TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
This addresses the problem of maintaining predictive accuracy for clinicians and patients when clinical environments evolve, though it is incremental as it builds on existing transfer learning methods for a specific domain.
The paper tackled performance drift in clinical decision support tools due to temporal population shifts, such as during COVID-19, by proposing TRACER, a transfer learning framework that adapts models in real-time without full retraining, improving discrimination and calibration in real-world applications.
Clinical decision support tools built on electronic health records often experience performance drift due to temporal population shifts, particularly when changes in the clinical environment initially affect only a subset of patients, resulting in a transition to mixed populations. Such case-mix changes commonly arise following system-level operational updates or the emergence of new diseases, such as COVID-19. We propose TRACER (Transfer Learning-based Real-time Adaptation for Clinical Evolving Risk), a framework that identifies encounter-level transition membership and adapts predictive models using transfer learning without full retraining. In simulation studies, TRACER outperformed static models trained on historical or contemporary data. In a real-world application predicting hospital admission following emergency department visits across the COVID-19 transition, TRACER improved both discrimination and calibration. TRACER provides a scalable approach for maintaining robust predictive performance under evolving and heterogeneous clinical conditions.