Deep learning applications for the classification of psychiatric disorders using neuroimaging data: systematic review and meta-analysis

Abstract

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to conventional machine learning (ML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n=22), schizophrenia (SZ; n=22) and attention-deficit/hyperactivity disorder (ADHD; n=9). Thirty-two of the thirty-five studies that directly compared DL to ML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and ML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. These results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. The current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets.