An objective quantitative diagnosis of depression using a local-to-global multimodal fusion graph neural network

Shuyu Liu; Jingjing Zhou; Xuequan Zhu; Ya Zhang; Xinzhu Zhou; Shaoting Zhang; Zhi Yang; Ziji Wang; Ruoxi Wang; Yizhe Yuan; Xin Fang; Xiongying Chen; DIRECT Consortium; Yanfeng Wang; Ling Zhang; Gang Wang; Cheng Jin

doi:10.1016/j.patter.2024.101081

An objective quantitative diagnosis of depression using a local-to-global multimodal fusion graph neural network

Patterns (N Y). 2024 Nov 4;5(12):101081. doi: 10.1016/j.patter.2024.101081. eCollection 2024 Dec 13.

Authors

Shuyu Liu¹, Jingjing Zhou^{2

3

4}, Xuequan Zhu², Ya Zhang^{5

6}, Xinzhu Zhou², Shaoting Zhang⁵, Zhi Yang², Ziji Wang⁷, Ruoxi Wang¹, Yizhe Yuan¹, Xin Fang¹, Xiongying Chen²; DIRECT Consortium; Yanfeng Wang^{5

6}, Ling Zhang², Gang Wang^{2

3

4}, Cheng Jin^{1

2

5

8}

Affiliations

¹ Medical Robot Research Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
² Beijing Key Laboratory of Mental Disorders, National Clinical Research Center for Mental Disorders & National Center for Mental Disorders, Beijing Anding Hospital & Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing 100088, China.
³ CAS Key Laboratory of Behavioral Science, Institute of Psychology, Beijing 100101, China.
⁴ Department of Psychology, University of Chinese Academy of Sciences, Beijing 100101, China.
⁵ Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China.
⁶ School of Electronic Information and Electronical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
⁷ Department of Cognitive Science, Swarthmore College, Philadelphia, PA 19081, USA.
⁸ Stanford University School of Medicine, Ground Floor, 875 Blake Wilbur Drive, Stanford, CA 94305-5847, USA.

Abstract

This study developed an artificial intelligence (AI) system using a local-global multimodal fusion graph neural network (LGMF-GNN) to address the challenge of diagnosing major depressive disorder (MDD), a complex disease influenced by social, psychological, and biological factors. Utilizing functional MRI, structural MRI, and electronic health records, the system offers an objective diagnostic method by integrating individual brain regions and population data. Tested across cohorts from China, Japan, and Russia with 1,182 healthy controls and 1,260 MDD patients from 24 institutions, it achieved a classification accuracy of 78.75%, an area under the receiver operating characteristic curve (AUROC) of 80.64%, and correctly identified MDD subtypes. The system further discovered distinct brain connectivity patterns in MDD, including reduced functional connectivity between the left gyrus rectus and right cerebellar lobule VIIB, and increased connectivity between the left Rolandic operculum and right hippocampus. Anatomically, MDD is associated with thickness changes of the gray and white matter interface, indicating potential neuropathological conditions or brain injuries.

Keywords: brain connectivity analysis; graph neural network; major depressive disorder; multimodal fusion; neuroimaging biomarkers.

Associated data

figshare/10.6084/m9.figshare.27107440