Ethnoracial disparities in emergency department triage decisions persist, despite efforts to standardize protocols. Here, we analyze 1.35 million encounters at four U.S. emergency departments that all use the Emergency Severity Index triage protocol. We independently score visits as emergent (level 2) or urgent (level 3) by applying the criteria computationally and compare to nurse assignments. We show that, matched on clinical presentation and hospital context, Hispanic patients are less often triaged emergent than Non-Hispanic White (NHW) patients at every site (odds ratios (ORs): 0.75 [95% CI 0.72–0.78] to 0.90 [0.86–0.94]), and Non-Hispanic Black patients at two (0.73 [0.71–0.74], 0.89 [0.86–0.92]). Disparities increase where the algorithm scores patients lower-risk (Hispanic-NHW ORs: 0.73 [0.69–0.77] to 0.88 [0.83–0.94]), and attenuate where it scores them higher-risk (0.83 [0.79–0.89] to 0.95 [0.90–1.00]), suggesting a disparate “benefit-of-the-doubt” pattern of clinical discretion. Standardized decision support may reduce these disparities, and we estimate a worst-case increase on ED lengths of stay to be 1.0 -3.8% across sites. Analysis of 1.35 million emergency department visits found that racial and ethnic disparities in triage scores were concentrated in lower-risk visits, where assessment relies more on clinical judgment.
No takes yet. Share an insight, caveat, or question.
Milà et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: