The application of artificial intelligence (AI) to the development of data-driven approaches has the potential to have a major impact on improving childhood vaccination rates in the United States and on decreasing economic and racial disparities in childhood vaccination rates by driving increased access to vaccination services for underserved and vulnerable communities. Childhood vaccination is one of the most effective public health strategies for maintaining community health and wellness (Nabel 2013). Despite the critical role of childhood vaccination in preventing diseases and widespread support for immunization programs, the theoretical goal of universal access is far from realized. The international goal of equitable distribution of vaccination services for all people is described in the Global Vaccine Action Plan (GVAP) for 2021-2030 (“Global Vaccine Action Plan,” 2013), which presents a comprehensive strategy for closing the disparities in immunization. A central component of the GVAP strategy is a call for innovative approaches and models, such as AI-based methods, for increasing access to and compliance with routine vaccination.
This project goal is to increase childhood vaccination rates in underserved communities in the United States by developing an AI tool to help mobile immunization program organizers optimize site selection across communities and assist in the logistical planning of the vaccination resources. The proposed solution will analyze public health data to identify spatio-temporal patterns in the under-vaccinated child population, provide organizers with information-rich visualizations to identify locations where disease severity is the highest (“hotspots”), predict the amount of supplies to meet the need of the area without wasting resources, and information such as time requirements to be most effective when deploying mobile immunizations.