Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices

TL;DR

This paper proposes a new evaluation framework for adaptive AI medical devices, using three measurements to distinguish model improvements from environmental changes, aiding regulatory assessment.

Contribution

It introduces a novel approach with measurements for learning, potential, and retention to evaluate adaptive AI models in medical devices.

Findings

Gradual population shifts enable stable learning and retention.

Rapid shifts expose trade-offs between plasticity and stability.

The approach aids regulatory assessment of adaptive AI systems.

Abstract

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.