Apply GIS and Machine Learning to Examine the Interplay of Factors Affecting COVID-19 Vaccine Rates

Keywords: GIS, Machine Learning, AI, Covid, Public Heath
Session Type: Virtual Paper Abstract
Day: Monday
Session Start / End Time: 2/28/2022 09:40 AM (Eastern Time (US & Canada)) - 2/28/2022 11:00 AM (Eastern Time (US & Canada))
Room: Virtual 46

Abstract

The paper summarizes a recent study that analyzes the interplay of race, poverty, politics and age distribution on COVID-19 vaccination rates in each county across the United States. Traditional regression analysis is built on the assumption of constant impact factors over the entire study area, but in reality, variables have different impacts in different counties. The research applies GIS and machine learning algorithms to quantify contributing factors for county level vaccination hesitancy in the continental US. Joint effects of multiple variables (Race/Ethnicity, Partisanship, Age etc.) are considered simultaneously to capture the unique combination of what factors affect the vaccination rate. By implementing a state-of-the-art Artificial Intelligence Explanations (AIX) algorithm, the study is able to solve the black box problem with machine learning models and provide answers to the “how much” question for each measured impact factor in every county.

By highlighting the variable impact of different factors in each county, this research can be a helpful tool for local health officials and others working to improve vaccination rates in individual communities. An interactive GIS online dashboard is made available so that one can search and select a county in continental US, display a diagram to show the value of each contributing factor, and see by how much each variable impacts the predicted vaccination rate in the selected county (SHAP value). It is apparent that the influence of a variable is not universally the same across different geographies.