Data reuse enables cost-efficient randomized trials of medical AI models

2025-11-12

AI Summary

Traditional randomized controlled trials (RCTs) for medical AI models incur high costs and long durations, impeding rapid iterative validation. To address this, we propose BRIDGE—a data-reuse RCT design that skips redundant intervention assessments in patient subgroups where new and legacy AI models yield concordant predictions. Leveraging real-world data from breast cancer, cardiovascular disease, and sepsis cohorts, BRIDGE integrates risk-cohort overlap analysis, causal inference testing, and rigorous Type I error control to enable adaptive, modular trial execution. This framework represents the first globally reported methodology to systematically reuse observational data in medical AI RCTs. In a breast cancer screening simulation, BRIDGE reduced enrollment by 46.6%, yielding cost savings exceeding $2.8 million while preserving 80% statistical power; prediction concordance among high-risk patients reached 64.8%.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Sampling/Simulation-based Search
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Randomized controlled trials (RCTs) are indispensable for establishing the clinical value of medical artificial-intelligence (AI) tools, yet their high cost and long timelines hinder timely validation as new models emerge rapidly. Here, we propose BRIDGE, a data-reuse RCT design for AI-based risk models. AI risk models support a broad range of interventions, including screening, treatment selection, and clinical alerts. BRIDGE trials recycle participant-level data from completed trials of AI models when legacy and updated models make concordant predictions, thereby reducing the enrollment requirement for subsequent trials. We provide a practical checklist for investigators to assess whether reusing data from previous trials allows for valid causal inference and preserves type I error. Using real-world datasets across breast cancer, cardiovascular disease, and sepsis, we demonstrate concordance between successive AI models, with up to 64.8% overlap in top 5% high-risk cohorts. We then simulate a series of breast cancer screening studies, where our design reduced required enrollment by 46.6%--saving over US$2.8 million--while maintaining 80% power. By transforming trials into adaptive, modular studies, our proposed design makes Level I evidence generation feasible for every model iteration, thereby accelerating cost-effective translation of AI into routine care.

Problem

• Reduces cost and time for clinical AI validation trials
• Reuses data from prior trials when predictions are concordant
• Maintains statistical validity while cutting enrollment requirements

Innovation

• Reuses data from completed AI model trials
• Reduces enrollment needs for subsequent trials
• Maintains statistical power while cutting costs