Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |