Correlation of vital sign centiles with in-hospital outcomes among adults encountered by emergency medical services

Abstract

Background: Vital signs are a critical component of the prehospital assessment. Prior work has suggested that vital signs may vary in their distribution by age. These differences in vital signs may have implications on in-hospital outcomes or be utilized within prediction models. We sought to (1) identify empirically derived (unadjusted) cut points for vital signs for adult patients encountered by emergency medical services (EMS), (2) evaluate differences in age-adjusted cutoffs for vital signs in this population, and (3) evaluate unadjusted and age-adjusted vital signs measures with in-hospital outcomes.

Methods: We used two multiagency EMS data sets to derive (National EMS Information System from 2018) and assess agreement (ESO, Inc., from 2019 to 2021) of vital signs cutoffs among adult EMS encounters. We compared unadjusted to age-adjusted cutoffs. For encounters within the ESO sample that had in-hospital data, we compared the association of unadjusted cutoffs and age-adjusted cutoffs with hospitalization and in-hospital mortality.

Results: We included 13,405,858 and 18,682,684 encounters in the derivation and validation samples, respectively. Both extremely high and extremely low vital signs demonstrated stepwise increases in admission and in-hospital mortality. When evaluating age-based centiles with vital signs, a gradual decline was noted at all extremes of heart rate (HR) with increasing age. Extremes of systolic blood pressure at upper and lower margins were greater in older age groups relative to younger age groups. Respiratory rate (RR) cut points were similar for all adult age groups. Compared to unadjusted vital signs, age-adjusted vital signs had slightly increased accuracy for HR and RR but lower accuracy for SBP for outcomes of mortality and hospitalization.

Conclusions: We describe cut points for vital signs for adults in the out-of-hospital setting that are associated with both mortality and hospitalization. While we found age-based differences in vital signs cutoffs, this adjustment only slightly improved model performance for in-hospital outcomes.