Large language model-supported interactive case-based learning: a pilot study.

IF 1.8 4区医学 Q2 MEDICINE, GENERAL & INTERNAL

Internal Medicine Journal Pub Date : 2025-03-24 DOI:10.1111/imj.70030

Haelynn Gim, Benjamin Cook, Jasmin Le, Brandon Stretton, Christina Gao, Aashray Gupta, Joshua Kovoor, Christina Guo, Matthew Arnold, Galina Gheihman, Stephen Bacchi

引用次数: 0

Abstract

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.

查看原文本刊更多论文

大语言模型（LLM）已被提出作为增强基于案例的学习的一种手段，但容易产生与事实不符的内容。本研究开发了一种基于 LLM 的工具，并对其性能进行了评估。在回答学生提出的问题时，LLM 在 832/857 个（97.1%）案例中符合所提供的剧本，在其余案例中，LLM 在 24/25 个（96.0%）案例中符合医学要求。为此目的使用 LLM 似乎是可行的，但仍需进一步研究其对教育的影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Internal Medicine Journal 医学-医学：内科

CiteScore

3.50

自引率

4.80%

发文量

600

审稿时长

3-6 weeks

期刊介绍： The Internal Medicine Journal is the official journal of the Adult Medicine Division of The Royal Australasian College of Physicians (RACP). Its purpose is to publish high-quality internationally competitive peer-reviewed original medical research, both laboratory and clinical, relating to the study and research of human disease. Papers will be considered from all areas of medical practice and science. The Journal also has a major role in continuing medical education and publishes review articles relevant to physician education.