Are ChatGPT’s knowledge and interpretation ability comparable to those of medical students in Korea for taking a parasitology examination?: a descriptive study

作者：Sun Huh · 发表于：Journal of Educational Evaluation for Health Professions · 年份：2023 · DOI：10.3352/jeehp.2023.20.1 · 被引用次数：243 · 研究领域：Artificial Intelligence in Healthcare and Education、Topic Modeling、Explainable Artificial Intelligence (XAI)

This study aimed to compare the knowledge and interpretation ability of ChatGPT, a language model of artificial general intelligence, with those of medical students in Korea by administering a parasitology examination to both ChatGPT and medical students. The examination consisted of 79 items and was administered to ChatGPT on January 1, 2023. The examination results were analyzed in terms of ChatGPT’s overall performance score, its correct answer rate by the items’ knowledge level, and the acceptability of its explanations of the items. ChatGPT’s performance was lower than that of the medical students, and ChatGPT’s correct answer rate was not related to the items’ knowledge level. However, there was a relationship between acceptable explanations and correct answers. In conclusion, ChatGPT’s knowledge and interpretation ability for this parasitology examination were not yet comparable to those of medical students in Korea.