aceModerate evidence
Published recordEducationGood Space
More
Meta-analysis of randomized controlled trials comparing outcomes of artificial intelligence-based teaching versus traditional-based teaching in medical education
- Truvace record
- TRV-2026-2786raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Systematic review or meta-analysis
- Sources
- 1 sourcePeer-reviewed
- sha256
- 349363a7f434…check it
AIMS: To evaluate comparative outcomes of artificial Intelligence (AI)-based and traditional-based teaching in medical education. METHODS: The literature search was carried out in CENTRAL, CINAHL, Web of Science, MEDLINE, and EMBASE to identify randomized controlled trials (RCTs) comparing AI-based versus traditional-based teachings in medical education. Estimate of effect size was determined for knowledge score, skills score, and teaching satisfaction score via fixed-effect modelling. RESULTS: Fourteen RCTs enr…
The gain
A meta-analysis of 14 randomized trials with 1,116 medical students found AI-based teaching produced higher knowledge scores (SMD 0.36), skills scores (SMD 0.78) and satisfaction scores (SMD 0.97) than traditional teaching.
What this doesn’t fix
The authors say the evidence may be subject to publication and reporting bias, with high heterogeneity between studies, and the trials covered medical students rather than postgraduate trainees.
Sources
1 on file- Postgraduate Medical Journaldoi:10.1093/postmj/qgag077
What the review found when it combined the studies
These are the review’s own pooled results, copied from its abstract. Truvace did not recalculate them.
Medical student knowledge score with AI-based teaching compared with traditional teaching
SMD 0.36 (95% CI 0.24 to 0.49)
1,116 people
The review’s own words
The use of AI-based teaching was associated with significantly higher knowledge score (standardized mean difference (SMD): 0.36, 95% CI, 0.24-0.49, P < .00001), skills score (SMD: 0.78, 95% CI, 0.57-0.99, P < .00001), and teaching satisfaction score (SMD: 0.97, 95% CI, 0.66-1.29, P < .00001) compared to the traditional-based teaching.
Medical student teaching satisfaction score with AI-based teaching compared with traditional teaching
SMD 0.97 (95% CI 0.66 to 1.29)
1,116 people
The review’s own words
The use of AI-based teaching was associated with significantly higher knowledge score (standardized mean difference (SMD): 0.36, 95% CI, 0.24-0.49, P < .00001), skills score (SMD: 0.78, 95% CI, 0.57-0.99, P < .00001), and teaching satisfaction score (SMD: 0.97, 95% CI, 0.66-1.29, P < .00001) compared to the traditional-based teaching.
Medical student skills score with AI-based teaching compared with traditional teaching
SMD 0.78 (95% CI 0.57 to 0.99)
1,116 people
The review’s own words
The use of AI-based teaching was associated with significantly higher knowledge score (standardized mean difference (SMD): 0.36, 95% CI, 0.24-0.49, P < .00001), skills score (SMD: 0.78, 95% CI, 0.57-0.99, P < .00001), and teaching satisfaction score (SMD: 0.97, 95% CI, 0.66-1.29, P < .00001) compared to the traditional-based teaching.
Code checks every number above against the review’s text before it is shown. The short labels are an AI model’s reading of that text, so the review’s own sentence sits under each one. A pooled figure is only as strong as the studies behind it. How Truvace uses pooled results
Cite this record
v1Truvace Impact Record TRV-2026-2786, v1: “Meta-analysis of randomized controlled trials comparing outcomes of artificial intelligence-based teaching versus traditional-based teaching in medical education.” Truvace, 2026-11-12. /record/TRV-2026-2786 (accessed on the day you copy it). sha256 349363a7f434abbe…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2786 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.