The effectiveness of GAI-assisted teaching methods in medical education: a systematic review and meta-analysis

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Objective: The study evaluated the effectiveness of generative artificial intelligence (GAI)-assisted teaching methods on the medical educational outcomes. Methods: Following the PRISMA guidelines, a systematic search was conducted for literature on AI-assisted educational interventions in medical education (e.g. clinical, nursing and dentistry medicine). PROSPERO registration number was CRD420251173150. Meta-analyses of the outcomes were performed using the Review Manager 5.4. Heterogeneity was evaluated using the I 2 statistic and Cochran's Q test. A forest plot, Egger's test and the trim-and-fill method were used to evaluate publication bias and robustness. Results: A total of 5,764 publications was initially retrieved, of which 78 studies involving 3,635 medical students in the GAI-assisted teaching group and 3,931 medical students in the control group were included. The pooled results revealed that GAI-assisted teaching significantly improved academic performance in terms of both knowledge (SMD = 0.95, 95% CI: 0.72–1.18, p < 0.05) and practical (SMD = 1.48, 95% CI: 1.20–1.77, p < 0.05) scores, compared to the control group. Additional benefits included improved student satisfaction (SMD = 1.52, 95% CI: 1.01–2.02, p < 0.05), self-efficacy in learning (SMD = 0.75, 95% CI: 0.17–1.32, p < 0.05), learning initiative (SMD = 1.20, 95% CI: 0.10–2.30, p < 0.05), self-directed learning ability (SMD = 1.25, 95% CI: 0.81–1.69, p < 0.05), clinical thinking ability (SMD = 1.18, 95% CI: 0.86–1.50, p < 0.05) and analytical and problem-solving skills (SMD = 1.53, 95% CI: 0.77–2.29, p < 0.05). Conclusions: The results showed that the GAI-assisted teaching could improve efficiently various aspects of education outcomes for medical students, including academic performance, self-efficacy and initiative in learning, and skills development. In future, policymakers should consider integrating artificial intelligence into teacher training and medical curriculum design to improve learning outcomes.

This publication has 66 references indexed in Scilit: