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

• URL: http://arxiv.org/abs/2605.08230v1
• Date: Wed, 06 May 2026 20:28:33 GMT
• Title: Social Determinants of Health and Fentanyl Overdose Mortality Across US Counties: An XGBoost and SHAP Analysis Identifying Silent Risk Counties and Treatment Deserts
• Abstract summary: Social determinants of health, including disability, treatment access, and behavioral health issues, may help identify vulnerable counties.<n>We combined data from four government sources for 975 U.S. counties.<n>Treatment desert counties had 143 higher overdose mortality.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Comparative Evaluation of Explainable Machine Learning Versus Linear Regression for Predicting County-Level Lung Cancer Mortality Rate in the United States [0.1957338076370071]
  Lung cancer (LC) is a leading cause of cancer-related mortality in the United States.<n>This study applied three models to predict county-level LC mortality rates across the United States.
  arXiv  Detail & Related papers  (2025-12-10T23:33:12Z)
• MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis [40.3028468133626]
  Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology.<n>textbfMeCaMIL, a causality-aware MIL framework, explicitly models demographic confounders through structured causal graphs.<n>MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes.
  arXiv  Detail & Related papers  (2025-11-14T06:47:21Z)
• Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis [50.46938276133494]
  Interstitial lung disease (ILD) is a leading cause of morbidity and mortality in systemic sclerosis (SSc)<n>This study introduces a novel, large-scale longitudinal chest CT analysis framework that utilizes radiomics and deep learning to predict mortality.
  arXiv  Detail & Related papers  (2025-09-27T23:46:57Z)
• Quantifying Clinician Bias and its Effects on Schizophrenia Diagnosis in the Emergency Department of the Mount Sinai Health System [35.98898736539817]
  In the United States, schizophrenia (SCZ) carries a race and sex disparity that may be explained by clinician bias.<n>We investigated the effects of clinician bias on SCZ diagnosis while controlling for known risk factors and patient sociodemographic information.
  arXiv  Detail & Related papers  (2025-09-02T13:53:17Z)
• Enhanced Mortality Prediction In Patients With Subarachnoid Haemorrhage Using A Deep Learning Model Based On The Initial CT Scan [34.86503928854081]
  Convolutional neural networks (CNN) are capable of generating highly accurate predictions from imaging data. Our objective was to predict mortality in Subarachnoid hemorrhage patients by processing the initial CT scan on a CNN based algorithm.
  arXiv  Detail & Related papers  (2023-08-25T13:33:56Z)
• Predicting Cardiovascular Disease Risk using Photoplethysmography and Deep Learning [9.273651488255036]
  Cardiovascular diseases (CVDs) are responsible for a large proportion of premature deaths in low- and middle-income countries. Here we investigated the potential to use photoplethysmography (), a sensing technology available on most smartphones. We developed a deep learning PPG-based CVD risk score (DLS) to predict the probability of having major adverse cardiovascular events.
  arXiv  Detail & Related papers  (2023-05-09T17:46:43Z)
• Factors affecting the COVID-19 risk in the US counties: an innovative approach by combining unsupervised and supervised learning [0.0]
  factors that could affect the risk of COVID-19 infection and mortality were analyzed in county level. Results showed that mean temperature, percent of people below poverty, percent of adults with obesity, air pressure, population density, wind speed, longitude, and percent of uninsured people were the most significant attributes.
  arXiv  Detail & Related papers  (2021-06-24T04:29:00Z)
• Where you live matters: a spatial analysis of COVID-19 mortality [0.0]
  The COVID-19 pandemic has caused 2 million fatalities in Mexico. The anomaly in the case/mortality ratio with Mexico is explored by spatial analysis and whether mortality varies locally according to local factors. To address this, hexagonal cartogram maps (hexbin) used to spatially map COVID-19 mortality and visualise association with patient-level data on demographics and pre-existing health conditions.
  arXiv  Detail & Related papers  (2021-01-11T21:25:13Z)
• Point Process Modeling of Drug Overdoses with Heterogeneous and Missing Data [0.0]
  Opioid overdose rates have increased in the United States over the past decade and reflect a major public health crisis. We present a spatial-temporal point process model for drug overdose clustering. We find that drug and opioid overdose deaths exhibit significant excitation, with branching ratio ranging from.72 to.98.
  arXiv  Detail & Related papers  (2020-10-12T23:47:55Z)
• Real-time Prediction of COVID-19 related Mortality using Electronic Health Records [30.892335739985526]
  COVID-19 Early Warning System (CovEWS) is a clinical risk scoring system for assessing COVID-19 related mortality risk. CovEWS provides continuous real-time risk scores for individual patients with clinically meaningful predictive performance up to 192 hours (8 days) in advance.
  arXiv  Detail & Related papers  (2020-08-31T08:07:27Z)
• Computational Support for Substance Use Disorder Prevention, Detection, Treatment, and Recovery [62.9980747784214]
  Substance Use Disorders involve the misuse of alcohol, opioids, marijuana, and methamphetamine. 1 in 12 U.S. adults have or have had a substance use disorder. National Institute on Drug Abuse estimates that SUDs cost the U.S. $520 billion annually.
  arXiv  Detail & Related papers  (2020-06-23T18:30:20Z)
• Effectiveness and Compliance to Social Distancing During COVID-19 [72.94965109944707]
  We use a detailed set of mobility data to evaluate the impact that stay-at-home orders had on the spread of COVID-19 in the US. We show that there is a unidirectional Granger causality, from the median percentage of time spent daily at home to the daily number of COVID-19-related deaths with a lag of 2 weeks.
  arXiv  Detail & Related papers  (2020-06-23T03:36:19Z)
• Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT [48.785596536318884]
  The proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States.
  arXiv  Detail & Related papers  (2020-04-02T21:49:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.