Brain‐based ranking of cognitive domains to predict schizophrenia (2019) AcademicArticle

Schizophrenia is a devastating brain disorder that disturbs sensory perception, motoraction, and abstract thought. Its clinical phenotype implies dysfunction of variousmental domains, which has motivated a series of theories regarding the underlyingpathophysiology. Aiming at a predictive benchmark of a catalog of cognitive functions,we developed a data-driven machine-learning strategy and provide a proof ofprinciple in a multisite clinical dataset (n = 324). Existing neuroscientific knowledge ondiverse cognitive domains was first condensed into neurotopographical maps. Wethen examined how the ensuing meta-analytic cognitive priors can distinguishpatients and controls using brain morphology and intrinsic functional connectivity.Some affected cognitive domains supported well-studied directions of research onauditory evaluation and social cognition. However, rarely suspected cognitivedomains also emerged as disease relevant, including self-oriented processing of bodilysensations in gustation and pain. Such algorithmic charting of the cognitive landscapecan be used to make targeted recommendations for future mental health research.