Triage Performance Across Large Language Models, ChatGPT, and Untrained Doctors in Emergency Medicine: Comparative Study
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Background: Large language models (LLMs) have demonstrated impressive performances in various medical domains, prompting an exploration of their potential utility within the high-demand setting of emergency department (ED) triage. This study evaluated the triage proficiency of different LLMs and ChatGPT, an LLM-based chatbot, compared to professionally trained ED staff and untrained personnel. We further explored whether LLM responses could guide untrained staff in effective triage. Objective: This study aimed to assess the efficacy of LLMs and the associated product ChatGPT in ED triage compared to personnel of varying training status and to investigate if the models’ responses can enhance the triage proficiency of untrained personnel. Methods: A total of 124 anonymized case vignettes were triaged by untrained doctors; different versions of currently available LLMs; ChatGPT; and professionally trained raters, who subsequently agreed on a consensus set according to the Manchester Triage System (MTS). The prototypical vignettes were adapted from cases at a tertiary ED in Germany. The main outcome was the level of agreement between raters’ MTS level assignments, measured via quadratic-weighted Cohen κ. The extent of over- and undertriage was also determined. Notably, instances of ChatGPT were prompted using zero-shot approaches without extensive background information on the MTS. The tested LLMs included raw GPT-4, Llama 3 70B, Gemini 1.5, and Mixtral 8x7b. Results: GPT-4–based ChatGPT and untrained doctors showed substantial agreement with the consensus triage of professional raters (κ=mean 0.67, SD 0.037 and κ=mean 0.68, SD 0.056, respectively), significantly exceeding the performance of GPT-3.5–based ChatGPT (κ=mean 0.54, SD 0.024; P<.001). When untrained doctors used this LLM for second-opinion triage, there was a slight but statistically insignificant performance increase (κ=mean 0.70, SD 0.047; P=.97). Other tested LLMs performed similar to or worse than GPT-4–based ChatGPT or showed odd triaging behavior with the used parameters. LLMs and ChatGPT models tended toward overtriage, whereas untrained doctors undertriaged. Conclusions: While LLMs and the LLM-based product ChatGPT do not yet match professionally trained raters, their best models’ triage proficiency equals that of untrained ED doctors. In its current form, LLMs or ChatGPT thus did not demonstrate gold-standard performance in ED triage and, in the setting of this study, failed to significantly improve untrained doctors’ triage when used as decision support. Notable performance enhancements in newer LLM versions over older ones hint at future improvements with further technological development and specific training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
seaborn: statistical data visualization
Waskom, M. (2021) · Journal of Open Source Software · doi:10.21105/joss.03021 · Cited by 7,310 · cited 1×
“For designing graphical representations, we used the matplotlib (version 3.1.3) [29] and seaborn (version 0.12.0) [30] packages.”
InfluentialKung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 1×
“…many medical professionals, it is remarkable that systems such as ChatGPT without any specialized training have been able to pass US medical exams [5,6]; provide answers to questions from a web-based platform that are preferred over doctors’ replies [7]; and in most cases, offer appropriate…”
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Ayers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613 · cited 1×
“…as ChatGPT without any specialized training have been able to pass US medical exams [5,6]; provide answers to questions from a web-based platform that are preferred over doctors’ replies [7]; and in most cases, offer appropriate recommendations to questions on cardiovascular disease prevention [8].”
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00819-6 · Cited by 1,099
The imperative for regulatory oversight of large language models (or generative AI) in healthcare
Meskó, B., & Topol, E. J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00873-0 · Cited by 1,047
ChatGPT: the future of discharge summaries?
Patel, S. B., & Lam, K. (2023) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00021-3 · Cited by 728 · cited 1×
“The capabilities of text generation and summarization introduce numerous controversial research and clinical use cases such as creating discharge summaries [9] or crafting scientific abstracts [10].”
Ambient artificial intelligence scribes to alleviate the burden of clinical documentation.
Tierney, A. A., Gayre, G., Hoberman, B., Mattern, B., Ballesca, M., Kipnis, P., Liu, V., & Lee, K. (2024) · NEJM Catalyst · doi:10.1056/cat.23.0404 · Cited by 400 · cited 2×
“All these use cases carry the promise of improving quality and efficiency by offering second opinions [13] and reducing the documentation burden on strained health care professionals [12].”
Towards Accurate Differential Diagnosis with Large Language Models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.00164 · Cited by 311
Towards accurate differential diagnosis with large language models
McDuff, D., Schaekermann, M., Tu, T., Palepu, A., Wang, A., Garrison, J., Singhal, K., Sharma, Y., Azizi, S., Kulkarni, K., et al. (2025) · Nature · doi:10.1038/s41586-025-08869-4 · Cited by 311 · cited 2×
“All these use cases carry the promise of improving quality and efficiency by offering second opinions [13] and reducing the documentation burden on strained health care professionals [12].”
Artificial intelligence chatbot performance in triage of ophthalmic conditions
Lyons, R. J., Arepalli, S. R., Fromal, O., Choi, J. D., & Jain, N. (2024) · Canadian Journal of Ophthalmology · doi:10.1016/j.jcjo.2023.07.016 · Cited by 101 · cited 2×
“Similar on-par performance between GPT-4–based ChatGPT and ophthalmology trainees has been reported in another medical context, further underlining this finding [24].”
Boonstra, A., & Laven, M. (2022) · BMC Health Services Research · doi:10.1186/s12913-022-08070-7 · Cited by 87 · cited 1×
“However, recent results from algorithmic solutions demonstrate their potential in enhancing clinical decision processes and optimizing resource utilization [34].”
Cited by
Luo, X., Tham, Y. C., Giuffrè, M., Ranisch, R., Daher, M., Lam, K., Eriksen, A. V., Hsu, C.-W., Ozaki, A., Moraes, F. Y. D., et al. (2025) · BMJ Evidence-Based Medicine · doi:10.1136/bmjebm-2025-113825 · Cited by 97
Liu, S., Wright, A. P., McCoy, A. B., Huang, S. S., Steitz, B., & Wright, A. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf059 · Cited by 44
Sorich, M. J., Mangoni, A. A., Bacchi, S., Menz, B. D., & Hopkins, A. M. (2024) · Journal of Medical Internet Research · doi:10.2196/67409 · Cited by 26
Metadata
- Authors
- Masanneck, L., Schmidt, L., Seifert, A., Kölsche, T., Huntemann, N., Jansen, R., Mehsin, M., Bernhard, M., Meuth, S. G., Böhm, L., & Pawlitzki, M.
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2024-06-14
- Volume
- 26
- Pages
- e53297
- ISSN
- 1438-8871 (ISSN-L)
- OpenAlex
- W4399667220
- Cited by
- 124
- References
- 12
- FWCI
- 9.94
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.