Reasons for death in patients successfully resuscitated from out-of-hospital and in-hospital cardiac arrest

Abstract

Introduction: There is no standard for categorizing reasons for death in those who achieve return of spontaneous circulation (ROSC) after cardiac arrest but die before hospital discharge. Categorization is important for comparing outcomes across studies, assessing benefits of interventions, and developing quality-improvement initiatives. We developed and tested a method for categorizing reasons for death after cardiac arrest in both in-hospital (IHCA) and out-of-hospital (OHCA) arrests.

Methods: Single-center, retrospective, cohort study of patients with ROSC after IHCA or OHCA between 2008 and 2017 who died before hospital discharge. Traumatic arrests and patients with "do-not-resuscitate" orders prior to their arrest were excluded. Two investigators assigned each patient to one of five predefined reasons for death. Interrater reliability was assessed using Fleiss' kappa. For final categorization, discrepancies were resolved by a third investigator.

Results: There were 182 IHCA and 226 OHCA included. There was substantial agreement between raters (kappa of 0.62 and 0.61 for IHCA and OHCA, respectively). Reasons for death for IHCA and OHCA were: neurological withdrawal of care (27% vs 73%), comorbid withdrawal of care (36% vs 4%), refractory hemodynamic shock (25% vs 17%), respiratory failure (1% vs 3%), and sudden cardiac death (11% vs 4%). The differences in reasons for death among the two groups were significant (p-value < 0.001).

Conclusions: Categorizing reasons for death after cardiac arrest with ROSC is feasible using our proposed categories, with substantial inter-rater agreement. Neurologic withdrawal of care is much less common in IHCA than OHCA, which may have implications for further research.

Keywords: Cardiac arrest; Cause of death; Heart arrest; In-hospital cardiac arrest; Mode of death; Out-of-hospital cardiac arrest.

Figure 1.. Categorization and Fleiss' kappa calculations

IHCA, in-hospital cardiac arrest; OHCA, out-of-hospital cardiac arrest; k = Fleiss' kappa *Final reasons for death frequencies are based on the full cohort of 408 patients.

Figure 2.. Kaplan Meier survival curves for reasons for death for IHCA and OHCA

One observation with time = 375 days is censored for neurological withdrawal of care in IHCA. IHCA = In-hospital cardiac arrest; OHCA = Out-of-hospital cardiac arrest.

Figure 3.. Reasons for death following IHCA and OHCA and discrepancy between reviewers.

Detailed distribution of reasons for death between the reviewers of IHCA and OHCA, respectively. 27 IHCA and 21 OHCA from the first training set were not included in the final Kappa calculations and are not included in the 5 × 5 table, but are included in the final frequencies listed at the bottom of the figure. The differences in final reasons for death among the two groups were significant (p-value < 0.001). The 5 × 5 tables should be read as follows: at the end of each row or column is the total number of patients that each reviewer placed in that category. The total number of partients that both reviewers originally agreed on in a given category appears in the boxes descending diagonally from left to right. Additional boxes in that row or column represent the number of patients each reviewer categorized differently from the other reviewer. For example, reviewers 1 and 2 classified 49 and 45 patients as NWC, respectively. There were 40 patients that they both categorized as NWC. Of the 45 patients that Reviewer 2 classified as NWC, Reviewer1 labeled 4 as CWC and 1 as RFS. Of the 49 that Reviewer 1 classified as NWC, Reviewer 2 labelled 9 as CWC. IHCA = In-hospital cardiac arrest; OHCA = Out-of-hospital cardiac arrest; NWC = Neurological withdrawal of care; CWC = Comorbid withdrawal of care; RHS = Refractory hemodynamic shock; RF = Respiratory failure; SCD = Sudden cardiac death.