Saved in:
Bibliographic Details
Main Authors: Yan, Mengying, Tian, Ziye, Li, Siqi, Liu, Nan, Goldstein, Benjamin A., Liu, Molei, Hong, Chuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.12795
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909962443161600
author Yan, Mengying
Tian, Ziye
Li, Siqi
Liu, Nan
Goldstein, Benjamin A.
Liu, Molei
Hong, Chuan
author_facet Yan, Mengying
Tian, Ziye
Li, Siqi
Liu, Nan
Goldstein, Benjamin A.
Liu, Molei
Hong, Chuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12795
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
Yan, Mengying
Tian, Ziye
Li, Siqi
Liu, Nan
Goldstein, Benjamin A.
Liu, Molei
Hong, Chuan
Machine Learning
Methodology
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.
title TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
topic Machine Learning
Methodology
url https://arxiv.org/abs/2512.12795