A Meta-analysis of the application effect of artificial intelligence-assisted teaching in medical education

WEI Wei; LUO Gaomeng; LIU Runming; LIU Sha; LI Xiang

doi:10.12173/j.issn.1004-5511.202505084

Abstract：Objective To evaluate the effectiveness of artificial intelligence(AI)-assisted teaching in medical education through Meta-analysis.Methods PubMed,Web of Science,Embase,Wanfang,CNKI,and VIP databases were searched from database creation to April 1,2025,to identify relevant studies on the application of AI-assisted teaching in medical education.The risk of bias was assessed using the Cochrane Collaboration's tool for assessing risk of bias.Meta-analysis was performed using R software.Heterogeneity tests,subgroup analyses,and sensitivity analyses were used to verify the robustness of the results.Results A total of 17 randomized controlled trials were included.Compared with traditional teaching,AI-assisted teaching significantly improved medical education participants' theoretical scores[SMD=1.35,95％CI(0.78,1.92)],practical/operational skills[SMD=2.45,95％CI(0.89,4.02)],and teaching satisfaction[RR=1.39,95％CI(1.20,1.61)].The differences were statistically significant(P＜0.05).Subgroup analysis showed that,compared with traditional teaching,AI-assisted medical education improved theoretical performance across different medical education groups(junior college students,undergraduate students,graduate students,and physicians)and practical/operational skills across some groups(junior college students,undergraduate students,and physicians).Sensitivity analysis showed robust results,except for publication bias in theoretical performance,and the conclusions were unchanged after trimming and filling correction.Conclusion AI can effectively empower medical education,significantly improving learning outcomes and teaching satisfaction,and contributing to the cultivation of clinical medical talent.