An Integrative Approach for Subtyping Mental Disorders Using Multi-modality Data.

Mental disorders exhibit significant heterogeneity, posing challenges for accurate subtyping and diagnosis. Traditional clustering methods do not integrate multi-modal data, limiting their clinical applicability. This study introduces the Mixed INtegrative Data Subtyping (MINDS) method, a Bayesian hierarchical joint model designed to identify subtypes of Attention-Deficit/Hyperactivity Disorder (ADHD) and Obsessive-Compulsive Disorder (OCD) in adolescents using multi-modality data from the Adolescent Brain Cognitive Development (ABCD) Study. MINDS integrates clinical assessments and neuro-cognitive measures while simultaneously performing clustering and dimension reduction. By leveraging Polya-Gamma augmentation, we propose an efficient Gibbs sampler to improve computational efficiency and provide subtype identification. Simulation studies demonstrate superior robustness of MINDS compared to traditional clustering techniques. Application to the ABCD study reveals more reliable and clinically meaningful subtypes of ADHD and OCD with distinct cognitive and behavioral profiles. These findings show the potential of multi-modal model-based clustering for advancing precision psychiatry in mental health.