Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 16, 2025

Prompt design and comparing large language models for healthcare simulation case scenarios

View Full Paper
Ask AI
Bookmark
Share

Authors

SMSara MaazSOSadek ObeidatCMCynthia J. Mosher

Discussion

Loading...

Member takes

Overview

Mixed methods study compares scenario quality in healthcare simulation using ChatGPT, Bing, and Bard, suggesting targeted prompting techniques are essential.

Key Points

  • ChatGPT-4 generated higher quality scenarios than Bing and Bard, achieving mean scores of 71.25 and 85.09 for different prompting methods.
  • Scenarios were evaluated using the Simulation Scenario Evaluation Tool, revealing significant quality differences across models.
  • The mixed methods exploratory design included both quantitative scores and qualitative content analysis of the generated scenarios.
  • Findings indicate that careful prompt design can enhance scenario quality in healthcare simulations.

Cite This Study

Maaz et al. (2025) studied this question.

synapsesocial.com/papers/68c23626b210217d64773ceahttps://doi.org/10.54531/qzgo9534
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Evaluation of large language models as a diagnostic tool for medical learners and clinicians using advanced prompting techniques2025 · 10 citations
  2. 2Large language model-based patient simulation to foster communication skills in healthcare professionals: User-centered development and usability study (Preprint)2025
  3. 3Using Large Language Models to Simulate History Taking: Implications for Symptom-Based Medical Education2025
  4. 4Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs2025
  5. 5An Organized Approach to Using Large Language Models for Medical Information2025