Objective and quantitative neuroimaging biomarkers are crucial for early diagnosis of major depressive disorder (MDD). However, previous studies using machine learning (ML) to distinguish MDD have often used small sample sizes and overlooked MDD's neural connectome and mechanism. To address these gaps, we applied Dynamic Graph Convolutional Nets (DGCNs) to a large multi-site dataset of 2317 resting state functional MRI (RS-fMRI) scans from 1081 MDD patients and 1236 healthy controls from 16 Rest-meta-MDD consortium sites. Our DGCN model combined with the personal whole brain functional connectivity (FC) network achieved an accuracy of 82.5 % (95 % CI:81.6-83.4 %, AUC:0.869), outperforming other universal ML classifiers. The most prominent domains for classification were mainly in the default mode network, fronto-parietal and cingulo-opercular network. Our study supports the stability and efficacy of using DGCN to characterize MDD and demonstrates its potential in enhancing neurobiological comprehension of MDD by detecting clinically related disorders in FC network topologies.
Keywords: Dynamic graph neural network; Machine learning; Magnetic resonance imaging; Major depression disorder; Multi-site.
Copyright © 2024. Published by Elsevier B.V.