Human-AI Assisted Regulatory Documentation Automation in Health Insurance: A Design Science Reference Framework

Abstract

Administrative complexity is a major contributor to healthcare spending in the United States, particularly within health insurance systems that rely on regulatory documentation, benefit configuration, and multi-step compliance workflows. This study proposes the Human-AI Collaborative Regulatory Transformation Framework (HCRTF) for converting unstructured regulatory documentation, redline files, and benefit tables into structured requirement templates in health insurance workflows. HCRTF combines AI-assisted parsing, requirement mapping, traceability, human validation, and feedback loops into one regulated workflow model. Using a design science research approach, the framework is evaluated through workflow decomposition, requirements-to-framework mapping, alternative workflow comparison, synthetic redline-to-requirement demonstration, and risk-control analysis. The study does not claim production deployment, measured time savings, extraction accuracy, or organizational adoption. Instead, it presents a design-stage reference framework for regulated healthcare administrative environments and defines the validation path needed for future empirical testing using real or de-identified regulatory documentation.