Multi-Scale Demographic Analysis of Covid-19 Booster Vaccination Rates Using Graph Neural Networks

This study presents a multi-scale demographic analysis of COVID-19 booster vaccination rates using Graph Neural Networks (GNNs). Data from Nueces County, Texas, was analyzed at two levels of geographic granularity: block groups and census tracts. The block group model demonstrated superior accuracy in predicting vaccination rates compared to the census tract model, emphasizing the importance of fine-grained data for public health planning. To evaluate the combination of models at different scales, aggregation methods such as weighted sum, majority voting, and stacking were employed. While these methods provided insights, they did not outperform the block group model. The study highlights the potential of GNNs for improving public health interventions through targeted vaccination strategies. Limitations include the dataset's focus on data up to February 2022 and the absence of more granular demographic factors. Future work will incorporate temporal factors and explore smaller geographic scales, such as block-level data, for enhanced precision.