Leveraging Artificial Intelligence: Driven Decision Support Systems to Improve Care Coordination and Health Outcomes in Underserved Populations

Abstract

Artificial intelligence (AI)-driven decision support systems (DSS) represent a transformative approach to addressing healthcare disparities in underserved populations. This paper examines the integration of AI technologies into care coordination frameworks to enhance health outcomes among vulnerable communities. Through systematic analysis of recent literature and implementation frameworks, we demonstrate how machine learning algorithms, predictive analytics, and intelligent automation can optimize clinical decision-making, reduce diagnostic errors, and improve resource allocation in resource-constrained settings. Key findings reveal that AI-DSS implementations have shown significant improvements in early disease detection, treatment adherence, and care continuity among underserved populations. However, critical challenges persist, including algorithmic bias, digital divide concerns, data privacy issues, and implementation barriers in low-resource environments. This paper proposes an integrated framework for responsible AI deployment that prioritizes health equity, community engagement, and culturally sensitive design. By synthesizing evidence from contemporary sources, we identify best practices for AI-DSS implementation, policy recommendations for equitable technology access, and strategies for mitigating unintended consequences. The findings suggest that when properly designed and implemented with equity-centered principles, AI-driven decision support systems can serve as powerful tools for reducing health disparities and improving care coordination in underserved populations.