Khader Ahmed Mohammed

AI-Enabled Intelligent Workflow Design for Continuous Coverage Across Medicaid, CHIP, and ACA Marketplaces

Abstract:

Maintaining continuous health insurance coverage remains a critical challenge within the U.S. healthcare ecosystem, particularly for populations served by Medicaid, the Children’s Health Insurance Program (CHIP), and Affordable Care Act (ACA) Marketplaces. Despite federal requirements for coordinated eligibility and streamlined enrollment, coverage disruptions commonly referred to as churn persist due to administrative complexity, fragmented data exchange, and variability in state-level policy implementation. These gaps contribute to service interruptions, increased administrative costs, and inequitable health outcomes.
This presentation presents the design and evaluation of an AI-enabled intelligent workflow system aimed at improving coverage continuity across Medicaid, CHIP, and ACA programs. The proposed solution integrates artificial intelligence, automation, and business process management (BPM) technologies to orchestrate eligibility determination, renewals, and program transitions in a compliant and interoperable manner. The framework aligns with federal policy mandates and leverages healthcare interoperability standards such as FHIR and Da Vinci Implementation Guides, alongside BPM platforms including Pega and Appian.
At the core of the system are AI-driven predictive models that automate verification of income, household composition, and tax data through secure data exchanges. These models identify beneficiaries at high risk of disenrollment and trigger proactive, targeted interventions by caseworkers. BPM capabilities enable dynamic coordination between automated services and human decision-making, resulting in faster renewals, improved data accuracy, and enhanced communication across state and federal systems.
The evaluation framework focuses on measurable outcomes, including reductions in churn, increased renewal success rates, improved transition efficiency, operational cost savings, and downstream impacts on health outcomes. By combining predictive analytics with standardized process automation, this approach demonstrates how intelligent workflow design can translate policy intent into measurable system performance improvements.
The proposed model offers a practical roadmap for state and federal agencies seeking to modernize eligibility and enrollment systems. It highlights how AI-driven, standards-based, and human-centered workflow design can bridge the gap between policy and implementation, support continuous coverage, and advance equity across U.S. public health insurance programs.

Profile: