Spatial Modeling of Sociodemographic Risk for COVID-19 Mortality

Abstract

In early 2020, the Coronavirus Disease 19 (COVID-19) rapidly spread across the United States, exhibiting significant geographic variability. While several studies have examined the predictive relationships of differing factors on COVID-19 deaths, few have looked at spatiotemporal variation at refined geographic scales. The objective of this analysis is to examine spatiotemporal variation of COVID-19 deaths in association with socioeconomic, health, demographic, and political factors, using regionalized multivariate regression as well as nationwide county-level geographically weighted random forest (GWRF) models. Analyses were performed on data from three sepearate timeframes: pandemic onset until May 2021, May 2021 through November 2021, and December 2021 until April 2022.Regionalized regression results across three time windows suggest that existing measures of social vulnerability for disaster preparedness (SVI) are associated with a higher degree of mortality from COVID-19. In comparison, GWRF models provide a more robust evaluation of feature importance and prediction, exposing the importance of local features, such as obesity, which is obscured by regional delineation. Overall, GWRF results indicate a more nuanced modeling strategy is useful for capturing the diverse spatial and temporal nature of the COVID-19 pandemic.