articleNature MedicineFeb 23, 2026HYBRID OA

ChatGPT Health performance in a structured test of triage recommendations

Mount Sinai Health System · University of Miami

PubMed
Indexed incrossrefpubmed

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…

Citation impact

17
total citations
FWCI
142.74
Percentile
100%
References
16
Too recent for citation history.

Authors

19

Topics & keywords

Keywords
  • Triage
  • Test (biology)
  • Emergency department
  • Health care
  • Intervention (counseling)
  • Prospective cohort study
  • Emergency medical services
UN Sustainable Development Goals
  • Zero hunger
No related works found for this paper.