Patient, Neighborhood, and Spatial Determinants of Out-of-Hospital Cardiac Arrest Outcomes Throughout the Chain of Survival: A Community-Oriented Multilevel Analysis

Abstract

Objective: Global and national trends of out-of-hospital cardiac arrest (OHCA) have been examined; however, geographic variation and socioeconomic disparities of OHCA outcomes in the community setting are less understood. We developed and tested a replicable, community-oriented assessment strategy aimed to identify spatial variations in OHCA outcomes using socioeconomic, prehospital, and in-hospital factors. Methods: Emergency medical service (EMS) records of adult, non-traumatic OHCA within Alachua County, FL (2012-2017) were retrospectively reviewed and matched to corresponding medical records at the University of Florida (UF). Incidence of cardiac arrest was geocoded to census tracts and connected to U.S. census socioeconomic attribute data. Primary outcomes include survival to emergency department (ED), hospital admission, discharge, and discharge to home. Multilevel mixed-effects logistic regression models were developed to assess sub-county geographic variance, probabilities of survival, and prehospital risk factors. Getis-Ord Gi statistic and Moran's I-test was applied to assess spatial clustering in outcome survival rates. Results: Of the 1562 OHCA cases extracted from EMS records, 1,335 (85.5%) were included with 372 transported to study site. Predicted probability of survival to ED was 57.0% (95CI: 51.3-62.3%). Of transported cases to study site ED, predicted probabilities of survival was to 41.7% (95CI: 36.1-47.6%) for hospital admission, 16.1% (95CI: 10.7-23.5%) for hospital discharge, and 7.1% (95CI: 3.7-13.3%) for home discharge. Census tracts accounted for significant variability in survival to ED (p < 0.001), discharge (p = 0.031), and home discharge outcomes (p = 0.036). There was no significant geographic variation in survival to admission outcome. Neighborhood-level factors significantly improved model fit for survival to ED, discharge, and discharge home outcomes. Multiple modifiable patient- and neighborhood-level variables of interest were identified, including rural-urban differences. Conclusion: We identified important geographic disparities that exist in OHCA outcomes at the community level. By using a replicable schematic, this variation can be explained through community-oriented modifiable socioeconomic and prehospital factors.

Keywords: chain of survival; community-based; neurological outcomes; out-of-hospital cardiac arrest; prehospital; spatial distribution.

Figure 1:

Flowchart of inclusions and exclusions of OHCA incidences responded by Alachua County Fire Rescue from January 2012 through January 2017.

Figure 2:

Distribution of probabilities of survival for each census tract and outcome. Whisker extent is reflected by Tukey definition.

Figure 3:

(A) Getis-Ord Gi* hotspot analysis of average predicted probabilities of survival to ED for each census tract. General G* = 0.691 (p<0.0001). (B) Local Moran’s I spatial outlier analysis of average predicted probabilities of survival to ED for each census tract. Global Moran’s I = 0.0797 (p<0.0001).