Abstract

Healthcare inequality remains a persistent global challenge, particularly affecting marginalized and underserved populations. Disparities in access, quality, and health outcomes are exacerbated by socioeconomic, geographic, and systemic barriers. This paper proposes a conceptual model for addressing healthcare inequality through the implementation of Artificial Intelligence (AI)-based Decision Support Systems (DSS). The model integrates advanced data analytics, machine learning algorithms, and real-time health information to support clinical and policy decisions aimed at reducing disparities in healthcare delivery. The conceptual model operates on three core pillars: data integration, predictive analytics, and equitable decision-making. First, the model aggregates data from diverse sources—including electronic health records (EHRs), social determinants of health, and population health databases—to build a comprehensive profile of healthcare needs in various communities. Second, AI-driven predictive analytics are employed to identify at-risk populations, forecast disease trends, and allocate resources efficiently. Finally, the system provides tailored decision support for healthcare providers and policymakers, ensuring that interventions are responsive to the specific needs of disadvantaged groups. A key feature of the model is its emphasis on explainable AI (XAI), which ensures transparency, accountability, and trust in AI-generated recommendations. The model also incorporates fairness-aware algorithms to mitigate bias in data and decision-making, promoting inclusivity and ethical use of technology. Case simulations demonstrate how the system can optimize screening programs, prioritize high-risk patients, and guide equitable health policy formulation. This paper underscores the transformative potential of AI-based DSS in reducing healthcare inequality by enabling data-driven, context-sensitive, and inclusive health interventions. By aligning technology with principles of social justice and health equity, the model offers a strategic pathway for addressing longstanding disparities in healthcare systems. Future research will focus on real-world implementation, stakeholder engagement, and continuous learning to refine the model and expand its applicability across different healthcare settings.