Using an AI-based approach that captures complex patterns across the brain as a whole, rather than focusing on individual regions that appear abnormal, the researchers found that the greater the severity of symptoms, the more pronounced the deviations in brain structure were compared with those observed in healthy individuals. First author Julius Wiegert of the Hector Institute for Artificial Intelligence in Psychiatry (HITKIP) at the ZI emphasises that AI-based methods can reveal subtle structural differences that often remain undetected using conventional analytical approaches.
The structural deviations varied substantially from one individual to another. Despite these individual differences, however, the researchers also identified commonalities: the patterns of structural brain alterations in depression and anxiety showed marked similarities, while differing from those observed in individuals with elevated alcohol consumption.
According to senior author Prof. Dr. Emanuel Schwarz, Head of HITKIP at the ZI, the findings support transdiagnostic approaches that conceptualise mental disorders in terms of shared underlying mechanisms rather than rigid diagnostic boundaries.
Publication: Wiegert, J., Marty-Lombardi, S., Oweda, J. et al. Breaking the norm: population-scale deviations of brain structure in depression and anxiety. Molecular Psychiatry (2026).
https://doi.org/10.1038/s41380-026-03691-4
Source: Press release from the Central Institute of Mental Health (ZI) Mannheim
