Claims

AI-powered PBL/CBL shows favourable but heterogeneous effects on clinical reasoning capability that could not be statistically pooled

Claim · All claims
Evidence · 1 study (3 entries) · quant-synthesis r1–r2 · q2 · i3 large
Currency · newest study 2025 · checked against its sources 2026-10-31 (automated, 3 of 3 entries) · not reviewed by a person

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q2 i3 LearnGuide, a customised ChatGPT tool, showed higher effectiveness than traditional PBL for clinical reasoning (SMD = 1.34, 95% CIs [0.91,1.77]). → Wei H 2025 q2 i3 ChatGPT-assisted PBL showed a weaker favourable effect on clinical reasoning versus traditional teaching (SMD = 0.90, 95% CIs [0.26,1.54]). → Wei H 2025 (2) q2 i? COMET-tutored students' clinical reasoning gains were similar to human-tutored students, with no significant post-test difference (Mann-Whitney, P = .058). → Wei H 2025 (3)

Evidence

Wei H 2025

Wei H, Dai Y, Yuan K, Li KY, Hung KF, Hu EM, Lee AHC, Chang JWW, Zhang C, Li X. (2025). AI-Powered Problem- and Case-based Learning in Medical and Dental Education: A Systematic Review and Meta-analysis. International Dental Journal. https://doi.org/10.1016/j.identj.2025.100858

q2 · i3 · quant-synthesis · r2

Descriptive synthesis of one RCT (Wang et al., 101 medical undergraduates and postgraduates) measuring clinical reasoning with CCTT Level Z; the review reports "SMD = 1.34" versus traditional PBL, noting the measure relied on subjective self-assessment.

"Compared with traditional PBL, the integration of LearnGuide, a customised tool based on ChatGPT, showed higher effectiveness in enhancing clinical reasoning capability (SMD = 1.34, 95% CIs [0.91,1.77])."

Wei H 2025 (2)

Wei H, Dai Y, Yuan K, Li KY, Hung KF, Hu EM, Lee AHC, Chang JWW, Zhang C, Li X. (2025). AI-Powered Problem- and Case-based Learning in Medical and Dental Education: A Systematic Review and Meta-analysis. International Dental Journal. https://doi.org/10.1016/j.identj.2025.100858

q2 · i3 · quant-synthesis · r2

Descriptive synthesis of one RCT (Zeng et al., 42 fifth-year medical interns) using mini-CEX assessment; ChatGPT-assisted PBL showed "SMD = 0.90" versus traditional teaching on clinical judgment and overall clinical competence.

"A weaker favourable effect was observed in ChatGPT-assisted PBL when compared to traditional teaching (SMD = 0.90, 95% CIs [0.26,1.54])."

Wei H 2025 (3)

Wei H, Dai Y, Yuan K, Li KY, Hung KF, Hu EM, Lee AHC, Chang JWW, Zhang C, Li X. (2025). AI-Powered Problem- and Case-based Learning in Medical and Dental Education: A Systematic Review and Meta-analysis. International Dental Journal. https://doi.org/10.1016/j.identj.2025.100858

q2 · i? · quant-synthesis · r1

Descriptive synthesis of one RCT (Suebnukarn, 36 second-year dental students) using the clinical reasoning problem approach; COMET-tutored and human-tutored groups did not differ significantly (P = .058); normality test was not fulfilled.

"Previous studies using the CRP approach showed that the clinical reasoning gains for AI-tutored students were similar to those for human-tutored students, with no significant difference in the average post-test score observed for the 2 groups (Mann-Whitney, P = .058)."

Discussion

Page metadata
Field Value
status review
generated by process:wiki-ingest on 2026-10-31
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.