Functional MRI connectivity accurately distinguishes cases with psychotic disorders from healthy controls, based on cortical features associated with brain network development

Abstract Background Machine learning (ML) can distinguish cases with psychotic disorder from healthy controls based on magnetic resonance imaging (MRI) data but it is not yet clear which MRI metrics are the most informative for case-control ML, or how ML algorithms relate to the underlying biology. Methods We analysed multi-modal MRI data from two independent case-control studies of psychotic disorders (cases, N=65, 28; controls, N=59, 80) and compared ML accuracy across 5 selected MRI metrics from 3 modalities. Cortical thickness, mean diffusivity and fractional anisotropy were estimated at each of 308 cortical regions, as well as functional and structural connectivity between each pair of regions. Functional connectivity data were also used to classify non-psychotic siblings of cases (N=64) and to distinguish cases from controls in a third independent study (cases, N=67; controls, N=81). Results In both principal studies, the most informative metric was fMRI connectivity: the areas under the receiver operating characteristic curve were 88% and 76%, respectively. The cortical map of diagnostic connectivity features (ML weights) was replicable between studies (r = 0.27, P Conclusions ML most accurately distinguished cases from controls by a replicable pattern of fMRI connectivity features, highlighting abnormal hubness of cortical nodes in an anatomical pattern consistent with the concept of psychosis as a disorder of network development.