THE ROLE OF AI-ENABLED INFORMATION SECURITY FRAMEWORKS IN PREVENTING FRAUD IN U.S. HEALTHCARE BILLING SYSTEMS

Abstract

This quantitative study investigated the role of AI-enabled information security frameworks in preventing fraud within U.S. healthcare billing systems, addressing a critical challenge in safeguarding financial integrity and improving payment accuracy. The research aimed to evaluate how the integration of artificial intelligence with established security controls influences technical detection performance, operational efficiency, and financial outcomes in healthcare organizations. A total of 126 peer-reviewed studies and industry reports published over the past decade were systematically reviewed to construct the theoretical foundation, guide the selection of variables, and inform the research design. The study utilized a large multi-payer dataset encompassing over 12 million claims from Medicare, Medicaid, and commercial payers, along with organizational-level measures of security maturity, AI capabilities, and governance quality. Descriptive analysis revealed that organizations implementing mature AI-enabled frameworks exhibited significantly lower fraud incidence, reduced improper payment rates, and shorter detection latency compared to those relying on traditional systems. Correlation analysis indicated strong negative associations between framework maturity and fraud-related outcomes and positive associations between AI capability indices and operational metrics such as workload yield and recovery ratios. Reliability and validity assessments confirmed the robustness of the measurement constructs, while collinearity diagnostics indicated no significant multicollinearity among predictors. Multiple regression analyses demonstrated that framework maturity, logging completeness, access control strength, and AI capability were significant predictors of improved detection performance and financial recovery, explaining a substantial proportion of variance across key outcomes. Subgroup analyses further revealed that the effectiveness of AI-enabled frameworks was moderated by organizational size, payer type, and enforcement intensity. The findings underscored the critical importance of integrating AI with strong governance, comprehensive logging, and secure access controls to build resilient fraud prevention systems.