The evidence base for GAI-based teaching in medical education is of low quality with substantial heterogeneity and reporting gaps¶

Claim · All claims
Evidence · 1 study · quant-synthesis r2 · q3
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? GRADE assessment rated the overall quality of evidence as low, attributed to substantial heterogeneity, inadequate randomization reporting, and limited blinding across the 11 included RCTs. → Li Juan 2025

Evidence¶

Li Juan 2025¶

Li Juan, Yin Kaiyu, Wang Yida, Jiang Xiaoqin, Chen Dongxu. (2025). Effectiveness of generative artificial intelligence-based teaching versus traditional teaching methods in medical education: a meta-analysis of randomized controlled trials. BMC Medical Education. https://doi.org/10.1186/s12909-025-07750-2

q3 · i? · quant-synthesis · r2

Risk-of-bias assessment with the Cochrane tool and GRADE rating across the 11 included RCTs. Only 5 studies had low-risk random sequence generation, one had low-risk allocation concealment, and incomplete outcome data and selective reporting were high risk in 2 studies each.

"The overall quality of evidence, as evaluated using the GRADE framework, was categorized as low (Appendix 2). This classification was primarily attributed to substantial heterogeneity across studies, inadequate reporting of randomization procedures, and limited implementation of blinding methods."

Discussion¶

Related Claims¶

• GAI-based teaching and traditional teaching produce comparable knowledge acquisition scores in medical students — related
• Evidence quality is limited by heterogeneity in VR platforms, publication bias, and unclear randomization in included trials — related