TRIPOD + LLM: reporting guidelines for prediction models using large language models

Dr. Marianne Huebner, CSTAT and Department of Statistics and Probability

Reporting guidelines are consensus-based tools to help authors clearly and completely report their research, ensuring reliability and usability. 

Prediction models estimate

• the probability of a certain condition being present but not yet detected (diagnosis)
• the probability of an outcome developing in the future (prognosis)

We will briefly introduce the background of prediction models, performance, and validation, and then discuss reporting guidelines of the TRIPOD statement. TRIPOD-LLM is an extension addressing the unique challenges of large language models in biomedical applications.

Prerequisite: Familiarity with regression modeling.

*This seminar is available for RECR Credit, 1.5 Hours. Attendance will be verified and a survey must be completed afterwards with well thought out responses to receive RECR Credit.

References:

Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, Demner-Fushman D, Dligach D, Daneshjou R, Fernandes C, Hansen LH, Landman A, Lehmann L, McCoy LG, Miller T, Moreno A, Munch N, Restrepo D, Savova G, Umeton R, Gichoya JW, Collins GS, Moons KGM, Celi LA, Bitterman DS. The TRIPOD-LLM reporting guideline for studies using large language models. Nat Med. 2025 Jan;31(1):60-69. doi: 10.1038/s41591-024-03425-5

Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, Ghassemi M, Liu X, Reitsma JB, van Smeden M, Boulesteix AL, Camaradou JC, Celi LA, Denaxas S, Denniston AK, Glocker B, Golub RM, Harvey H, Heinze G, Hoffman MM, Kengne AP, Lam E, Lee N, Loder EW, Maier-Hein L, Mateen BA, McCradden MD, Oakden-Rayner L, Ordish J, Parnell R, Rose S, Singh K, Wynants L, Logullo P. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024 Apr 16;385:e078378. doi: 10.1136/bmj-2023-078378.