Multisite generalizability of schizophrenia diagnosis classification based on functional brain connectivity

Pierre Orban, Christian Dansereau, Laurence Desbois, Violaine Mongeau-Pérusse, Charles Édouard Giguère, Hien Nguyen, Adrianna Mendrek, Emmanuel Stip, Pierre Bellec

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)167-171
Number of pages5
JournalSchizophrenia Research
Volume192
DOIs
Publication statusPublished - Feb 2018
Externally publishedYes

Keywords

  • Classification
  • Cognition
  • Machine learning
  • Multisite
  • Schizophrenia
  • fMRI

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Fingerprint

Dive into the research topics of 'Multisite generalizability of schizophrenia diagnosis classification based on functional brain connectivity'. Together they form a unique fingerprint.

Cite this