Abstract 336: Data-driven Classification of Arrest Location for Emergency Department Cardiac Arrests

Abstract

Introduction: Out-of-hospital cardiac arrest (OHCA), in-hospital cardiac arrest (IHCA), and emergency department (ED) cardiac arrests differ in epidemiology, etiology, and outcomes. Resuscitation research is inconsistent in how ED arrests are classified. We used unsupervised learning to compare ED arrests to non-ED OHCA and to non-ED IHCA. Hypothesis: Clinical features of ED cardiac arrest patients who achieve return of spontaneous circulation (ROSC) are more similar to IHCA than to OHCA. Methods: We performed a retrospective study including all patients resuscitated from cardiac arrest who were treated at a single academic medical center from January 2010 to December 2019. We abstracted clinical information from our prospective registry, including the details of arrest location (ED arrests, OHCA, or IHCA); age; sex; initial arrest rhythm; number of doses of epinephrine, bicarbonate and shocks given during the arrest; duration of arrest; most advanced airway placed intra-arrest; number of rearrests; early post-arrest illness severity (Pittsburgh Cardiac Arrest Category: PCAC); and survival to hospital discharge. We used unsupervised learning (K-prototypes) to identify clusters within the OHCA and IHCA cohorts. We determined the number of subgroups using Scree plots. Finally, we assigned individual ED arrest patients the nearest OHCA or IHCA cluster based on the shortest Gower distance from that patient to the nearest cluster center. Results: We included 2,723 patients: 1,709 (63%) OHCA, 642 (23%) IHCA, and 372 (14%) ED arrests. We identified 3 clusters in the OHCA cohort, and 4 clusters in the IHCA cohort. Of the total ED arrest cases, 292 (78%) most closely resembled an IHCA cluster and 80 (22%) most closely resembled an OHCA cluster. The large majority (64%) of ED arrests that were closest to an IHCA cluster survived to hospital discharge; 50% of this subset were awake post-arrest (PCAC I), and 16% were deeply comatose (PCAC IV). In contrast, only 13% of ED arrests that were closest to an OHCA cluster survived to hospital discharge; 65% of this subset were deeply comatose (PCAC IV) and only 5% were awake post arrest (PCAC I). Conclusion: Among cardiac arrest patients with ROSC, the large majority of ED arrests resemble IHCA more than OHCA.