TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk

TL;DR

TRACER is a transfer learning framework designed to adapt clinical predictive models in real-time, effectively handling population shifts and maintaining performance during evolving healthcare scenarios like COVID-19.

Contribution

It introduces a novel transfer learning-based method for real-time model adaptation without full retraining, addressing performance drift in clinical decision tools.

Findings

Outperformed static models in simulation studies.

Improved discrimination and calibration in COVID-19 hospital admission prediction.

Scalable approach for evolving clinical environments.

Abstract

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.