Identifying suicide attempts, ideation, and non-ideation in major depressive disorder from structural MRI data using deep learning

Jinlong Hu; Yangmin Huang; Xiaojing Zhang; Bin Liao; Gangqiang Hou; Ziyun Xu; Shoubin Dong; Ping Li

doi:10.1016/j.ajp.2023.103511

Identifying suicide attempts, ideation, and non-ideation in major depressive disorder from structural MRI data using deep learning

Asian J Psychiatr. 2023 Apr:82:103511. doi: 10.1016/j.ajp.2023.103511. Epub 2023 Feb 10.

Authors

Jinlong Hu¹, Yangmin Huang¹, Xiaojing Zhang², Bin Liao³, Gangqiang Hou⁴, Ziyun Xu⁵, Shoubin Dong¹, Ping Li⁶

Affiliations

¹ Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
² Guangdong Provincial Key Laboratory of Genome Stability and Disease Prevention and Regional Immunity and Diseases, Department of Pathology, Shenzhen University Medical School, Shenzhen University, Shenzhen, China.
³ College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China. Electronic address: liaobin_lb@163.com.
⁴ Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China. Electronic address: nihaohgq@163.com.
⁵ Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China.
⁶ Department of Chinese and Bilingual Studies, Faculty of Humanities, The Hong Kong Polytechnic University, Hong Kong, China.

PMID: 36791609
DOI: 10.1016/j.ajp.2023.103511

Abstract

The present study aims to identify suicide risks in major depressive disorders (MDD) patients from structural MRI (sMRI) data using deep learning. In this paper, we collected the sMRI data of 288 MDD patients, including 110 patients with suicide ideation (SI), 93 patients with suicide attempts (SA), and 85 patients without suicidal ideation or attempts (NS). And we developed interpretable deep neural network models to classify patients in three tasks including SA-versus-SI, SA-versus-NS, and SI-versus-NS, respectively. Furthermore, we interpreted the models by extracting the important features that contributed most to the classification, and further discussed these features or ROI/brain regions.

Keywords: Deep learning; Major depressive disorder; Structural MRI; Suicide behavior.

MeSH terms

Deep Learning*
Depressive Disorder, Major* / diagnostic imaging
Humans
Suicidal Ideation
Suicide, Attempted