Applications of large language models in psychiatry: a systematic review

Abstract

Background: With their unmatched ability to interpret and engage with human language and context, large language models (LLMs) hint at the potential to bridge AI and human cognitive processes. This review explores the current application of LLMs, such as ChatGPT, in the field of psychiatry.

Methods: We followed PRISMA guidelines and searched through PubMed, Embase, Web of Science, and Scopus, up until March 2024.

Results: From 771 retrieved articles, we included 16 that directly examine LLMs' use in psychiatry. LLMs, particularly ChatGPT and GPT-4, showed diverse applications in clinical reasoning, social media, and education within psychiatry. They can assist in diagnosing mental health issues, managing depression, evaluating suicide risk, and supporting education in the field. However, our review also points out their limitations, such as difficulties with complex cases and potential underestimation of suicide risks.

Conclusion: Early research in psychiatry reveals LLMs' versatile applications, from diagnostic support to educational roles. Given the rapid pace of advancement, future investigations are poised to explore the extent to which these models might redefine traditional roles in mental health care.

Keywords: LLMS; artificial intelligence; generative pre-trained transformer (GPT); large language model; psychiatry.

Figure 1

SJR scores and journal quartiles of the included studies.

Figure 2

PRISMA flowchart.

Figure 3

A demographic distribution graph showing the publication years and countries of origin for the included studies.

Figure 4

Applications and evaluations of LLMs in diverse domains of psychiatry.

Figure 5

Data Input Spectrum for GPT in Psychiatric Applications.

Figure 6

Strengths and limitations of GPT’s current applications in psychiatry practice.