
Generalizability of machine learning for classification of schizophrenia based on resting‐state functional MRI data
Author(s) -
Cai XinLu,
Xie DongJie,
Madsen Kristoffer H.,
Wang YongMing,
Bögemann Sophie Alida,
Cheung Eric F. C.,
Møller Arne,
Chan Raymond C. K.
Publication year - 2020
Publication title -
human brain mapping
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.005
H-Index - 191
eISSN - 1097-0193
pISSN - 1065-9471
DOI - 10.1002/hbm.24797
Subject(s) - generalizability theory , artificial intelligence , machine learning , transfer of learning , computer science , generalization , data set , set (abstract data type) , neuroimaging , cross validation , functional magnetic resonance imaging , pattern recognition (psychology) , psychology , mathematics , statistics , mathematical analysis , programming language , psychiatry , neuroscience
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.