Integration of Generative AI with Human Expertise in HEOR: A Hybrid Intelligence Framework

Abstract

Introduction: Health economics and outcomes research (HEOR) is pivotal in shaping healthcare policies, optimizing decision-making, and ensuring effective resource allocation. However, current HEOR workflows often struggle to keep pace with the growing complexity of data, constrained resources, and the need for adaptable, real-time analysis. Generative artificial intelligence (Gen-AI) offers a transformative opportunity to address these challenges by augmenting human expertise with advanced computational capabilities. Despite its potential, the integration of Gen-AI into HEOR workflows remains largely unexplored, leaving professionals uncertain about how to effectively leverage its capabilities. This study bridges this gap by introducing a novel hybrid intelligence framework that integrates Gen-AI with human input to enhance critical HEOR tasks, including health economic model conceptualization, evidence synthesis, and patient-reported outcome (PRO) assessment.

Methods: Building on established adoption theories such as the technology acceptance model (TAM) and unified theory of acceptance and use of technology (UTAUT), the framework emphasizes key enablers like perceived usefulness, ease of use, organizational readiness, and social influence to support seamless integration within HEOR workflows. The framework incorporates two implementable approaches: human-in-the-loop (HITL), where AI takes the lead with human validation and refinement, and AI-in-the-loop (AITL), where human professionals remain in control, leveraging AI for verification and enhancements. Advanced tools like retrieval augmented generation (RAG) and Graph RAG are employed alongside techniques such as prompt engineering to ensure outputs are reliable, contextually grounded, and aligned with HEOR needs.

Conclusion: By combining computational efficiency with human insight, this hybrid approach contributes to the evolving integration of AI in HEOR, fostering innovation and driving actionable outcomes. This research sets a foundation for practically integrating Gen-AI into HEOR, offering an actionable pathway to transform workflows, improve healthcare decision-making, and ultimately enhance patient care.

Keywords: AI-in-the-loop; Generative artificial intelligence; Human-in-the-loop; Hybrid intelligence framework; Prompt engineering; Retrieval augmented generation.