EUVIMEDObjevte EUVIMED
Open access

ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study

Riley Scherr iD, Faris F Halaseh iD, Aidin Spina iD, Saman Andalib iD, Ronald Rivera iD

JMIR Medical Education · 2023-11-10 · 9 · e49877

DOI: 10.2196/49877 ↗

At a glance

Journal article in JMIR Medical Education, published online on 2023-11-10. Written by Riley Scherr and 4 co-authors. Institution: Irvine School of Medicine, University of California, Irvine, CA, United States. Cited 122 times so far (Crossref); 21 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

The transition to clinical clerkships can be difficult for medical students, as it requires the synthesis and application of preclinical information into diagnostic and therapeutic decisions. ChatGPT—a generative language model with many medical applications due to its creativity, memory, and accuracy—can help students in this transition.

Objective

This paper models ChatGPT 3.5’s ability to perform interactive clinical simulations and shows this tool’s benefit to medical education.

Methods

Simulation starting prompts were refined using ChatGPT 3.5 in Google Chrome. Starting prompts were selected based on assessment format, stepwise progression of simulation events and questions, free-response question type, responsiveness to user inputs, postscenario feedback, and medical accuracy of the feedback. The chosen scenarios were advanced cardiac life support and medical intensive care (for sepsis and pneumonia).

Results

Two starting prompts were chosen. Prompt 1 was developed through 3 test simulations and used successfully in 2 simulations. Prompt 2 was developed through 10 additional test simulations and used successfully in 1 simulation.

Conclusions

ChatGPT is capable of creating simulations for early clinical education. These simulations let students practice novel parts of the clinical curriculum, such as forming independent diagnostic and therapeutic impressions over an entire patient encounter. Furthermore, the simulations can adapt to user inputs in a way that replicates real life more accurately than premade question bank clinical vignettes. Finally, ChatGPT can create potentially unlimited free simulations with specific feedback, which increases access for medical students with lower socioeconomic status and underresourced medical schools. However, no tool is perfect, and ChatGPT is no exception; there are concerns about simulation accuracy and replicability that need to be addressed to further optimize ChatGPT’s performance as an educational resource.

Subjects

Author keywords

AIAI in medical educationChatGPTartificial intelligenceclinical educationcurriculumgenerativemedical educationmedical school simulationspreclinical curriculumsimulationsimulations

Authors and institutions

  • Irvine School of Medicine, University of California, Irvine, CA, United States.
  • Department of Emergency Medicine, Irvine School of Medicine, University of California, Irvine, CA, United States.

ORCID profiles: Riley Scherr, Faris F Halaseh, Aidin Spina, Saman Andalib, Ronald Rivera

Cite

APA

Scherr, R., Halaseh, F. F., Spina, A., Andalib, S., & Rivera, R. (2023). ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study. JMIR Medical Education, 9, e49877. https://doi.org/10.2196/49877

Vancouver

Scherr R, Halaseh FF, Spina A, Andalib S, Rivera R. ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study. JMIR Medical Education. 2023;9:e49877. doi:10.2196/49877

BibTeX
@article{Scherr2023,
  author = {Scherr, Riley and Halaseh, Faris F and Spina, Aidin and Andalib, Saman and Rivera, Ronald},
  title = {ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study},
  journal = {JMIR Medical Education},
  year = {2023},
  volume = {9},
  pages = {e49877},
  doi = {10.2196/49877}
}
Start for free →