Abstract
The fatal drug overdose crisis is a pressing issue that continues to impact communities throughout the United States. Various risk factors, including individual characteristics, social determinants of health, and environmental contextual factors, have been linked to drug overdose deaths. However, integrating diverse information and generating individual predictions of drug overdose deaths on a unified scale remains challenging. The persistence of health disparities in overdose rates emphasizes the need for tailored and potentially personalized prevention strategies. This research aims to address the general research question of improving risk prediction and risk stratification for drug overdose deaths. We developed a machine-learning framework for improved prediction and identify a subgroup of people who were "contextually vulnerable". The first part of the thesis focused on examining the impact of the built environment, social determinants of health measures, and aggregated risk from the built environment at the neighborhood level on drug overdose death locations in Miami-Dade County, Florida using Risk Terrain Modeling (RTM) and regression models. In the second part, individual risk factors and estimated risk from RTM were combined to build a spatial generalized linear mixed model (GLMM) for generating individual predictions of drug overdose deaths. A "shifting subjects" algorithm was proposed, and customized GLMMs were developed using model averaging to improve predictions. The concept of "contextual vulnerability" was introduced to identify the people most affected by changes in the environment, forming a group known as the "contextual vulnerability" group (CVG). The customized GLMM and averaging yield the largest gains in prediction accuracy for individuals in the CVG compared to conventional logistic regression models. Simulation studies were conducted to compare different models, and contextual vulnerability analysis was applied to data on drug overdose deaths in Seattle, WA. This identification of CVG can impact prevention efforts and strategies.