🤖 AI Summary
This study investigates the social and structural determinants driving rising fentanyl overdose mortality across U.S. counties, with a focus on identifying “silent-risk” counties—those not yet exhibiting high death rates but possessing significant underlying vulnerability—and “treatment deserts,” characterized by severe shortages of addiction treatment resources. Integrating four major governmental datasets, including CDC records, the authors apply interpretable machine learning (XGBoost with SHAP values) to 2022 county-level data, complemented by five-fold cross-validation, spatial autocorrelation analysis (Moran’s I), K-means clustering, and standardized mortality ratios (SMRs). The model demonstrates strong performance (Spearman ρ = 0.67, R² = 0.457), successfully flagging 143 silent-risk counties. Treatment desert counties exhibit 52.6% higher overdose mortality, while spatial analysis reveals 75 hotspots and 136 coldspots; notably, 72% of suppressed-data counties are rural and 65% are treatment deserts, underscoring the tight linkage between social determinants and spatial clustering patterns.
📝 Abstract
Background: Fentanyl overdose deaths are still increasing across the U.S. We do not fully understand which county-level social and structural conditions lead to higher overdose death rates. Social determinants of health, including disability, treatment access, and behavioral health issues, may help identify vulnerable counties before deaths become severe. No earlier study has used explainable machine learning with SHAP attribution on 2022 CDC WONDER data to study treatment access gaps and silent risk counties.
Methods: We combined data from four government sources for 975 U.S. counties, including CDC WONDER (2022) overdose mortality data, CDC Social Vulnerability Index (SVI), CDC PLACES health behavior data, and Area Health Resources Files. An XGBoost model was used to predict overdose mortality risk using Standardized Mortality Ratio (SMR). Five-fold cross-validation was used to test model accuracy, and SHAP values were used to show which factors increase or decrease risk.
Results: XGBoost outperformed all tested models (Spearman rho=0.67, R2=0.457, MAE=0.409, high-risk recall=71.1%). Top predictors were disability rate, hypertension, smoking, and lack of vehicle access. Treatment desert counties had 52.6% higher overdose mortality (SMR 1.786 vs 1.170; p<0.0001). K-means identified 143 silent risk counties. Overdose deaths were spatially clustered (Moran's I=0.505, p=0.001) with 75 hotspots and 136 coldspots. Suppressed counties were 58.2% of WONDER counties, mostly rural (72%) and treatment deserts (65%).
Conclusions: County-level SDOH factors predict overdose deaths, especially disability, treatment access, and behavioral health burden. MOUD expansion should prioritize treatment desert counties, and silent risk counties need early intervention before mortality worsens.