Foundation model of electronic medical records for adaptive risk estimation
ARES, powered by ETHOS, advances predictive health care AI by delivering dynamic, real-time, personalized risk estimation with patient-specific explainability. Although our results are promising, the clinical impact remains uncertain. Demonstrating ARES's true utility in real-world settings will be the focus of our future work.
Authors
- Jarosław Wąs (ORCID: https://orcid.org/0000-0003-2964-745X)
- David D. B. Bates (ORCID: https://orcid.org/0000-0002-3105-156X)
- Michal K. Grzeszczyk (ORCID: https://orcid.org/0000-0002-5304-1020)
- Nassim Oufattole
- Anthony E. Samir (ORCID: https://orcid.org/0000-0002-7801-8724)
- Yugang Jia (ORCID: https://orcid.org/0009-0008-0628-5461)
- Arkadiusz Sitek (ORCID: https://orcid.org/0000-0002-0677-4002)
- Jonathan W. Cunningham (ORCID: https://orcid.org/0000-0003-4481-7867)
- Paweł Renc (ORCID: https://orcid.org/0000-0002-0487-7454)
- Matthew B. A. McDermott (ORCID: https://orcid.org/0000-0001-6048-9707)
- Deirdre Goode
- Szymon Bieganski
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- Lemuel Shattuck Hospital (US)
- Newton Wellesley Hospital (US)
- Massachusetts General Hospital (US)
- Medical University of Lodz (PL)
- Massachusetts Institute of Technology (US)
- AGH University of Krakow (PL)
- Columbia University (US)
Publication Details
- Journal
- GigaScience
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1093/gigascience/giaf107
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- American Heart Association
- National Institutes of Health
- National Heart, Lung, and Blood Institute