System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Epublish

PubMed: 40514050 DOI: 10.1136/bmjment-2025-301787

Role of large language models in mental health research: an international survey of researchers' practices and perspectives.

BMJ Ment Health 28(1)

Authors: Jake Linardon, Mariel Messer, Cleo Anderson, Claudia Liu, Zoe McClure, Hannah K Jarman, Simon B Goldberg, John Torous

Affiliations

  • SEED Lifespan Strategic Research Centre, School of Psychology, Faculty of Health, Deakin University, Geelong, Victoria, Australia.
  • SEED Lifespan Strategic Research Centre, School of Psychology, Faculty of Health, Deakin University, Geelong, Victoria, Australia.
  • Department of Counselling Psychology, University of Wisconsin, Madison, Wisconsin, USA.
  • Center for Healthy Minds, University of Wisconsin, Madison, Wisconsin, USA.
  • Division of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA.

Abstract

BACKGROUND

Large language models (LLMs) offer significant potential to streamline research workflows and enhance productivity. However, limited data exist on the extent of their adoption within the mental health research community.

OBJECTIVE

We examined how LLMs are being used in mental health research, the types of tasks they support, barriers to their adoption and broader attitudes towards their integration.

METHODS

714 mental health researchers from 42 countries and various career stages (from PhD student, to early career researcher, to Professor) completed a survey assessing LLM-related practices and perspectives.

FINDINGS

496 (69.5%) reported using LLMs to assist with research, with 94% indicating use of ChatGPT. The most common applications were for proofreading written work (69%) and refining or generating code (49%). LLM use was more prevalent among early career researchers. Common challenges reported by users included inaccurate responses (78%), ethical concerns (48%) and biased outputs (27%). However, many users indicated that LLMs improved efficiency (73%) and output quality (44%). Reasons for non-use were concerns with ethical issues (53%) and accuracy of outputs (50%). Most agreed that they wanted more training on responsible use (77%), that researchers should be required to disclose use of LLMs in manuscripts (79%) and that they were concerned about LLMs affecting how their work is evaluated (60%).

CONCLUSION

While LLM use is widespread in mental health research, key barriers and implementation challenges remain.

CLINICAL IMPLICATIONS

LLMs may streamline mental health research processes, but clear guidelines are needed to support their ethical and transparent use across the research lifecycle.

MeSH

Language, Machine Learning, Work, Research, Mental Health, Psychiatry