Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices
This addresses the problem of rigorous performance assessment for adaptive AI-enabled medical devices, particularly for regulatory science, though it is incremental in refining evaluation methods rather than introducing a new paradigm.
This work tackled the challenge of evaluating adaptive AI models for medical devices by introducing a novel approach with three measurements—learning, potential, and retention—to disentangle performance changes from model adaptations versus dynamic environments. In case studies with simulated population shifts, gradual transitions enabled stable learning and retention, while rapid shifts revealed trade-offs between plasticity and stability.
This work addresses challenges in evaluating adaptive artificial intelligence (AI) models for medical devices, where iterative updates to both models and evaluation datasets complicate performance assessment. We introduce a novel approach with three complementary measurements: learning (model improvement on current data), potential (dataset-driven performance shifts), and retention (knowledge preservation across modification steps), to disentangle performance changes caused by model adaptations versus dynamic environments. Case studies using simulated population shifts demonstrate the approach's utility: gradual transitions enable stable learning and retention, while rapid shifts reveal trade-offs between plasticity and stability. These measurements provide practical insights for regulatory science, enabling rigorous assessment of the safety and effectiveness of adaptive AI systems over sequential modifications.