Exploratory subgroup analysis suggests larger effects in practice courses than theory courses, driven by only 2 practice-oriented studies¶

Claim · All claims
Evidence · 1 study · quant-synthesis r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Exploratory subgroup analysis showed pooled SMD 0.60 (95% CI -0.10 to 1.30) for theory courses and SMD 1.60 (95% CI -0.21 to 3.41) for practice courses, with a course-type interaction (Qbetween = 24.31, P = 8.2e-07) but no interaction for learning duration (Qbetween = 0.26, P = 0.608). → Liu Xiaoliu 2026

Evidence¶

Liu Xiaoliu 2026¶

Liu Xiaoliu, Pan Jiayue, Zhang Chengyi, Wang Xiaomei, Wan Jinghua, Wang Qiang. (2026). Effectiveness of large language model-based teaching interventions in medical education: a systematic review and stratified meta-analysis of 14 studies. BMC Medical Education. https://doi.org/10.1186/s12909-026-09879-0

q3 · i? · quant-synthesis · r2

Exploratory subgroup analysis within the pooled score-based synthesis, stratified by course type (5 theory vs. 2 practice studies) and learning duration. Only test statistics are printed (Qbetween = 24.31, P = 8.2e-07), so no effect size for the interaction; the practice-course signal was "driven mainly by only two practice-oriented studies".

"The fixed-effect interaction test for course type suggested a statistical signal (Qbetween = 24.31, P = 8.2e-07), but this result was driven mainly by only two practice-oriented studies and within-group heterogeneity remained high."

Discussion¶

Related Claims¶

• LLM-based teaching is associated with higher post-course score-based outcomes than non-AI teaching in an exploratory pooled synthesis (SMD 0.90), with very high heterogeneity — a broader claim this one bears on
• Flipped classrooms are associated with improved procedural/technical skills in medical education (pooled SMD = 1.80), with larger effects among residents and in theoretical-course settings — reports the opposite
• Flipped classroom significantly improves practical exam scores over lecture-based learning (pooled SMD 0.50) — related
• Flipped classrooms are associated with higher learner satisfaction in medical education (pooled SMD = 0.69), with residents showing larger improvement than undergraduates (SMD 1.69 vs 0.37) — related
• Strict knowledge acquisition shows a smaller positive pooled signal for LLM-based teaching (SMD 0.80) — related
• Flipped classroom significantly improves theoretical exam scores over lecture-based learning in Chinese undergraduate preventive medicine courses (pooled SMD 0.99) — related