Journal article · 2026 · Open access

ChatGPT Health performance in a structured test of triage recommendations

Ashwin Ramaswamy, Alvira Tyagi, Hannah Hugo, Joy J. Jiang, Pushkala Jayaraman, Mateen Jangda, Alexis E. Te, Steven A. Kaplan, Joshua M. Lampert, Robert Freeman, Nicholas P. Gavin, Ashutosh Kumar Tewari and 7 more

Nature Medicine, 32(5), 1671–1675 · Published 23 February 2026 · DOI 10.1038/s41591-026-04297-7

Open full textCite this paper

In brief

“ChatGPT Health performance in a structured test of triage recommendations” is a 2026 journal article by Ashwin Ramaswamy and 18 co-authors, published in Nature Medicine. OpenAlex counts 144 citations as of 17 November 2026. It is open access under a CC BY licence: the full text is free to read at Nature Medicine.

Citations
144
Most cited in
2026 (141)
Field-weighted impact
134.25
References
18
Authors
19

Abstract

ChatGPT Health was launched in January 2026 as OpenAI's consumer health tool and has reached millions of users. Here we conducted a structured stress test of triage recommendations using 60 clinician-authored vignettes across 21 clinical domains under 16 factorial conditions, yielding 960 total responses. Performance followed an inverted U-shaped pattern, with the most dangerous failures concentrated at clinical extremes-nonurgent presentations (35%) and emergency conditions (48%). Among gold-standard emergencies, the system undertriaged 52% of cases, directing patients with diabetic ketoacidosis or impending respiratory failure to 24-48 h evaluation rather than the emergency department, while correctly triaging classical emergencies such as stroke and anaphylaxis. When family or friends minimized symptoms, indicating anchoring bias, triage recommendations shifted significantly in edge cases (odds ratio = 11.7, 95% confidence interval = 3.7-36.6), with the majority of shifts toward less urgent care. Crisis-intervention messages activated unpredictably across suicidal ideation presentations, occurring more frequently when patients described no specific method than when they did. Patient race, sex and barriers to care did not show significant effects, although confidence intervals did not exclude clinically meaningful differences. These findings reveal missed high-risk emergencies and inconsistent activation of crisis safeguards, raising safety concerns that warrant prospective validation before consumer-scale deployment of artificial intelligence triage systems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ramaswamy, A., Tyagi, A., Hugo, H., Jiang, J. J., Jayaraman, P., Jangda, M., Te, A. E., Kaplan, S. A., Lampert, J. M., Freeman, R., Gavin, N. P., Tewari, A. K., Sakhuja, A., Naved, B., Charney, A. W., Omar, M., Gorin, M. A., Klang, E., & Nadkarni, G. N. (2026). ChatGPT Health performance in a structured test of triage recommendations. Nature Medicine, 32(5), 1671–1675. https://doi.org/10.1038/s41591-026-04297-7

MLA 9

Ramaswamy, Ashwin, et al. “ChatGPT Health performance in a structured test of triage recommendations.” Nature Medicine, vol. 32, no. 5, 2026, pp. 1671–1675. https://doi.org/10.1038/s41591-026-04297-7.

Chicago

Ramaswamy, Ashwin, Alvira Tyagi, Hannah Hugo, Joy J. Jiang, Pushkala Jayaraman, Mateen Jangda, Alexis E. Te, et al. 2026. “ChatGPT Health performance in a structured test of triage recommendations.” Nature Medicine 32 (5): 1671–1675. https://doi.org/10.1038/s41591-026-04297-7.

Harvard

Ramaswamy, A. et al. (2026) ‘ChatGPT Health performance in a structured test of triage recommendations’, Nature Medicine, 32(5), pp. 1671–1675. doi:10.1038/s41591-026-04297-7.

IEEE

A. Ramaswamy et al., “ChatGPT Health performance in a structured test of triage recommendations,” Nature Medicine, vol. 32, no. 5, pp. 1671–1675, 2026, doi: 10.1038/s41591-026-04297-7.

BibTeX

@article{ramaswamy2026chatgpt,
  title     = {{ChatGPT Health performance in a structured test of triage recommendations}},
  author    = {Ramaswamy, Ashwin and Tyagi, Alvira and Hugo, Hannah and Jiang, Joy J. and Jayaraman, Pushkala and Jangda, Mateen and Te, Alexis E. and Kaplan, Steven A. and Lampert, Joshua M. and Freeman, Robert and Gavin, Nicholas P. and Tewari, Ashutosh Kumar and Sakhuja, Ankit and Naved, Bilal and Charney, Alexander W. and Omar, Mahmud and Gorin, Michael A. and Klang, Eyal and Nadkarni, Girish N.},
  journal   = {Nature Medicine},
  year      = {2026},
  volume    = {32},
  number    = {5},
  pages     = {1671--1675},
  doi       = {10.1038/s41591-026-04297-7},
  url       = {https://doi.org/10.1038/s41591-026-04297-7}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202411
202522
2026141141

Its field-weighted citation impact is 134.25: it has been cited 134.25 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • AI triage
  • emergency department triage
  • clinical decision support
  • anchoring effect
  • undertriage
  • diabetic ketoacidosis
  • respiratory failure
  • stroke

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Ramaswamy, A., Tyagi, A., Hugo, H., Jiang, J. J., Jayaraman, P., Jangda, M., Te, A. E., Kaplan, S. A., Lampert, J. M., Freeman, R., Gavin, N. P., Tewari, A. K., Sakhuja, A., Naved, B., Charney, A. W., Omar, M., Gorin, M. A., Klang, E., & Nadkarni, G. N. (2026). ChatGPT Health performance in a structured test of triage recommendations. Nature Medicine, 32(5), 1671–1675. https://doi.org/10.1038/s41591-026-04297-7

How many times has this paper been cited?

144 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Nature Medicine: sign in and open the full text from this page.

Who wrote this paper?

Ashwin Ramaswamy, Alvira Tyagi, Hannah Hugo, Joy J. Jiang, Pushkala Jayaraman, Mateen Jangda, Alexis E. Te, Steven A. Kaplan, Joshua M. Lampert, Robert Freeman, Nicholas P. Gavin, Ashutosh Kumar Tewari and 7 more.

What is the DOI of this paper?

10.1038/s41591-026-04297-7, permanently at https://doi.org/10.1038/s41591-026-04297-7. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.