RT Journal Article SR Electronic T1 Multisite generalizability of schizophrenia diagnosis classification based on functional brain connectivity JF bioRxiv FD Cold Spring Harbor Laboratory SP 141192 DO 10.1101/141192 A1 Pierre Orban A1 Christian Dansereau A1 Laurence Desbois A1 Violaine Mongeau-Pérusse A1 Charles-Édouard Giguère A1 Hien Nguyen A1 Adrianna Mendrek A1 Emmanuel Sti A1 Pierre Bellec YR 2017 UL http://biorxiv.org/content/early/2017/05/24/141192.abstract AB Our objective was to assess the generalizability, across sites and cognitive contexts, of schizophrenia classification based on functional brain connectivity. We tested different training-test scenarios combining fMRI data from 191 schizophrenia patients and 191 matched healthy controls obtained at 6 scanning sites and under different task conditions. Diagnosis classification accuracy generalized well to a novel site and cognitive context provided data from multiple sites were used for classifier training. By contrast, lower classification accuracy was achieved when data from a single distinct site was used for training. These findings indicate that it is beneficial to use multisite data to train fMRI-based classifiers intended for large-scale use in the clinical realm.