Social Determinants of Health and Fentanyl Overdose Mortality Across US Counties: An XGBoost and SHAP Analysis Identifying Silent Risk Counties and Treatment Deserts.

BACKGROUND: Fentanyl overdose deaths are still increasing across the U.S. Even though the crisis is growing, we still 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 where overdose data was available, including CDC WONDER (2022) overdose mortality data, CDC Social Vulnerability Index (SVI), CDC PLACES health behavior data, and Area Health Resources Files for healthcare workforce and resources. An XGBoost machine learning model was used to predict overdose mortality risk using Standardized Mortality Ratio (SMR) for each county. Five-fold cross-validation was used to test model accuracy, and SHAP values were used to show which factors increase or decrease risk. RESULTS: The XGBoost model performed better than all other tested models in predicting overdose risk. It matched real rankings fairly well (Spearman ρ = 0.67), explained about 46% of the variation in deaths (R2 = 0.457), had moderate prediction error (MAE = 0.409), and correctly identified about 71% of high-risk counties. The most important predictors were disability rate, hypertension, smoking, and lack of vehicle access. Treatment desert counties had much higher overdose mortality (52.6% higher; SMR 1.786 vs 1.170; p<0.0001). K-means found 143 silent risk counties with high risk but not yet high deaths. Overdose deaths were geographically clustered (Moran's I = 0.5053, p = 0.001) with 75 hotspots and 136 coldspots. Suppressed counties were 58.2% of 2022 CDC WONDER counties, mostly rural (72%) and treatment deserts (65%). CONCLUSIONS: County-level SDOH factors can help predict overdose deaths, especially disability level, access to treatment, and behavioral health burden. Identifying counties with the highest mortality risk can help policymakers and health systems target prevention resources before overdose deaths increase. Expansion of medications for opioid use disorder (MOUD) should focus on treatment desert counties through mobile clinics and telehealth-based buprenorphine services. Silent risk counties may benefit from early investments in naloxone distribution, recovery support programs, and efforts to strengthen the addiction treatment workforce.