EUVIMEDOdkrijte EUVIMED
Systematische ÜbersichtMetaanalyseOpen access

The Effectiveness of Artificial Intelligence in Undergraduate Health Professions Education: Systematic Review and Meta-Analysis of Randomized Controlled Trials

Wirksamkeit künstlicher Intelligenz in der Ausbildung von Gesundheitsberufen im Studium: systematische Übersicht und Metaanalyse randomisierter kontrollierter Studien

Nai Ming Lai iD, Yin Sear Lim iD, Min Thein Win iD, Prabal Bhargava iD, Paraidathathu Thomas iD, Qi Chwen Ong iD

JMIR Medical Education · 2026-05-05 · 12 · e88933-e88933

DOI: 10.2196/88933 ↗

Auf einen Blick

66 RCTs mit 4911 Teilnehmenden: Einige KI-Interventionen zeigten positive Effekte auf Zufriedenheit, Vertrauen und theoretisches Wissen. Die Evidenz war insgesamt niedrig bis sehr niedrig.

Fragestellung

Wie wirksam ist KI in der Ausbildung von Gesundheitsberufen im Studium im Vergleich zu Standardlehre?

Methode

Systematische Übersicht und Metaanalyse von RCTs, randomisierten Crossover- und Cluster-RCTs; Suche in PubMed, Cochrane, Embase, ERIC und Web of Science bis 26. Januar 2026; GRADE.

Ergebnisse

66 RCTs mit N=4911 Teilnehmenden. LLM-basierte personalisierte Lernhilfen: Zufriedenheit SMD 0,93 (95 %-KI 0,40–1,46; 7 Studien; 430 Teilnehmende), Vertrauen SMD 0,91 (95 %-KI 0,54–1,29; 7; 609) und theoretisches Wissen SMD 0,53 (95 %-KI 0,13–0,94; 12; 955).

Einschränkungen

Viele Studien mit hohem Verzerrungsrisiko; Heterogenität und Ungenauigkeit; keine Studien zu Kirkpatrick-Level 3 oder 4.

Schlussfolgerung der Autor:innen

Trotz der großen Zahl eingeschlossener Studien reicht die Evidenz nicht aus, um die Bildungspraxis zu informieren. Einige KI-Interventionen könnten Lernoutcomes verbessern, die Effekte sind aber inkonsistent.

Kernaussagen

  • LLM-basierte Lernhilfen zeigten positive Effekte auf mehrere Outcomes
  • Evidenz insgesamt niedrig bis sehr niedrig
  • Keine Studien zu Kirkpatrick-Level 3 oder 4

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in JMIR Medical Education, published online on 2026-05-05. Written by Nai Ming Lai and 5 co-authors. Institution: School of Medicine, Faculty of Health and Medical Sciences, Taylor's University, Subang Jaya, Selangor, Malaysia. Major MEDLINE topics: Artificial Intelligence, Health Occupations, Education, Medical, Undergraduate. Cited 10 times so far (Crossref); 121 references. The full text is freely available in PubMed Central.

Auf einen BlickPovzetekSubjectsBibliografski podatkiCiteRelated studies

Abstract (original language)

Background

Health professions education faces increasing challenges from rising health care complexity, pedagogical shifts, and constrained curricular space, and rapidly expanding knowledge and technological advances. While artificial intelligence (AI) shows promise for transforming health professions education, evidence of its effectiveness remains unclear.

Objective

This study synthesized evidence from randomized controlled trials (RCTs) on the effectiveness of AI in undergraduate health professions education.

Methods

We included RCTs, randomized crossover trials, and cluster RCTs comparing AI against standard educational interventions at the undergraduate level. We excluded quasi-experimental studies and those without clear AI components. We searched PubMed, Cochrane, Embase, Educational Resources Information Center, and Web of Science up to January 26, 2026. Outcomes were categorized according by Kirkpatrick levels; risk of bias was assessed using the Risk Of Bias Instrument for Use in Systematic Reviews for Randomised Controlled Trials tool; random-effects meta-analysis was conducted in RevMan (Cochrane); and certainty of evidence was rated using the Grading of Recommendations, Assessment, Development, and Evaluation approach. AI interventions were subcategorized by technology type and educational functions, yielding 13 subcategories.

Results

Of 39,783 records identified, 66 RCTs (N=4911 participants; 2020-2026) were included. Subcategorized analyses across 7 outcome domains yielded 48 comparisons. Most studies had high risk of bias, mainly due to poor allocation concealment and blinding, and certainty of evidence ranged from low to very low. Large language model (LLM)–based personalized learning aids comprised the largest evidence base and showed positive effects for satisfaction (standardized mean difference [SMD] 0.93, 95% CI 0.40-1.46; 7 studies; 430 participants; I ²=74%), confidence (SMD 0.91, 95% CI 0.54-1.29; 7 studies; 609 participants; I ²=64%), and theoretical knowledge (SMD 0.53, 95% CI 0.13-0.94; 12 studies; 955 participants; I ²=86%), all with very low certainty. Other AI subtypes, including LLM content generators, natural language processing (NLP) chatbots, and non-LLM adaptive learning platforms, showed generally favorable point estimates but substantial heterogeneity and wide CIs, often included no effect. Prediction intervals frequently crossed the null, indicating uncertainty across educational setting. No studies assessed Kirkpatrick levels 3 or 4.

Conclusions

This review synthesized RCT evidence on AI in undergraduate health professions education by technology type and function, incorporating evidence certainty. Despite the large number of included studies, evidence remains insufficient to inform educational practice. Some AI interventions may improve some learning outcomes, but effects are inconsistent and not reliably reproducible. High risk of bias, heterogeneity, imprecision, and absence of higher-level outcomes limit conclusions. AI applications should therefore be used cautiously and on a trial basis.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceHealth OccupationsEducation, Medical, UndergraduateHumansRandomized Controlled Trials as Topic

Author keywords

artificial intelligenceeducational resourcehealth professions educationlarge languge modelmeta-analysisundergraduate

Authors and institutions

  • School of Medicine, Faculty of Health and Medical Sciences, Taylor's University, Subang Jaya, Selangor, Malaysia.
  • Faculty of Health and Medical Sciences, Taylor's University, Subang Jaya, Selangor, Malaysia.
  • Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Level 6, West Wing, John Radcliffe Hospital, Headington, Oxford, England, OX3 9DU, United Kingdom, 44…

ORCID profiles: Nai Ming Lai, Yin Sear Lim, Min Thein Win, Prabal Bhargava, Paraidathathu Thomas, Qi Chwen Ong

Cite

APA

Lai, N. M., Lim, Y. S., Win, M. T., Bhargava, P., Thomas, P., & Ong, Q. C. (2026). The Effectiveness of Artificial Intelligence in Undergraduate Health Professions Education: Systematic Review and Meta-Analysis of Randomized Controlled Trials. JMIR Medical Education, 12, e88933-e88933. https://doi.org/10.2196/88933

Vancouver

Lai NM, Lim YS, Win MT, Bhargava P, Thomas P, Ong QC. The Effectiveness of Artificial Intelligence in Undergraduate Health Professions Education: Systematic Review and Meta-Analysis of Randomized Controlled Trials. JMIR Medical Education. 2026;12:e88933-e88933. doi:10.2196/88933

BibTeX
@article{Lai2026,
  author = {Lai, Nai Ming and Lim, Yin Sear and Win, Min Thein and Bhargava, Prabal and Thomas, Paraidathathu and Ong, Qi Chwen},
  title = {The Effectiveness of Artificial Intelligence in Undergraduate Health Professions Education: Systematic Review and Meta-Analysis of Randomized Controlled Trials},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e88933--e88933},
  doi = {10.2196/88933}
}
Start for free →