit is used to present diagnostic results in an easy-to-understand format, ensuring that users can quickly access key information, including disease classification, severity, and possible treatment recommendations.

[0033] The maintenance and update unit is used for the periodic inspection and update of the system, including model updates, system function enhancements, and processing of user feedback.

[0034] The performance monitoring and logging unit is used to monitor and record the system's operating status and user activities to support the system's secure and stable operation and subsequent auditing and improvement activities.

[0035] Furthermore, in the fMRI data preprocessing unit, the Pearson correlation coefficient (PCC) is calculated using the following formula to construct the functional connectivity matrix, where r in the formula... nm The Pearson correlation coefficient represents the signal time series between the nth brain region and the mth brain region;

[0036]

[0037] in, and These are the mean signal values ​​for brain regions n and m, respectively, where N represents the total number of time points, and T represents the mean signal values ​​for brain regions m and m. tn T represents the signal value in brain region n at time point t. tm This represents the signal value of brain region m at time point t.

[0038] Furthermore, the model evaluation module calculates accuracy, recall (R), and F1 score to optimize model parameters, where TP (True Positive Examples) is the number of samples that are actually positive but are predicted as positive by the model, FN (False Negative Examples) is the number of samples that are actually positive but are predicted as negative by the model, FP (False Positive Examples) is the number of samples that are actually negative but are predicted as positive by the model, and TN (True Negative Examples) is the number of samples that are actually negative but are predicted as negative by the model.

[0039]

[0040] The beneficial effects of this invention are as follows: First, this invention collects patients' medical data, including fMRI data, questionnaires, and scales, which are divided into stress disorder groups and non-stress disorder groups. A preprocessing module preprocesses the various types of data to improve data quality. A model training module performs deep learning training on the data to generate a stress-related disorder classification model. An evaluation module evaluates the effectiveness of the generated stress-related disorder classification model to ensure its accuracy and reliability; the evaluation results are used to select or optimize the optimal model. An integration module integrates the evaluated and optimized optimal model into a complete system, enabling it to comprehensively analyze patients' fMRI data and questionnaire results, and to classify patients into different types of stress-related disorders. Attached Figure Description

[0041] Figure 1 This is a flowchart of the present invention;

[0042] Figure 2 A diagram illustrating the fMRI time series acquisition process;

[0043] Figure 3 A diagram illustrating the sparse process of the fMRI functional connectivity matrix;

[0044] Figure 4This is a diagram of a feature fusion model. Detailed Implementation

[0045] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0046] Example 1: As Figures 1-4 As shown, a self-monitoring system for classifying stress-related disorders includes:

[0047] The data collection module, preprocessing module, model training module, model evaluation module, and system integration module are described.

[0048] The data collection module includes a data filtering unit and a data grouping unit;

[0049] The preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit;

[0050] The fMRI data preprocessing unit includes basic preprocessing, time series extraction, and functional connectivity matrix construction.

[0051] The questionnaire scale data preprocessing unit includes data cleaning, encoding conversion, and normalization processing;

[0052] The model training module includes an fMRI feature extraction unit, a questionnaire scale feature extraction unit, and a feature fusion unit;

[0053] The fMRI feature extraction unit includes a graph convolutional neural network (GCN) algorithm to perform deep feature extraction on the functional connectivity matrix and output fMRI feature vectors.

[0054] The questionnaire scale feature extraction unit includes natural language processing technology and GloVe model to process questionnaire and scale data and output questionnaire scale feature vectors.

[0055] The feature fusion unit takes fMRI feature vectors and questionnaire scale feature vectors as inputs, and outputs subtype classification results by applying a multilayer perceptron (MLP).

[0056] The model evaluation module includes a testing unit, a result acquisition unit, and an evaluation unit;

[0057] The system integration module includes a system integration unit, an operation interface unit, a result presentation unit, a maintenance and update unit, and a performance monitoring and logging unit.

[0058] Furthermore, the data collection module is used to obtain fMRI data and questionnaire scale data of stress-related disorders from the clinical database of stress-related disorders, screen out data that meet the quality requirements, and divide the two types of data into post-traumatic stress disorder group, acute stress response group and adaptation disorder group according to data attributes.

[0059] Furthermore, the preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit:

[0060] The fMRI data preprocessing unit performs a series of preprocessing steps on the collected fMRI data. Preprocessing includes noise removal from the time series, spatial standardization, time series normalization, and any necessary data transformations. After preprocessing, the fMRI data is divided according to predefined brain regions, and the time series data of each region is extracted. The extracted time series data is used to calculate the functional connectivity between brain regions.

[0061] The questionnaire and scale data preprocessing unit is used to preprocess questionnaire and scale data, including data cleaning, encoding conversion, and normalization, to provide standardized input for model training.

[0062] Furthermore, the model training module includes:

[0063] The fMRI feature extraction unit is used to perform deep feature extraction on the preprocessed functional connectivity matrix using a graph convolutional neural network (GCN), identify specific brain activity patterns associated with various stress-related disorder subtypes, and output fMRI feature vectors.

[0064] The questionnaire scale feature extraction unit is used to process questionnaire and scale data using natural language processing technology and GloVe model to capture psychological and behavioral characteristics associated with stress-related disorder subtypes and output questionnaire scale feature vectors.

[0065] The feature fusion unit is used to integrate feature vectors from different data sources. By applying a multilayer perceptron (MLP), it considers various features and their interactions to improve the accuracy of stress-related disorder subtype identification.

[0066] Furthermore, the model evaluation module includes:

[0067] The testing unit is used to run the model trained by the model training module on an independent test dataset to simulate the model's performance in real-world application scenarios, ensuring the accuracy and practicality of the evaluation.

[0068] The results acquisition unit is used to collect the test unit's running results, including the model's prediction accuracy, recall, and F1 score as key performance indicators, in order to fully understand the model's performance.

[0069] The evaluation unit is used to comprehensively analyze the performance data collected by the result acquisition unit, compare different models or different configurations of the same model, and determine the optimal model configuration and parameters. In addition, this unit is also responsible for identifying potential problems in model performance, such as overfitting or underfitting, and proposing corresponding optimization suggestions.

[0070] Furthermore, the system integration module includes:

[0071] The system integration unit is used to integrate the various modules into a unified operating system to ensure the automation and seamless operation of the process from data input to diagnostic output;

[0072] The user interface unit provides an intuitive and user-friendly interface, including data upload, result query, and system settings functions;

[0073] The results presentation unit is used to present diagnostic results in an easy-to-understand format, ensuring that users can quickly access key information, including disease classification, severity, and possible treatment recommendations.

[0074] The maintenance and update unit is used for the periodic inspection and update of the system, including model updates, system function enhancements, and processing of user feedback.

[0075] The performance monitoring and logging unit is used to monitor and record the system's operating status and user activities to support the system's secure and stable operation and subsequent auditing and improvement activities.

[0076] Furthermore, in the fMRI data preprocessing unit, the Pearson correlation coefficient (PCC) is calculated using the following formula to construct the functional connectivity matrix, where r in the formula... nm The Pearson correlation coefficient represents the signal time series between the nth brain region and the mth brain region;

[0077]

[0078] in, and These are the mean signal values ​​for brain regions n and m, respectively, where N represents the total number of time points, and T represents the mean signal values ​​for brain regions m and m. tn T represents the signal value in brain region n at time point t. tm This represents the signal value of brain region m at time point t.

[0079] Furthermore, the model evaluation module calculates accuracy, recall (R), and F1 score to optimize model parameters, where TP (True Positive Examples) is the number of samples that are actually positive but are predicted as positive by the model, FN (False Negative Examples) is the number of samples that are actually positive but are predicted as negative by the model, FP (False Positive Examples) is the number of samples that are actually negative but are predicted as positive by the model, and TN (True Negative Examples) is the number of samples that are actually negative but are predicted as negative by the model.

[0080]

[0081] The self-monitoring system for stress-related disorder typology of this invention includes modules that realize the complete process from data collection to disease classification. The process of a self-testing method for stress-related disorder typology is as follows:

[0082] Step 1: Data Collection. The system first uses a data collection module to obtain fMRI data and questionnaire data from patients with stress-related disorders from a clinical database. A data screening unit ensures the selected data meets quality standards, while a data grouping unit categorizes the data into three groups based on their different attributes: post-traumatic stress disorder (PTSD), acute stress response, and adjustment disorder.

[0083] Step 2: Data Preprocessing. In the preprocessing module, the fMRI data undergoes basic processing steps such as denoising, spatial standardization, and time-series normalization. After time-series extraction, a functional connectivity matrix is ​​generated between brain regions using a functional connectivity matrix construction unit, and a graph autoencoder is used to obtain a sparse connectivity matrix. Simultaneously, the questionnaire data is prepared for subsequent processing through cleaning, encoding transformation, and normalization.

[0084] Step 3: Model Training. In the model training module, the sparsed connection matrix is ​​used for deep feature extraction via a Graph Convolutional Neural Network (GCN). The questionnaire data is processed using natural language processing techniques and the GloVe model. Subsequently, the feature fusion unit integrates the feature vectors from the two data sources and applies a Multilayer Perceptron (MLP) to output the final subtype classification result.

[0085] Step 4: Model Evaluation. The model evaluation module optimizes parameters by evaluating the model on an independent test set and calculates key metrics such as accuracy, recall, and F1 score to ensure the effectiveness and reliability of the model.

[0086] Step 5: System Integration. The system integration module ensures that all sub-modules work together, provides a user-friendly interface, displays easy-to-understand diagnostic results, and enables system maintenance, updates, and performance monitoring.

[0087] Through the above steps, the system in this embodiment can effectively identify and classify different subtypes of stress-related disorders.

[0088] The specific embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. A self-monitoring system for classifying stress-related disorders, characterized in that... The system includes: The system includes a data collection module, a preprocessing module, a model training module, a model evaluation module, and a system integration module. The data collection module includes a data filtering unit and a data grouping unit; The preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit; The fMRI data preprocessing unit includes basic preprocessing, time series extraction, and functional connectivity matrix construction. The questionnaire scale data preprocessing unit includes data cleaning, encoding conversion, and normalization processing; The model training module includes an fMRI feature extraction unit, a questionnaire scale feature extraction unit, and a feature fusion unit; The fMRI feature extraction unit includes a graph convolutional neural network (GCN) algorithm to perform deep feature extraction on the functional connectivity matrix and output fMRI feature vectors. The questionnaire scale feature extraction unit includes natural language processing technology and GloVe model to process questionnaire and scale data and output questionnaire scale feature vectors. The feature fusion unit takes fMRI feature vectors and questionnaire feature vectors as inputs, and outputs subtype classification results by applying a multilayer perceptron (MLP). The model evaluation module includes a testing unit, a result acquisition unit, and an evaluation unit; The system integration module includes a system integration unit, an operation interface unit, a result presentation unit, a maintenance and update unit, and a performance monitoring and log recording unit. The preprocessing module includes an fMRI data preprocessing unit and a questionnaire scale data preprocessing unit: The fMRI data preprocessing unit performs a series of preprocessing steps on the collected fMRI data. Preprocessing includes noise removal from the time series, spatial standardization, time series normalization, and any necessary data transformations. After preprocessing, the fMRI data is divided according to predefined brain regions, and the time series data of each region is extracted. The extracted time series data is used to calculate the functional connectivity between brain regions. The questionnaire and scale data preprocessing unit is used to preprocess questionnaire and scale data, including data cleaning, encoding conversion, and normalization, to provide standardized input for model training. The model evaluation module includes: The testing unit is used to run the model trained by the model training module on an independent test dataset to simulate the model's performance in real-world application scenarios, ensuring the accuracy and practicality of the evaluation. The results acquisition unit is used to collect the test unit's running results, including the model's prediction accuracy, recall, and F1 score as key performance indicators, in order to fully understand the model's performance. The evaluation unit is used to comprehensively analyze the performance data collected by the results acquisition unit, compare different models or different configurations of the same model, and determine the optimal model configuration and parameters. In addition, this unit is also responsible for identifying potential problems in model performance, such as overfitting or underfitting, and proposing corresponding optimization suggestions. In the fMRI data preprocessing unit, the Pearson correlation coefficient (PCC) is calculated using the following formula to construct the functional connectivity matrix. The Pearson correlation coefficient represents the signal time series between the nth brain region and the mth brain region; ； in, and These are the mean signal values ​​for brain regions n and m, respectively, where N represents the total number of time points. This represents the signal value in brain region n at time point t. This represents the signal value of brain region m at time point t.

2. The self-monitoring system for stress-related disorder classification according to claim 1, characterized in that: The data collection module is used to obtain fMRI data and questionnaire data of stress-related disorders from the clinical database of stress-related disorders, screen out data that meet the quality requirements, and divide the two types of data into post-traumatic stress disorder group, acute stress response group and adjustment disorder group according to data attributes.

3. The self-monitoring system for stress-related disorder classification according to claim 1, characterized in that: The model training module includes: The fMRI feature extraction unit is used to perform deep feature extraction on the preprocessed functional connectivity matrix using a graph convolutional neural network (GCN), identify specific brain activity patterns associated with various stress-related disorder subtypes, and output fMRI feature vectors. The questionnaire scale feature extraction unit is used to process questionnaire and scale data using natural language processing technology and GloVe model to capture psychological and behavioral characteristics associated with stress-related disorder subtypes and output questionnaire scale feature vectors. The feature fusion unit is used to integrate feature vectors from different data sources. By applying a multilayer perceptron (MLP), it considers various features and their interactions to improve the accuracy of stress-related disorder subtype identification.

4. The self-monitoring system for stress-related disorder classification according to claim 1, characterized in that: The system integration module includes: The system integration unit is used to integrate the various modules into a unified operating system to ensure the automation and seamless operation of the process from data input to diagnostic output; The user interface unit provides an intuitive and user-friendly interface, including data upload, result query, and system settings functions; The results presentation unit is used to present diagnostic results in an easy-to-understand format, ensuring that users can quickly access key information, including disease classification, severity, and possible treatment recommendations. The maintenance and update unit is used for the periodic inspection and update of the system, including model updates, system function enhancements, and processing of user feedback. The performance monitoring and logging unit is used to monitor and record the system's operating status and user activities to support the system's secure and stable operation and subsequent auditing and improvement activities.

5. The self-monitoring system for stress-related disorder classification according to claim 1, characterized in that: The model evaluation module calculates accuracy, recall (R), and F1 score to optimize model parameters. TP (True Positive Examples): the number of samples that are actually positive and predicted as positive by the model; FN (False Negative Examples): the number of samples that are actually positive but predicted as negative by the model; FP (False Positive Examples): the number of samples that are actually negative but predicted as positive by the model; TN (True Negative Examples): the number of samples that are actually negative and predicted as negative by the model. ； ； 。

Images