Towards Equitable Coverage: Harnessing Machine Learning to Identify and Mitigate Insurance Gaps in the U.S. Healthcare System

Abstract

Despite advancements in healthcare access, significant disparities persist in health insurance coverage among vulnerable populations in the United States. These gaps disproportionately affect racial and ethnic minorities, low-income groups, and rural communities, leading to poor health outcomes and increased financial strain (U.S. Department of Health and Human Services, 2022). This research explores how machine learning (ML) can be leveraged to identify, predict, and address these coverage gaps using large-scale datasets such as electronic health records (EHRs), insurance enrollment data, and demographic information. By applying predictive analytics, the study aims to uncover patterns of underinsurance and non-enrollment, enabling proactive outreach and policy interventions (Rajkomar, Dean, & Kohane, 2018). The research evaluates current ML models for their accuracy, ethical implications, and effectiveness in informing targeted outreach strategies. Furthermore, it discusses how health policymakers and insurance providers can use these insights to implement data-driven solutions that promote equitable access to care. This study contributes to the ongoing dialogue on health equity, technology integration, and value-based insurance design in public health policy (Obermeyer, Powers, Vogeli, & Mullainathan, 2019).