Foundation models for electronic health records: representation dynamics and transferability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910911140200448 |
|---|---|
| author | Burkhart, Michael C. Ramadan, Bashar Liao, Zewei Chhikara, Kaveri Rojas, Juan C. Parker, William F. Beaulieu-Jones, Brett K. |
| author_facet | Burkhart, Michael C. Ramadan, Bashar Liao, Zewei Chhikara, Kaveri Rojas, Juan C. Parker, William F. Beaulieu-Jones, Brett K. |
| contents | Foundation models (FMs) trained on electronic health records (EHRs) have shown strong performance on a range of clinical prediction tasks. However, adapting these models to local health systems remains challenging due to limited data availability and resource constraints. In this study, we investigated what these models learn and evaluated the transferability of an FM trained on MIMIC-IV to an institutional EHR dataset at the University of Chicago Medical Center. We assessed their ability to identify outlier patients and examined representation-space patient trajectories in relation to future clinical outcomes. We also evaluated the performance of supervised fine-tuned classifiers on both source and target datasets. Our findings offer insights into the adaptability of FMs across different healthcare systems, highlight considerations for their effective implementation, and provide an empirical analysis of the underlying factors that contribute to their predictive performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10422 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foundation models for electronic health records: representation dynamics and transferability Burkhart, Michael C. Ramadan, Bashar Liao, Zewei Chhikara, Kaveri Rojas, Juan C. Parker, William F. Beaulieu-Jones, Brett K. Machine Learning Foundation models (FMs) trained on electronic health records (EHRs) have shown strong performance on a range of clinical prediction tasks. However, adapting these models to local health systems remains challenging due to limited data availability and resource constraints. In this study, we investigated what these models learn and evaluated the transferability of an FM trained on MIMIC-IV to an institutional EHR dataset at the University of Chicago Medical Center. We assessed their ability to identify outlier patients and examined representation-space patient trajectories in relation to future clinical outcomes. We also evaluated the performance of supervised fine-tuned classifiers on both source and target datasets. Our findings offer insights into the adaptability of FMs across different healthcare systems, highlight considerations for their effective implementation, and provide an empirical analysis of the underlying factors that contribute to their predictive performance. |
| title | Foundation models for electronic health records: representation dynamics and transferability |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.10422 |