Artificial Intelligence in Healthcare Real Estate: Mapping Evidence Gaps Across the Asset Lifecycle

Artificial intelligence (AI) is transforming healthcare and the built environment, yet its application to healthcare real estate (HRE) remains fragmented and poorly understood. This study systematically reviews AI applications across the HRE asset lifecycle to identify evidence gaps and evaluate their potential to improve decision-making, operational performance, and sustainable healthcare infrastructure. Following the Joanna Briggs Institute methodology and PRISMA-ScR guidelines, the search identified 2881 records, of which 87 studies met the inclusion criteria. Building on the evidence gaps identified through this mapping, this study develops conceptual contributions, including a lifecycle maturity index, the Algorithm-to-Asset-Value Translation Chain, and the AI-HREDF, that serve as theoretically grounded, testable proposals for future empirical investigation. Each study was classified by lifecycle stage, evidence directness, and evidence strength. Only 14 studies (16%) provided direct evidence linking AI to HRE decisions, while most focused on operations and facility management, leaving major gaps in site selection, planning, construction, and investment. This review identifies three evidence translation gaps that prevent AI advances from becoming measurable improvements in asset performance and financial value. To address these challenges, we propose the AI-Integrated Healthcare Real Estate Decision Framework (AI-HREDF), the Algorithm-to-Asset-Value Translation Chain, and a research agenda for future work. The findings provide a foundation for integrating AI into healthcare infrastructure planning, management, and investment while supporting more resilient, resource-efficient, and sustainable healthcare facilities.