Predictive Analytics for Healthcare Resource Allocation in Underserved Communities

Abstract

Undeserved communities are usually at the receiving ends of resources allocation, particularly healthcare resources, which calls for understanding the key factors that contributes to efficient allocation of resources to the areas. This study investigates the use of predictive analytics for healthcare resource allocation in underserved communities. With the aid of predictive analytics, government can allocate resources effectively, which is sufficient enough to cater for the health needs of the people. The study adopted machine learning techniques, with 26 features included in the model to predict healthcare resource allocation. Data utilized in the study was collected from survey with the participants being residents in underserved communities. The study found that the important features are age, mental health status, visit to the hospital, and healthcare facilities quality, among others. It was recommended that Enhance mental health services and prioritize high-quality healthcare facilities to improve patient outcomes. Increase the availability and accessibility of healthcare providers, especially in areas with frequent hospital visits.