Generalizability of machine learning for classification of schizophrenia based on resting-state functional MRI data

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

DOI

  • Xin Lu Cai, CAS - Institute of Psychology, University of Chinese Academy of Sciences, Sino Danish Center for Education and Research
  • ,
  • Dong Jie Xie, CAS - Institute of Psychology, Zhejiang Normal University
  • ,
  • Kristoffer H. Madsen, Sino Danish Center for Education and Research, Københavns Universitet, Danmarks Tekniske Universitet
  • ,
  • Yong Ming Wang, CAS - Institute of Psychology, University of Chinese Academy of Sciences, Sino Danish Center for Education and Research
  • ,
  • Sophie Alida Bögemann, CAS - Institute of Psychology, University of Chinese Academy of Sciences, Sino Danish Center for Education and Research
  • ,
  • Eric F.C. Cheung, Castle Peak Hospital
  • ,
  • Arne Møller
  • Raymond C.K. Chan, CAS - Institute of Psychology, University of Chinese Academy of Sciences, Sino Danish Center for Education and Research

Machine learning has increasingly been applied to classification of schizophrenia in neuroimaging research. However, direct replication studies and studies seeking to investigate generalizability are scarce. To address these issues, we assessed within-site and between-site generalizability of a machine learning classification framework which achieved excellent performance in a previous study using two independent resting-state functional magnetic resonance imaging data sets collected from different sites and scanners. We established within-site generalizability of the classification framework in the main data set using cross-validation. Then, we trained a model in the main data set and investigated between-site generalization in the validated data set using external validation. Finally, recognizing the poor between-site generalization performance, we updated the unsupervised algorithm to investigate if transfer learning using additional unlabeled data were able to improve between-site classification performance. Cross-validation showed that the published classification procedure achieved an accuracy of 0.73 using majority voting across all selected components. External validation found a classification accuracy of 0.55 (not significant) and 0.70 (significant) using the direct and transfer learning procedures, respectively. The failure of direct generalization from one site to another demonstrates the limitation of within-site cross-validation and points toward the need to incorporate efforts to facilitate application of machine learning across multiple data sets. The improvement in performance with transfer learning highlights the importance of taking into account the properties of data when constructing predictive models across samples and sites. Our findings suggest that machine learning classification result based on a single study should be interpreted cautiously.

OriginalsprogEngelsk
TidsskriftHuman Brain Mapping
Vol/bind41
Nummer1
Sider (fra-til)172-184
Antal sider13
ISSN1065-9471
DOI
StatusUdgivet - jan. 2020

Se relationer på Aarhus Universitet Citationsformater

ID: 190889535