Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Psychiatry. Nov 19, 2025; 15(11): 108199
Published online Nov 19, 2025. doi: 10.5498/wjp.v15.i11.108199
Published online Nov 19, 2025. doi: 10.5498/wjp.v15.i11.108199
Large language models in clinical psychiatry: Applications and optimization strategies
Yi-Fan Wang, Lin Lu, National Institute on Drug Dependence and Beijing Key Laboratory of Drug Dependence, Peking University, Beijing 100191, China
Ming-Da Li, Lin Lu, Wei Yan, Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China
Su-Hong Wang, College of Future Technology Peking University, Peking University, Beijing 100871, China
Yin Fang, School of Public Health, North China University of Science and Technology, Tang
Jie Sun, Pain Medicine Center, Peking University Third Hospital, Beijing 100191, China
Lin Lu, Peking-Tsinghua Center for Life Sciences and PKU-IDG/McGovern Institute for Brain Research, Peking University, Beijing 100871, China
Co-first authors: Yi-Fan Wang and Ming-Da Li.
Co-corresponding authors: Lin Lu and Wei Yan.
Author contributions: Wang YF and Li MD conducted the literature review, interpretation of data and drafted the original manuscript, they contributed equally to this article, they are the co-first authors of this manuscript; Wang SH, Fang Y, and Sun J revised the manuscript; Lu L and Yan W conceptualized and designed the study, supervised, and made critical revisions they contributed equally to this article, they are the co-corresponding authors of this manuscript; and all authors prepared the draft and approved the submitted version.
Supported by the STI2030-Major Projects, No. 2021ZD0203400 and No. 2021ZD0200800; and the National Natural Science Foundation of China, No. 82171477.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Wei Yan, Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Huayuan Bei Road, Beijing 100191, China. weiyan@bjmu.edu.cn
Received: April 14, 2025
Revised: May 27, 2025
Accepted: September 3, 2025
Published online: November 19, 2025
Processing time: 205 Days and 5.1 Hours
Revised: May 27, 2025
Accepted: September 3, 2025
Published online: November 19, 2025
Processing time: 205 Days and 5.1 Hours
Core Tip
Core Tip: This article comprehensively reviews the application scenarios and research advancements of large language models (LLMs) in psychiatry, ranging from outpatient reception, diagnosis and therapy, clinical nursing, medication safety, to prognosis tracking. It explores optimization methods for LLMs in psychiatry. These methods combine the techniques such as pre-training, supervised fine-tuning, retrieval-augmented generation, agent systems, and prompt engineering. Based on the research findings, we propose a clinical LLM for mental health using the Mixture of Experts framework. This approach addresses the shortcomings of single LLM system and aims to improve the accuracy of psychiatric diagnosis and therapeutic interventions.