Machine Learning based Structural and Diffusion MRI to Identify Suicide Risk in Depressed Patients
Huiru Li1, Huawei Zhang1, Li Yin2, Zhiyun Jia1, and Qiyong Gong1
1Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan Universit, Chengdu, China, 2Department of Psychiatry, West China Hospital of Sichuan University, Chengdu, China
In this study, we used 5 machine learning algorithms with structural and diffusion MRI to classify suicidal risk in depressed patients and the best performance was acquired by support vector machine. In addition, the most important 10 features were most located in fronto-temporal–parietal regions. This study found a classification model using MRI data can help diagnosis and assess suicidal risk in depressed patients.
This abstract and the presentation materials are available to members only;
a login is required.