FLARE: A Systematic, Uncertainty-Aware Framework for Evidence-Based Adoption of Artificial Intelligence in Healthcare
06:00 · August 26, 2026 · arXiv cs.AI RSS
Artificial intelligence is increasingly being introduced into healthcare workflows, yet most evaluations emphasize model accuracy rather than whether adoption is economically worthwhile in real clinical settings. This study proposes FLARE, a systematic and uncertainty-aware framework for evaluating the financial and operational implications of adopting AI in healthcare. FLARE combines fuzzy logic, time-driven activity-based costing, and return on investment analysis to estimate the cost of clinical service delivery, the cost of AI development and operation, and the economic consequences of workflow integration under uncertainty. The framework was demonstrated through an early health technology assessment case study of AI-assisted large vessel occlusion detection in the CT stroke pathway for acute ischemic stroke. The case study shows how FLARE can quantify conventional pathway cost, AI-related development and recurring costs, and AI-enabled service savings within a unified activity-based model. Under expected assumptions, the analysis identified a break-even threshold of approximately 3,992 patients per year, with positive first-year return on investment at typical annual stroke volumes of about 5,000 patients. The results further show that economic benefit depends not only on algorithmic performance, but also on patient volume, verification time, infrastructure choices, and workflow design. FLARE provides a transparent and practical decision-support framework for early-stage evaluation of AI adoption in healthcare. By making uncertainty, resource use, and implementation trade-offs explicit, it helps clinicians, administrators, and policymakers determine when AI deployment is economically viable and where operational changes may improve value.
Summary
FLARE is a framework that integrates fuzzy logic with time-driven activity-based costing and return-on-investment analysis to assess the financial and operational viability of introducing artificial intelligence into clinical workflows. Rather than stopping at model accuracy, it traces resource consumption across the full lifecycle of an AI solution, from initial development and validation through deployment, integration, and ongoing operation. Fuzzy logic is used to represent uncertainty in activity durations and resource use, allowing the same model to generate expected, optimistic, and pessimistic cost estimates without requiring separate scenarios to be built by hand.
The framework was applied to an early health-technology-assessment case study of AI-assisted detection of large-vessel occlusion in the CT pathway for acute ischemic stroke. Within a single activity-based model, FLARE quantified the cost of the conventional stroke pathway, the one-time and recurring costs of the AI component, and the potential service savings that result from workflow changes. Under the study’s base assumptions, the analysis produced a break-even volume of roughly 3,992 patients per year and indicated a positive first-year return on investment at the typical annual volume of about 5,000 stroke patients. The results also showed that net economic benefit is sensitive to factors beyond algorithmic performance, including annual patient throughput, the time required for radiologist verification, infrastructure choices, and the precise redesign of clinical processes.
By making these trade-offs explicit, FLARE supplies researchers and hospital decision-makers with a transparent, activity-level view of when and under what conditions AI adoption becomes economically justified. The approach therefore extends conventional performance reporting with the granular costing and uncertainty handling needed for early-stage adoption decisions.
Why it matters
Actionable framework for Dutch health-AI teams; aligns with EU emphasis on transparent, value-based AI deployment and Dutch strengths in ethical AI and health informatics research.
