EUVIMEDAtrasti EUVIMED
Systematische ÜbersichtMetaanalyseStudienprotokollOpen access

Effectiveness of Generative AI–Enabled Teaching for Clinical Reasoning in Health Care Education: Protocol for a Systematic Review and Meta-Analysis

Suzanne Johnston iD, Sonyia McFadden iD, David H Glass iD, Claire McFeeters iD, Joanne Marley iD

JMIR Research Protocols · 2026

DOI: 10.2196/95709 ↗

At a glance

Systematische Übersicht in JMIR Research Protocols, 2026. Written by Suzanne Johnston and 4 co-authors. Institution: Faculty of Life and Health Science, School of Health Science, Ulster University, Belfast, Northern Ireland, United Kingdom. Major MEDLINE topics: Clinical Reasoning, Generative Artificial Intelligence, Teaching, Education, Professional. 59 references. The full text is freely available in PubMed Central.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Clinical reasoning skills are key competencies required by health care professionals. Generative AI (GenAI)–enabled teaching may be able to offer personalized learning; however, its effectiveness compared with traditional teaching methods for developing clinical reasoning capabilities remains underexplored.

Objective

This systematic review and meta-analysis will evaluate, synthesize, and compare the evidence on effectiveness in clinical reasoning capabilities between GenAI-enabled teaching and traditional teaching methods in health care education.

Methods

This review protocol will adhere to the PRISMA-P (Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols) guidelines. The population will include health care professionals. The intervention will be the use of GenAI-enhanced teaching methods, with traditional teaching methods as the comparator. The primary outcome will be objective clinical reasoning performance, with relevant validity for the construct, population, and intended purpose. A database search will be conducted across Embase, MEDLINE, CINAHL, Scopus, and Cochrane CENTRAL, supplemented by Google Scholar, reference list, and citation searches. Study designs will include randomized controlled trials (RCTs), non-RCTs, quasiexperimental studies, and cohort studies with suitable controls. Title and abstract screening and full-text screening will be completed by 2 independent reviewers, with arbitration as required. IBM SPSS will be used to combine and calculate the overall effect. A random-effects model will be deployed, with the Hartung-Knapp-Sidik-Jonkman method used, as appropriate, to calculate the CI around the estimated pooled effect. Study heterogeneity will be assessed using I2 and τ2, and where studies are judged to be too diverse, results will be presented narratively. Prediction intervals will be used, if appropriate, to show how the true effect may vary between similar studies. Risk of bias will be reviewed by 2 independent reviewers, with arbitration, as required, using the Risk of Bias 2 (ROB 2) tool for RCTs and the Risk of Bias in Non-Randomized Studies of Interventions (ROBINS-I) tool for non-RCTs, quasiexperimental studies, and interventional cohort studies. Sensitivity analysis will be used to explore possible sources of heterogeneity. A subgroup analysis may include the type and functionality of GenAI used and/or health care professional background.

Results

The review was funded in September 2025. A trial search was completed on MEDLINE in December 2025, with final database searches completed in February 2026. A total of 4831 studies were retrieved, with 2083 duplicates removed. A further 2558 studies were removed at title and abstract screening, with 190 studies undergoing full-text screening and 42 studies included in the final review. Expected completion date of the final review is autumn or winter 2026.

Conclusions

Health care education is rapidly adopting GenAI-enhanced teaching methods, despite inconclusive evidence on their effectiveness. The findings from this review will offer essential insight into the optimization of GenAI-enhanced teaching methods for clinical reasoning within current and future curriculum design. Trial Registration PROSPERO CRD420261284944; https://www.crd.york.ac.uk/PROSPERO/view/CRD420261284944 International Registered Report Identifier (IRRID) DERR1-10.2196/95709

Subjects

MeSH terms (MEDLINE)

Clinical ReasoningGenerative Artificial IntelligenceTeachingEducation, ProfessionalHealth PersonnelHumansMeta-Analysis as TopicResearch DesignSystematic Reviews as Topic

Author keywords

GenAIclinical reasoningeducationgenerative artificial intelligencehealth care professionalsystematic review

Authors and institutions

  • Faculty of Life and Health Science, School of Health Science, Ulster University, Belfast, Northern Ireland, United Kingdom.
  • School of Computing, Ulster University, Belfast, Northern Ireland, United Kingdom.

ORCID profiles: Suzanne Johnston, Sonyia McFadden, David H Glass, Claire McFeeters, Joanne Marley

Cite

APA

Johnston, S., McFadden, S., Glass, D. H., McFeeters, C., & Marley, J. (2026). Effectiveness of Generative AI–Enabled Teaching for Clinical Reasoning in Health Care Education: Protocol for a Systematic Review and Meta-Analysis. JMIR Research Protocols. https://doi.org/10.2196/95709

Vancouver

Johnston S, McFadden S, Glass DH, McFeeters C, Marley J. Effectiveness of Generative AI–Enabled Teaching for Clinical Reasoning in Health Care Education: Protocol for a Systematic Review and Meta-Analysis. JMIR Research Protocols. 2026. doi:10.2196/95709

BibTeX
@article{Johnston2026,
  author = {Johnston, Suzanne and McFadden, Sonyia and Glass, David H and McFeeters, Claire and Marley, Joanne},
  title = {Effectiveness of Generative AI–Enabled Teaching for Clinical Reasoning in Health Care Education: Protocol for a Systematic Review and Meta-Analysis},
  journal = {JMIR Research Protocols},
  year = {2026},
  doi = {10.2196/95709}
}
Start for free →