Accuracy of a Commercial Large Language Model Protocol: Gage Repeatability and Reproducibility Study

• Published in: Journal of medical Internet research 2024-09, Vol.26 (12)
• Main Authors: Franc, Jeffrey Micheal, Hertelendy, Attila Julius, Cheng, Lenard, Hata, Ryan, Verde, Manuela
• Format: Article
• Language: English
• Subjects: Analysis; Artificial intelligence; Computational linguistics; Disaster medicine; Language processing; Natural language interfaces; Technology application; Triage (Medicine)
• ISSN: 1439-4456
• DOI: 10.2196/55648

The release of ChatGPT (OpenAI) in November 2022 drastically reduced the barrier to using artificial intelligence by allowing a simple web-based text interface to a large language model (LLM). One use case where ChatGPT could be useful is in triaging patients at the site of a disaster using the Simple Triage and Rapid Treatment (START) protocol. However, LLMs experience several common errors including hallucinations (also called confabulations) and prompt dependency. This study addresses the research problem: “Can ChatGPT adequately triage simulated disaster patients using the START protocol?” by measuring three outcomes: repeatability, reproducibility, and accuracy. Nine prompts were developed by 5 disaster medicine physicians. A Python script queried ChatGPT Version 4 for each prompt combined with 391 validated simulated patient vignettes. Ten repetitions of each combination were performed for a total of 35,190 simulated triages. A reference standard START triage code for each simulated case was assigned by 2 disaster medicine specialists (JMF and MV), with a third specialist (LC) added if the first two did not agree. Results were evaluated using a gage repeatability and reproducibility study (gage R and R). Repeatability was defined as variation due to repeated use of the same prompt. Reproducibility was defined as variation due to the use of different prompts on the same patient vignette. Accuracy was defined as agreement with the reference standard. Although 35,102 (99.7%) queries returned a valid START score, there was considerable variability. Repeatability (use of the same prompt repeatedly) was 14% of the overall variation. Reproducibility (use of different prompts) was 4.1% of the overall variation. The accuracy of ChatGPT for START was 63.9% with a 32.9% overtriage rate and a 3.1% undertriage rate. Accuracy varied by prompt with a maximum of 71.8% and a minimum of 46.7%. This study indicates that ChatGPT version 4 is insufficient to triage simulated disaster patients via the START protocol. It demonstrated suboptimal repeatability and reproducibility. The overall accuracy of triage was only 63.9%. Health care professionals are advised to exercise caution while using commercial LLMs for vital medical determinations, given that these tools may commonly produce inaccurate data, colloquially referred to as hallucinations or confabulations. Artificial intelligence–guided tools should undergo rigorous statistical evaluation—using methods such as gage