Large language model‐supported interactive case‐based learning: a pilot study
Large language models (LLMs) have been proposed as a means to augment case-based learning but are prone to generating factually incorrect content. In this study, an LLM-based tool was developed, and its performance evaluated. In response to student-generated questions, the LLM adhered to the provided screenplay in 832/857 (97.1%) instances, and in the remaining instances, it was medically appropriate in 24/25 (96.0%) cases. Use of LLM appears to be feasible for this purpose, and further studies are required to examine their educational impact.
Authors
- Aashray Gupta (ORCID: https://orcid.org/0000-0002-8038-0378)
- Stephen Bacchi (ORCID: https://orcid.org/0000-0001-5130-8628)
- Brandon Stretton (ORCID: https://orcid.org/0000-0002-7939-3489)
- Joshua G. Kovoor (ORCID: https://orcid.org/0000-0002-3880-3840)
- Christina Guo (ORCID: https://orcid.org/0000-0002-1645-3202)
- Matthew Arnold (ORCID: https://orcid.org/0009-0005-9510-0948)
- Galina Gheihman (ORCID: https://orcid.org/0000-0003-1599-3271)
- Benjamin K. Cook (ORCID: https://orcid.org/0009-0000-1993-213X)
- Jasmin Le
- Christina Gao (ORCID: https://orcid.org/0009-0005-0033-3352)
- Haelynn Gim
Institutions
- Harvard University (US)
- Johns Hopkins University (US)
- Flinders University (AU)
- Lyell McEwin Hospital (AU)
- The Alfred Hospital (AU)
- Massachusetts General Hospital (US)
- Ballarat Health Services (AU)
- Mass General Brigham (US)
- The University of Adelaide (AU)
Publication Details
- Journal
- Internal Medicine Journal
- Published
- 2025-03-24
- DOI
- https://doi.org/10.1111/imj.70030
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62
Funders
- Fulbright Australia