Saved in:
Bibliographic Details
Main Authors: Zhu, Yunying, Weckstein, Andrew R, Lin, Kueiyu Joshua, Yang, Jie
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.14227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911683958538240
author Zhu, Yunying
Weckstein, Andrew R
Lin, Kueiyu Joshua
Yang, Jie
author_facet Zhu, Yunying
Weckstein, Andrew R
Lin, Kueiyu Joshua
Yang, Jie
contents Accurate disease trajectory prediction is critical for early intervention, resource allocation, and improving long-term outcomes. While electronic health records (EHRs) provide a rich longitudinal view of patient health in clinical environments, models trained on curated research cohorts may not reflect routine deployment settings, and those trained on single-hospital datasets capture only fragments of each patient's trajectory. This highlights the importance of leveraging large, multi-hospital health systems for training and validation to better reflect real-world clinical complexity. In this work, we develop DT-Transformer, a foundation model trained on 57.1M structured EHR entries over 1.7M patients from Mass General Brigham (MGB), spanning 11 hospitals and a broad network of outpatient clinics. DT-Transformer achieves strong discrimination in both held-out and prospective validation settings. Next-event prediction achieves a median age- and sex-stratified AUC of 0.871 across 896 disease categories, with all categories exceeding AUC 0.5. These results support health system-scale training as a path toward foundation models suited to real-world clinical forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14227
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System
Zhu, Yunying
Weckstein, Andrew R
Lin, Kueiyu Joshua
Yang, Jie
Machine Learning
Computation and Language
Accurate disease trajectory prediction is critical for early intervention, resource allocation, and improving long-term outcomes. While electronic health records (EHRs) provide a rich longitudinal view of patient health in clinical environments, models trained on curated research cohorts may not reflect routine deployment settings, and those trained on single-hospital datasets capture only fragments of each patient's trajectory. This highlights the importance of leveraging large, multi-hospital health systems for training and validation to better reflect real-world clinical complexity. In this work, we develop DT-Transformer, a foundation model trained on 57.1M structured EHR entries over 1.7M patients from Mass General Brigham (MGB), spanning 11 hospitals and a broad network of outpatient clinics. DT-Transformer achieves strong discrimination in both held-out and prospective validation settings. Next-event prediction achieves a median age- and sex-stratified AUC of 0.871 across 896 disease categories, with all categories exceeding AUC 0.5. These results support health system-scale training as a path toward foundation models suited to real-world clinical forecasting.
title DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2605.14227