Prediction of Transdiagnostic Risk for Serious Mental Illness Using Multimodal MRI and Clinical Data

A Random Forest model using diffusion MRI graph metrics (betweenness centrality) and clinical scales (SOPS, K10) discriminated transdiagnostic risk stages in youth (n=243). No accuracy metrics were reported; external validation is needed.

• Prospective two-site cohort of 243 participants aged 12–25 followed for up to 4 years, stratified into five clinical stages (healthy to discrete disorder).
• Key predictive features included diffusion MRI nodal betweenness centrality in the angular gyrus, inferior temporal gyrus, amygdala, and calcarine fissure, plus SOPS and K10 distress scales.
• Limitation: Small sample, no external validation, and no performance metrics (e.g., AUC, sensitivity) provided in the abstract.

RadPigeon summaries are original and for information only. They are not clinical advice.