Unraveling COVID-19 Disparities by Assessing the Influence of Demographic and Comorbidity Factors Using Machine Learning Technique: A Case Study of Mecklenburg County, North Carolina

Keywords: COVID-19 health disparities, Demographic and comorbidity influence, Geographic health inequalities, Machine learning in epidemiology, Targeted public health interventions
Abstract Type: Paper Abstract

Abstract

The COVID-19 pandemic has revealed significant disparities in health outcomes across different population groups, which may encompass a range of demographic (social determinants of health) and comorbidity factors. Therefore, it is critical to determine to what extent these variables affect the differences in infection and mortality rates throughout a given region. This research investigates the influence of these factors on varying infection and mortality rates with a focus on high geographical granularity (zip code) in Mecklenburg County, North Carolina. By leveraging machine learning techniques, this research studies the relationships between these factors and geographic disparities to provide valuable insights into the structural vulnerabilities within communities, guiding public health strategies and interventions. Insights from this research will inform public health authorities in understanding how structural inequalities contribute to health disparities during pandemics. This approach will help guide targeted interventions and resource allocation in future public health crises, ensuring that the most vulnerable populations are adequately protected.