Method, system and equipment for constructing a risk assessment model for obsessive-compulsive disorder

Abstract

The invention provides a method, system and equipment for constructing a risk assessment model of obsessive-compulsive disorder. By adding group sparse regularization and smooth regularization to the group sparse representation model, a sparse network is constructed; the sparse network is used to represent the original fMRI data set The brain connection network matrix corresponding to the ROI sequence; use the brain connection network matrix to train the preset network model, and obtain the trained obsessive-compulsive disorder risk assessment model. Since the preset network model used for training in this embodiment includes: a brain feature extraction module and a classification module, the brain feature extraction module extracts the edge features of the brain connection network matrix based on the DPN network model, so this embodiment constructs The risk assessment model for obsessive-compulsive disorder can better learn the internal relationship of features, reduce the data dimension, reduce the complexity of data processing, improve the efficiency and accuracy of data processing, and provide a basis for risk assessment of obsessive-compulsive disorder.

Description

technical field [0001] The invention relates to the technical field of medical diagnosis, in particular to a method, system and equipment for constructing an obsessive-compulsive disorder risk assessment model. Background technique [0002] Obsessive-compulsive disorder (OCD) is a chronic hereditary psychiatric disorder. Obsessive thoughts or behaviors are the main clinical manifestation of obsessive-compulsive disorder patients, which can reduce the patient's quality of life. According to clinical research, genetic factors and the surrounding social environment can lead to OCD. A patient's unaffected first-degree relatives (UFDR) are immediate family members such as brothers and parents. Because UFDRs share some of the same OCD genes and they live in similar environments, UFDRs are also at high risk for OCD. [0003] Most of the existing OCD risk assessment models for early diagnosis of brain diseases are OCD risk assessment models based on machine learning. For example...

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide a construction method, system and equipment for the risk assessment model of obsessive-compulsive disorder, which overcomes the risk assessment of obsessive-compulsive disorder in the prior art in the risk assessment of obsessive-compulsive disorder The first-degree relatives were not identified as high-risk groups, and the accuracy of identification was low

Images