A predictive system for social functioning in patients with depression

Abstract

This invention belongs to the field of intelligent diagnosis technology for mental illnesses, specifically relating to a system for predicting the social function of patients with depression. The system includes: an input module for inputting patient indicators; a feature extraction module for extracting gray matter features (IC_SA_GMV) of attention-related brain networks from the input indicators; a prediction module integrating a social function prediction model for patients with depression, which calculates the predicted social function of the patient by analyzing the indicators; and an output module for outputting the prediction results. The system provided by this invention can accurately predict the social function of patients with depression and has promising application prospects.

Description

Technical Field

[0001] This invention belongs to the field of intelligent diagnosis technology for mental illnesses, and specifically relates to a system for predicting the social function of patients with depression. Background Technology

[0002] Major Depressive Disorder (MDD), also known as clinical depression, major depressive disorder, or unipolar depression, is a mental illness. Typical symptoms of this disorder include a depressed mood, low self-esteem, and loss of interest in previously enjoyed activities.

[0003] Social functioning refers to an individual's abilities in areas such as occupation, daily life, marriage, and social interactions. Meningococcal diabetic dysplasia (MDD) often involves cognitive impairment, such as attention deficits, which can severely affect clinical remission and long-term social functioning. However, the neural mechanisms underlying cognitive impairment in MDD remain unclear.

[0004] In current technology, the diagnosis of social functioning in patients with MDD mainly uses the Social Deficit Screening Scale (SDSS) to assess an individual's social functioning. The SDSS contains 10 items and uses a 0-2 rating scale: (0) no abnormalities, or only very minor deficits that do not cause complaints / problems; (1) functional deficits; (2) severe functional deficits. Specifically, it includes 10 items: occupation and work, marital functioning, parental functioning, social withdrawal, social activities outside the family, insufficient activities within the family, family functioning, personal care, interest and concern for the outside world, conscientiousness, and planning. However, there is currently a lack of objective biological predictive indicators for evaluating an individual's social functioning.

[0005] Artificial intelligence has already seen numerous applications in the medical field, particularly in the diagnosis of various diseases. For example, "CN202010170779.7 A Knowledge Graph-Based Intelligent Diagnostic Device and System for Depression" has attempted to diagnose depression using machine learning methods. However, the neural mechanisms underlying cognitive impairment in MDD (Depression Depression) remain unclear. Therefore, it is currently uncertain what indicators should be used as input features for machine learning models to achieve accurate diagnosis of social functioning. Summary of the Invention

[0006] In view of the problems of the prior art, the purpose of this invention is to provide a system for predicting the social function of patients with depression.

[0007] A system for predicting social functioning in patients with depression includes:

[0008] The input module is used to input the patient's indicators;

[0009] The feature extraction module is used to extract the gray matter features IC_SA_GMV of attention-related brain networks from the input metrics;

[0010] The prediction module integrates a social function prediction model for patients with depression. By calculating the indicators, the prediction results of the patient's social function are obtained.

[0011] The output module is used to output the prediction results.

[0012] Preferably, the gray matter feature IC_SA_GMV of the attention-related brain network is obtained according to the following method:

[0013] Step 1: Input the patient's attention test results and obtain the cognitive test score for attention;

[0014] Step 2: Input the patient's structural MRI and resting-state functional MRI data, and extract ALFF and GMV images;

[0015] Step 3: Using supervised multivariate canonical correlation analysis (MCCAR) and joint independent component analysis (jICA), the cognitive test score of attention obtained in Step 1 is used as reference information to guide the data fusion of ALFF and GMV to obtain the gray matter features IC_SA_GMV of the brain network related to attention.

[0016] Preferably, the attention test (RVP test, Rapid Visual Processing) is the RVP test from the Cambridge Automated Cognitive Assessment Tool (CANTAB).

[0017] Preferably, the social function prediction model for patients with depression is a linear regression model.

[0018] Preferably, the expression for the linear regression model is:

[0019] y = -14.391X + 2.213

[0020] Where X represents the gray matter feature IC_SA_GMV of attention-related brain networks, and y represents the social function score.

[0021] Preferably, a higher social function score indicates a worse social function for the patient, while a lower social function score indicates a better social function for the patient.

[0022] The present invention also provides a computer-readable storage medium having stored thereon a computer program for implementing the above-described system for predicting the social functioning of patients with depression.

[0023] This invention, through the analysis of a large number of MDD patient sample data, discovered multimodal brain imaging biomarkers related to attention. Utilizing these multimodal brain imaging biomarkers, this invention, for the first time, constructs a model-based system for predicting the social functioning of MDD patients. This system can accurately predict patients' social functioning and has promising application prospects.

[0024] Obviously, based on the above description of the present invention, and according to common technical knowledge and conventional methods in the field, various other modifications, substitutions or alterations can be made without departing from the basic technical concept of the present invention.

[0025] The following detailed embodiments further illustrate the above-described content of the present invention. However, this should not be construed as limiting the scope of the present invention to the following examples. All technologies implemented based on the above-described content of the present invention fall within the scope of the present invention. Attached Figure Description

[0026] Figure 1 The flowchart for Experiment 1 is shown below, in which (a) in the discovery dataset (16-60 years old), cognitive guidance was used to guide the fusion of two MRI features using the RVP test cognitive score from CANTAB as a reference. (b) The analysis of cognitive guidance fusion was repeated in an age-restricted cohort (18-45 years old). (c) Group comparisons were performed on the components identified between MDD and HC, and a linear regression model was used to determine predictive markers of social function. Detailed Implementation

[0027] It should be noted that the algorithms for data acquisition, transmission, storage and processing steps not specifically described in the embodiments, as well as the hardware structures and circuit connections not specifically described, can all be implemented using content already disclosed in the prior art.

[0028] Example 1: Social Functioning Prediction System for Depression Patients

[0029] The system in this embodiment includes:

[0030] The input module is used to input the patient's indicators;

[0031] The feature extraction module is used to extract the gray matter features IC_SA_GMV of attention-related brain networks from the input metrics;

[0032] The prediction module integrates a social function prediction model for patients with depression. By calculating the indicators, the prediction results of the patient's social function are obtained.

[0033] The output module is used to output the prediction results.

[0034] The gray matter feature IC_SA_GMV of the attention-related brain network is obtained as follows:

[0035] Step 1: Perform the RVP test on the patient using the Cambridge Automated Cognitive Assessment Tool to obtain attention-related cognitive test scores;

[0036] Step 2: Collect the patient's structural MRI and resting-state functional MRI data, and extract brain imaging images, including ALFF and GMV images;

[0037] Step 3: Using supervised multivariate canonical correlation analysis (MCCAR) and joint independent component analysis (jICA), the cognitive test scores of the five dimensions obtained in Step 1 are used as reference information to guide the data fusion of ALFF and GMV.

[0038] The social functioning prediction model for patients with depression is a linear regression model. The expression for the linear regression model is:

[0039] y = -14.391X + 2.213

[0040] Where X represents the gray matter feature IC_SA_GMV of the attention-related brain network, and y represents the social function score. The meaning of the social function score is similar to that of the SDSS scale assessment results; a higher score indicates poorer social function, and vice versa.

[0041] The technical solution of the present invention will be further illustrated by the following experiments.

[0042] Experimental Example 1: Screening of Social Function Prediction Indicators

[0043] I. Research Subjects and Methods

[0044] The procedure for this experiment is as follows: Figure 1As shown, this study included 131 patients with myocardial infarction (MDD) meeting the DMS-IV diagnostic criteria for depression, and 145 matched healthy controls. General information was collected from all participants, and attentional function (RVP) was assessed using the Cambridge Automated Neurocognitive Tests (CANTAB). Structural and resting-state functional MRI data were also collected from all participants. The Hamilton Depression Rating Scale (HAMD-17) was used to assess the severity of individual illnesses. Two years later, patients were followed up, and their social functioning was assessed using the Social Deficit Screening Scale (SDSS). Brain imaging data were processed and analyzed using FSL and DPARSF software. Low-frequency oscillations (ALFF) and gray matter volume (GMV) images of each participant were extracted as representative features for the fusion analysis of brain imaging data. ALFF reflects the intrinsic functional activity of the individual brain, while GMV reflects changes in gray matter volume.

[0045] Furthermore, using supervised multivariate canonical correlation analysis (MCCAR) and joint independent component analysis (jICA) techniques, and with cognitive test scores of sustained attention RVP as reference information, we guided the fusion of individual brain low-frequency amplitude (ALFF) and gray matter volume (GMV) data. The aim was to:

[0046] (1) Identify multimodal brain imaging biomarkers associated with cognitive function in MDD, especially persistent attention impairment.

[0047] (2) Based on the differentially identified multimodal brain imaging components between the MDD patient group and the control group, potential predictive biomarkers of social function were identified by linear regression model.

[0048] II. Experimental Results

[0049] This experiment used a t-test to explore the differences between groups in the two imaging feature loads, with a significance level set at p < 0.05. The extracted components were then compared in two ways: first, the differences between groups in attention-related brain imaging features were compared (…). Figure 1 c). Secondly, Pearson correlation analysis was used to explore the correlation between cognitively relevant imaging features (rsfMRI: ALFF_ICref, sMRI: GMV_ICref) and subjects' attention scores (significance p<0.05). Then, linear regression analysis was performed to explore brain imaging features that could predict the social function of MDD patients two years later. Figure 1 d). In addition, the following variables were included in the linear regression analysis to construct the stepwise regression model: age, gender, years of education, age of onset, number of relapses, total duration of illness, presence of suicidal ideation, presence of suicidal behavior, and clinical symptoms. Statistical significance was set at p-value < 0.05.

[0050] Ultimately, only the gray matter feature IC_SA_GMV of the brain network was significantly correlated with the patient's social function, and the expression of the established linear regression model is as follows:

[0051] y = -14.391X + 2.213

[0052] Where X represents the gray matter feature IC_SA_GMV of attention-related brain networks, and y represents the social function score.

[0053] As can be seen from the above embodiments and experimental examples, the present invention has discovered attention-related multimodal brain imaging biomarkers that are significantly associated with patients' social function. These multimodal brain imaging biomarkers can accurately predict the social function of MDD patients and have great application prospects.

Claims

1. A system for predicting the social functioning of patients with depression, characterized in that, include: The input module is used to input the patient's indicators; The feature extraction module is used to extract the gray matter features IC_SA_GMV of attention-related brain networks from the input metrics; The prediction module integrates a social function prediction model for patients with depression. By calculating the indicators, the prediction results of the patient's social function are obtained. The output module is used to output the prediction results; The gray matter features IC_SA_GMV of the attention-related brain network were obtained as follows: Step 1: Input the patient's attention test results and obtain the cognitive test score for attention; Step 2: Input the patient's structural MRI and resting-state functional MRI data, and extract ALFF and GMV images; Step 3: Using the supervised multivariate canonical correlation analysis method MCCAR and the joint independent component analysis (jICA) technique, the cognitive test score of attention obtained in Step 1 is used as reference information to guide the data fusion of ALFF and GMV to obtain the gray matter features IC_SA_GMV of the brain network related to attention. The social functioning prediction model for patients with depression is a linear regression model.

2. The social function prediction system for patients with depression according to claim 1, characterized in that: The attention test is the RVP test from the Cambridge Automated Cognitive Assessment Tool.

3. The social function prediction system for patients with depression according to claim 1, characterized in that: The expression for the linear regression model is: y = -14.391X + 2.213 Where X represents the gray matter feature IC_SA_GMV of attention-related brain networks, and y represents the social function score.

4. The social function prediction system for patients with depression according to claim 3, characterized in that: A higher social function score indicates a worse social function, while a lower social function score indicates a better social function.

5. A computer-readable storage medium, characterized in that, It stores a computer program for implementing the social function prediction system for patients with depression as described in any one of claims 1-4.

Images