Dissecting Psychiatric Heterogeneity and Comorbidity with Core Region-Based Machine Learning

 Qian Lv1  · Kristina Zeljic2  · Shaoling Zhao3,4 · Jiangtao Zhang5  · Jianmin Zhang5  · Zheng Wang1,6
1 School of Psychological and Cognitive Sciences, Beijing Key Laboratory of Behavior and Mental Health, IDG/McGovern Institute for Brain Research, Peking-Tsinghua Center for Life Sciences, Peking University, Beijing 100871, China 
2 School of Health and Psychological Sciences, City, University of London, London EC1V 0HB, UK 
3 Institute of Neuroscience, State Key Laboratory of Neuroscience, CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai 200031, China 
4 University of Chinese Academy of Sciences, Beijing 101408, China 
5 Tongde Hospital of Zhejiang Province (Zhejiang Mental Health Center), Zhejiang Ofce of Mental Health, Hangzhou 310012, China 
6 School of Biomedical Engineering, Hainan University, Haikou 570228, China

Machine learning approaches are increasingly being applied to neuroimaging data from patients with psychiatric disorders to extract brain-based features for diagnosis and prognosis. The goal of this review is to discuss recent practices for evaluating machine learning applications to obsessive-compulsive and related disorders and to advance a novel strategy of building machine learning models based on a set of core brain regions for better performance, interpretability, and generalizability. Specifically, we argue that a core set of co-altered brain regions (namely ‘core regions’) comprising areas central to the underlying psychopathology enables the efficient construction of a predictive model to identify distinct symptom dimensions/clusters in individual patients. Hypothesis-driven and data-driven approaches are further introduced showing how core regions are identified from the entire brain. We demonstrate a broadly applicable roadmap for leveraging this core set-based strategy to accelerate the pursuit of neuroimaging-based markers for diagnosis and prognosis in a variety of psychiatric disorders.

Psychiatric disorders; Obsessive-compulsive disorder; Core region; Magnetic resonance imaging; Machine learning; Neuroimaging-based diagnosis