Scholarlink

<p>The opioid crisis remains a significant public health challenge in the USA, with opioid-related overdose deaths continuing to rise in recent years. Understanding the patterns and key determinants of these deaths is crucial for improving prevention, intervention, and resource allocation strategies. This study analyzes temporal trends and county-level distributions of opioid overdose fatalities and applies machine learning models to predict county-level OOD rates using publicly available data from 2016 to 2023. Findings reveal that approximately 30% of US counties experienced an increase in opioid-related overdose deaths during this period, with 15 counties reporting spikes exceeding 50%. An eXtreme Gradient Boosting (XGBoost) regressor-based machine learning model was applied using 18 distinct features across 3142 counties, achieving an <i>R</i><sup>2</sup> value of 0.93. SHapley Additive exPlanations (SHAP) were employed to assess the contribution of each feature to the model’s predictions. The most influential features included “County Population,” “Average Mentally Unhealthy Days,” “Median Age,” “Percentage of the Population Uninsured,” “Violent Crime Rates,” and “Percentage of the Black Population.” These key features were then used to develop a Risk Index for identifying counties at high risk of opioid-related overdose deaths. This machine learning–driven study offers a valuable framework for targeted opioid-related overdose death prevention and intervention efforts, and optimized resource allocation to combat the ongoing opioid epidemic in the USA.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Opioid Overdose Death Prediction Using Machine Learning and Risk Factor Analysis Using SHAP Values for US Counties

  • 期刊论文

  • 发表日期：

    2025年10月15日

查看全文
  • Vishnu Kumar,
  • Robin Butler

摘要

The opioid crisis remains a significant public health challenge in the USA, with opioid-related overdose deaths continuing to rise in recent years. Understanding the patterns and key determinants of these deaths is crucial for improving prevention, intervention, and resource allocation strategies. This study analyzes temporal trends and county-level distributions of opioid overdose fatalities and applies machine learning models to predict county-level OOD rates using publicly available data from 2016 to 2023. Findings reveal that approximately 30% of US counties experienced an increase in opioid-related overdose deaths during this period, with 15 counties reporting spikes exceeding 50%. An eXtreme Gradient Boosting (XGBoost) regressor-based machine learning model was applied using 18 distinct features across 3142 counties, achieving an R2 value of 0.93. SHapley Additive exPlanations (SHAP) were employed to assess the contribution of each feature to the model’s predictions. The most influential features included “County Population,” “Average Mentally Unhealthy Days,” “Median Age,” “Percentage of the Population Uninsured,” “Violent Crime Rates,” and “Percentage of the Black Population.” These key features were then used to develop a Risk Index for identifying counties at high risk of opioid-related overdose deaths. This machine learning–driven study offers a valuable framework for targeted opioid-related overdose death prevention and intervention efforts, and optimized resource allocation to combat the ongoing opioid epidemic in the USA.