Page 65 - 南京医科大学自然版
P. 65
第46卷第7期 南京医科大学学报(自然科学版)
2026年7月 Journal of Nanjing Medical University(Natural Sciences) ·1011 ·
·专题研究:神经精神疾病·
从数据整合到临床转化:机器学习在抑郁症诊断中的应用
高子祥 ,李 翔 ,张 欣 ,钱昭均 ,嵇子慧 ,朱俐璇 ,徐忆初 ,陈亚丽 ,葛菲菲 1*
1
1
1
1
1
1*
2
1
南京中医药大学医学院,人工智能与信息技术学院,江苏 南京 210023
1 2
[摘 要] 抑郁症起病隐匿、症状异质性明显,现行诊断仍主要依赖临床访谈与量表评估,存在主观性较强、早期识别不足以
及对分型和预后判断能力有限等问题。随着神经影像、脑电图、语音与数字行为、临床量表及多组学等客观数据的不断积累,
机器学习为抑郁症客观识别提供了新的研究路径。文章围绕抑郁症客观识别这一核心问题,综述了机器学习在神经影像及其
他单模态客观数据中的应用进展,进一步总结了多模态数据在抑郁症诊断、分型、病程评估和疗效预测中的整合价值,并对常
见融合策略、模型可解释性及临床转化问题进行了归纳分析。
[关键词] 抑郁症;机器学习;神经影像学;多模态数据;辅助诊断
[中图分类号] R749.4 [文献标志码] A [文章编号] 1007⁃4368(2026)07⁃1011⁃09
doi:10.7655/NYDXBNSN260333
From data integration to clinical translation:a review of machine learning applications in
depression diagnosis
2
1
1
1
1
1
1*
1
GAO Zixiang ,LI Xiang ,ZHANG Xin ,QIAN Zhaojun ,JI Zihui ,ZHU Lixuan ,XU Yichu ,CHEN Yali ,GE
Feifei 1*
2
1 School of Medicine,School of Artificial Intelligence and Information Technology,Nanjing University of Chinese
Medicine,Nanjing 210023,China
[Abstract] Depression is characterized by an insidious onset and marked symptom heterogeneity. Current diagnostic practice still
mainly relies predominantly on clinical interviews and rating scales,which are constrained by substantial subjectivity,limited capacity
for early identification,and insufficient performance in subtype differentiation and prognostic evaluation. With the growing availability
of objective data,including neuroimaging,electroencephalography,speech and digital behavioral features,clinical scales,and multi⁃
omics profiles,machine learning has opened new avenues for the objective identification of depression. Focusing on this central issue,
the present review summarizes recent advances in the application of machine learning to neuroimaging and other unimodal objective
data,further discusses the integrative value of multimodal data in the diagnosis,subtyping,disease⁃course assessment,and treatment⁃
response prediction of depression,and provides a systematic overview of common fusion strategies,model interpretability,and issues
related to clinical translation.
[Key words] depression;machine learning;neuroimaging;multimodal data;auxiliary diagnosis
[J Nanjing Med Univ,2026,46(07):1011⁃1019]
1 抑郁症诊断现状及机器学习在单模态数据中的
应用
[基金项目] 国家自然科学基金(82574736);国家级大学生
抑郁症是一种常见的慢性复发性精神障碍,起
创新训练计划项目(202510315005)
病隐匿、病程迁延,复发率与致残率居高不下,严重
∗
通信作者(Corresponding author),E ⁃ mail:ffge@njucm.edu.cn
影响患者社会功能并加重公共卫生负担 。目前临
[1]
(ORCID:0000⁃0003⁃1336⁃8587);ylchen@njucm.edu.cn(OR⁃
CID:0009⁃0004⁃8738⁃1666) 床诊断主要依据精神障碍诊断操作性标准,结合汉

