Identifying COVID-19 Vaccine Deserts Using Machine Learning and Geospatial Analyses to Target Community-Engaged Testing for Vulnerable Rural Populations to Prevent Localized Outbreaks

Background: The aims of this study were to identify and target vaccine desert communities in West Virginia using overall vaccination rates and changes in vaccine uptake. Targeted vaccine deserts would then have tailored testing event services developed by building upon their perceptions of what is important and meeting the needs of individual communities. Materials/Methods: The study used a mixed methods approach to identify high risk vaccine desert communities, tailor communications and media to those identified communities, deploy the community orientated testing strategy within communities identified, and evaluate the impact and acceptability of the testing strategy. Outcome/Impact: This study provided innovative strategies for engaging with communities and using statistical methods to target testing to vulnerable communities with low vaccine uptake, at highest risk for persistent outbreaks, and transmission of more variant forms of the COVID-19 virus. The study leveraged existing and new partnerships with local and state agencies for implementation of a community engaged testing delivery model within vaccine deserts.