Abstract
Introduction Social disparities in out-of-hospital cardiac arrest (OHCA) outcomes are preventable, costly, and unjust. We sought to perform the first large artificial intelligence- (AI-) guided statistical and geographic information system (GIS) analysis of a multiyear and multisite cohort for OHCA outcomes (incidence and poor neurological disposition). Method We conducted a retrospective cohort analysis of a prospectively collected multicenter dataset of adult patients who sequentially presented to Houston metro area hospitals from 01/01/07-01/01/16. Then AI-based machine learning (backward propagation neural network) augmented multivariable regression and GIS heat mapping were performed. Results Of 3,952 OHCA patients across 38 hospitals, African Americans were the most likely to suffer OHCA despite representing a significantly lower percentage of the population (42.6 versus 22.8%; p < 0.001). Compared to Caucasians, they were significantly more likely to have poor neurological disposition (OR 2.21, 95%CI 1.25–3.92; p=0.006) and be discharged to a facility instead of home (OR 1.39, 95%CI 1.05–1.85; p=0.023). Compared to the safety net hospital system primarily serving poorer African Americans, the university hospital serving primarily higher income commercially and Medicare insured patients had the lowest odds of death (OR 0.45, p < 0.001). Each additional $10,000 above median household income was associated with a decrease in the total number of cardiac arrests per zip code by 2.86 (95%CI -4.26- -1.46; p < 0.001); zip codes with a median income above $54,600 versus the federal poverty level had 14.62 fewer arrests (p < 0.001). GIS maps showed convergence of the greater density of poor neurologic outcome cases and greater density of poorer African American residences. Conclusion This large, longitudinal AI-guided analysis statistically and geographically identifies racial and socioeconomic disparities in OHCA outcomes in a way that may allow targeted medical and public health coordinated efforts to improve clinical, cost, and social equity outcomes.
Highlights
Social disparities in out-of-hospital cardiac arrest (OHCA) outcomes are preventable, costly, and unjust
For each additional 10 African Americans suffering cardiac arrest in a zip code, its total number of poor neurologic outcomes increased by an average of 8.78 (p < 0.001)
Geospatial maps showed a clockwise band from north to east to south of higher cardiac arrest, associated mortality, lower income, and more poor neurologic outcome cases overlapping with where more African Americans with lower incomes lived (Figures 1–4). e association of race and poor neurological outcome was confirmed by locally weighted regression (Figure 5)
Summary
Out-of-hospital cardiac arrest (OHCA) remains a serious medical and public health challenge in the United States. Its most basic framework is the well-accepted traditional statistical method of multivariable regression that allows significant and independent associations between predictors and outcomes to be assessed in a way that is familiar to most biomedical researchers It integrates the well-accepted traditional statistical and causal inference technique of propensity score adjustment to postulate not just association but potential causality in nonrandomized data by reducing such biases as confounding and selection biases which threaten study validity (while noting that randomized controlled trials are the gold standard for assessing real causality, but successful ones historically are launched only after sufficient nonrandomized and causal inference studies better clarify the hypothesis to be tested). Geospatial analysis was conducted with neural network multivariable regression of arrest outcomes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
