Accuracy of a Commercial Large Language Model (ChatGPT) toPerform Disaster Triage of Simulated Patients Using the SimpleTriage and Rapid Treatment (START) Protocol:Gage Repeatabilityand Reproducibility Study Article

Franc, Jeffrey Micheal, Med, Dip Sport, Hertelendy, Attila Julius et al. (2024). Accuracy of a Commercial Large Language Model (ChatGPT) toPerform Disaster Triage of Simulated Patients Using the SimpleTriage and Rapid Treatment (START) Protocol:Gage Repeatabilityand Reproducibility Study . JOURNAL OF MEDICAL INTERNET RESEARCH, 26 10.2196/55648

Open Access International Collaboration

cited authors

  • Franc, Jeffrey Micheal; Med, Dip Sport; Hertelendy, Attila Julius; Cheng, Lenard; Hata, Ryan; Verde, Manuela

sustainable development goals

authors

publication date

  • September 30, 2024

published in

keywords

  • ChatGPT
  • GPT
  • Health Care Sciences & Services
  • LLM
  • LLMs
  • Life Sciences & Biomedicine
  • Medical Informatics
  • NLP
  • Science & Technology
  • accuracy;accurate;
  • artificial intelligence
  • disaster
  • disaster medicine
  • disasters
  • emergencies
  • emergency
  • language model
  • language models
  • large language models
  • natural language processing
  • repeatability
  • reproducibility
  • reproducible; repeatable
  • triage

Digital Object Identifier (DOI)

publisher

  • JMIR PUBLICATIONS, INC

volume

  • 26