TRIPOD-LLM: First Reporting Guideline for Large Language Models in Healthcare Research
TRIPOD-LLM extends the established TRIPOD+AI reporting framework specifically for studies using large language models in biomedical applications, providing a 19-item, 50-subitem checklist covering transparency, human oversight, and task-specific performance reporting. Developed through an expedited Delphi process, the guideline introduces a modular format accommodating diverse LLM research designs and includes an interactive web tool for checklist completion. As a living document, it aims to standardise the rapidly expanding field of clinical LLM research.
The original study
The TRIPOD-LLM reporting guideline for studies using large language models.
- Authors
- Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, et al.
- Journal
- Nature medicine
- Type
- Journal Article, Review
- PMID
- 39779929
Original abstract
Large language models (LLMs) are rapidly being adopted in healthcare, necessitating standardized reporting guidelines. We present transparent reporting of a multivariable model for individual prognosis or diagnosis (TRIPOD)-LLM, an extension of the TRIPOD + artificial intelligence statement, addressing the unique challenges of LLMs in biomedical applications. TRIPOD-LLM provides a comprehensive checklist of 19 main items and 50 subitems, covering key aspects from title to discussion. The guidelines introduce a modular format accommodating various LLM research designs and tasks, with 14 main items and 32 subitems applicable across all categories. Developed through an expedited Delphi process and expert consensus, TRIPOD-LLM emphasizes transparency, human oversight and task-specific performance reporting. We also introduce an interactive website ( https://tripod-llm.vercel.app/ ) facilitating easy guideline completion and PDF generation for submission. As a living document, TRIPOD-LLM will evolve with the field, aiming to enhance the quality, reproducibility and clinical applicability of LLM research in healthcare through comprehensive reporting.