EUVIMEDScopri EUVIMED
Randomisierte kontrollierte StudieOpen access

Integrating Large Language Models Into Trauma Education for Medical Students: Randomized Controlled Pilot Trial

Joona Gustafsson iD, Erno Lehtonen-Smeds iD, Niklas Pakkasjärvi iD

JMIR Medical Education · 2026-03-17 · 12 · e79134-e79134

DOI: 10.2196/79134 ↗

At a glance

Randomisierte kontrollierte Studie in JMIR Medical Education, published online on 2026-03-17. Written by Joona Gustafsson and 2 co-authors. Institution: Wellbeing Services County of Southwest Finland, University of Turku, PO Box 52, Turku, 20521, Finland. Major MEDLINE topics: Large Language Models, Students, Medical. Cited 4 times so far (Crossref); 23 references. The full text is freely available in PubMed Central.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

The exponential growth of medical knowledge presents a paradox for modern medical education. While access to information is immediate, applying it in a clinically meaningful way remains a challenge. Large language models (LLMs), such as ChatGPT, are widely used for information retrieval, yet their role in dynamic, high-pressure clinical learning remains poorly understood.

Objective

This study aims to evaluate whether unstructured access to an LLM improves decision-making, teamwork, and confidence in trauma education for medical students.

Methods

This randomized controlled pilot study involved 41 final-year medical students participating in a trauma simulation session. Students self-selected into teams of 4 to 6 and were randomized to either an LLM-assisted group (ChatGPT-4o mini) or a control group without LLM access. All teams completed 18 video-based trauma scenarios requiring time-sensitive clinical decisions. Prompting was unrestricted. Confidence and trauma exposure were assessed using pre- or postquestionnaires. Facilitators rated teamwork (1-5), decision accuracy, and response times. Knowledge retention was measured 4 weeks later via an online quiz.

Results

Confidence in trauma management improved in both groups ( P

Subjects

MeSH terms (MEDLINE)

Large Language ModelsStudents, MedicalPilot ProjectsHumansMaleFemaleEducation, Medical, UndergraduateAdult

Author keywords

ChatGPTLLMartificial intelligencedecision-makinglarge language modelsmedical educationmedical studentsteamwork

Authors and institutions

  • Wellbeing Services County of Southwest Finland, University of Turku, PO Box 52, Turku, 20521, Finland.
  • Wellbeing Services County of Ostrobotnia, Vaasa Central Hospital, Vaasa, Finland.

ORCID profiles: Joona Gustafsson, Erno Lehtonen-Smeds, Niklas Pakkasjärvi

Cite

APA

Gustafsson, J., Lehtonen-Smeds, E., & Pakkasjärvi, N. (2026). Integrating Large Language Models Into Trauma Education for Medical Students: Randomized Controlled Pilot Trial. JMIR Medical Education, 12, e79134-e79134. https://doi.org/10.2196/79134

Vancouver

Gustafsson J, Lehtonen-Smeds E, Pakkasjärvi N. Integrating Large Language Models Into Trauma Education for Medical Students: Randomized Controlled Pilot Trial. JMIR Medical Education. 2026;12:e79134-e79134. doi:10.2196/79134

BibTeX
@article{Gustafsson2026,
  author = {Gustafsson, Joona and Lehtonen-Smeds, Erno and Pakkasjärvi, Niklas},
  title = {Integrating Large Language Models Into Trauma Education for Medical Students: Randomized Controlled Pilot Trial},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e79134--e79134},
  doi = {10.2196/79134}
}
Start for free →