EP 254 ChatGTP in Undergraduate Medical Education- A Systematic Review and Meta-Analysis

Abstract

Artificial intelligence (AI) is increasingly embedded Gen-Z, with ChatGPT emerging as an educational tool. Its application has expanded rapidly across disciplines, including medical education, where it is widely used. Robust evidence synthesising its effectiveness in undergraduate medical education is still evolving. This study aimed to evaluate the impact of ChatGPT-assisted teaching compared with traditional educational methods in undergraduate medical students. A systematic review and meta-analysis were conducted in accordance with PRISMA 2020 guidelines. Independent searches were performed across PubMed, Embase, Ovid full-text journals, and the Cochrane Library using the terms “ChatGPT” and “medical education” in titles and abstracts until 25th September 2025. Randomised controlled trials involving undergraduate medical students were included. The intervention was ChatGPT-assisted teaching, with traditional classroom and bedside teaching as the comparator. Statistical analysis was performed using RevMan 5.0 with a random-effects model. Six randomised controlled trials met the inclusion criteria, comprising 361 undergraduate medical students (182 in the ChatGPT group and 179 in the traditional teaching group). ChatGPT-assisted learning was associated with significantly higher assessment scores, with a pooled mean difference of 6.21 points in favour of ChatGPT (95% CI 2.03–10.39, p = 0.004). Heterogeneity was substantial (I² = 98%), indicating marked variability between studies. ChatGPT-assisted teaching significantly improves learning outcomes in undergraduate medical students compared with traditional teaching. However, the very high heterogeneity and potential publication bias necessitate cautious interpretation, and further high-quality trials are required to define optimal educational implementation.