Use of Large Language Models for Rapid Quantitative Feedback in Case-Based Learning: A Pilot Study
Name
40670_2025_2343_ReferencePDF.pdf
Size
315.93 KB
Format
Adobe PDF
Checksum (MD5)
01cd8509abc2750aa8a53a3cff686d47
Author(s)
Qian, Carolyn
Gao, Christina
Park, Sang-O.
Gim, Haelynn
Hou, Kelly
Cook, Benjamin
Le, Jasmin
Stretton, Brandon
Maddison, John
McCoy, Liam
Date Issued
February 28, 2025
Journal
Medical Science Educator
Publisher
Springer US
Citation
Qian, C., Gao, C., Park, SO. et al. Use of Large Language Models for Rapid Quantitative Feedback in Case-Based Learning: A Pilot Study. Med.Sci.Educ. 35, 1169–1171 (2025).
Version
Author's final manuscript
Abstract
Abstract Large language models (LLMs) may be able to deliver interactive case-based content and score student interactions with such cases. In this study, GPT-4o demonstrated a high correlation with expert scorers in the evaluation of medical students’ interactions with cases. A difference between LLM scores and expert scorers was corrected through calibration.
MIT Department
Institute for Medical Engineering and Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s40670-025-02343-6
