Integrated causal-predictive machine learning models for tropical cyclone epidemiology

Abstract

Strategic preparedness has been shown to reduce the adverse health impacts of hurricanes and tropical storms, referred to collectively as tropical cyclones (TCs), but its protective impact could be enhanced by a more comprehensive and rigorous characterization of TC epidemiology. To generate the insights and tools necessary for high-precision TC preparedness, we develop and apply a novel Bayesian machine learning approach that standardizes estimation of historic TC health impacts, discovers common patterns and sources of heterogeneity in those health impacts, and enables identification of communities at highest health risk for future TCs. The model integrates (1) a causal inference component to quantify the immediate health impacts of recent historic TCs at high spatial resolution and (2) a predictive component that captures how TC meteorological features and socioeconomic/demographic characteristics of impacted communities are associated with health impacts. We apply it to a rich data platform containing detailed historic TC exposure information and Medicare claims data. The health outcomes used in our analyses are all-cause mortality and cardiovascular- and respiratory-related hospitalizations. We report a high degree of heterogeneity in the acute health impacts of historic TCs at both the TC level and the community level, with substantial increases in respiratory hospitalizations, on average, during a two-week period surrounding TCs. TC sustained windspeeds are found to be the primary driver of increased mortality and respiratory risk. Our modeling approach has broader utility for predicting the health impacts of many types of extreme climate events.