DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System

TL;DR

The paper introduces DT-Transformer, a foundation model trained on extensive multi-hospital EHR data, demonstrating high accuracy in disease trajectory prediction across diverse clinical settings.

Contribution

It presents a novel foundation model trained on large-scale, multi-hospital EHR data, improving disease prediction accuracy in real-world healthcare environments.

Findings

Achieved median AUC of 0.871 for next-event disease prediction.

Validated strong discrimination in both held-out and prospective settings.

Demonstrated the value of health system-scale training for clinical forecasting.

Abstract

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.