心理科学进展2026，Vol.34Issue(3)：424-440,中插1-中插3,20.DOI:10.3724/SP.J.1042.2026.0424
大模型在抑郁症筛查与诊断中的应用
The application of foundation models in depression screening and diagnosis
摘要
Abstract
Depression is a common mental disorder that significantly impairs patients'social functioning and quality of life.In recent years,foundation models,with their powerful semantic understanding capability and multimodal data-processing capacity,have shown notable potential in the early screening and auxiliary diagnosis of depression.The construction of foundation model-based systems for depression screening and diagnosis typically involves four stages:data preprocessing,model selection,model training,and model evaluation.In these applications,foundation models primarily operate through contextualized semantic representation,attention mechanisms,multimodal behavioral capture,and predictive processing.Despite these advantages,their application still faces challenges such as algorithmic bias,insufficient diagnostic specificity,hallucination phenomena,privacy and security concerns,and ethical risks.In the future,the integration of foundation models into psychological intervention frameworks should be strengthened,with an emphasis on clinical translation pathways,in order to construct a more refined,dynamic,and culturally adaptive digital phenotype of depression,and to achieve the digital and intelligent transformation of mental health services.关键词
大模型/抑郁症/早期筛查/辅助诊断Key words
foundation models/depression/early screening/auxiliary diagnosis分类
医药卫生引用本文复制引用
谢宇,郑弘欣,刘怡资,禹红刚,杨成赫..大模型在抑郁症筛查与诊断中的应用[J].心理科学进展,2026,34(3):424-440,中插1-中插3,20.基金项目
安徽省高等学校思想政治教育研究会2024年度高校思想政治教育研究专项课题(2024SZX012) （2024SZX012）
中国电信股份有限公司大中小一体化智能心育研发项目(24AHEKYF5020). （24AHEKYF5020）
