Predictive Modeling of Vaccination Uptake in US Counties: A Machine Learning-Based Approach

Area of Science:

• Public Health
• Epidemiology
• Health Informatics

Background:

• The COVID-19 pandemic has disproportionately affected the United States, with significant regional disparities in case incidence.
• Sociodemographic factors contribute to unequal disease spread across US counties, highlighting the need for predictive modeling.
• Stagnant COVID-19 vaccination rates in the US necessitate identifying key factors influencing vaccine uptake.

Purpose of the Study:

• To investigate the association between sociodemographic characteristics and COVID-19 vaccine uptake at the county level in the United States.
• To identify key sociodemographic predictors influencing vaccination rates across diverse US counties.

Main Methods:

• Utilized sociodemographic data from sources including the US Centers for Disease Control and Prevention and the US Census Bureau.
• Employed machine learning analysis, specifically the XGBoost algorithm, to model COVID-19 vaccine uptake.

Main Results:

• The predictive model achieved 62% accuracy in forecasting COVID-19 vaccination uptake across US counties.
• Key predictors identified include location, education level, ethnicity, income, and household internet access.
• A choropleth map was generated to visualize regional vaccination rate disparities, aiding public health planning.

Conclusions:

• Sociodemographic factors are significant predictors of COVID-19 vaccine uptake at the county level in the United States.
• Leveraging these insights can empower policymakers and public health officials to develop effective strategies for improving vaccination rates.
• Data-driven insights are essential for addressing health disparities and enhancing public health interventions during pandemics.