Automated Phenotyping of Mitral Stenosis Using Deep Learning
EchoNet-MS accurately assesses MS severity and etiology using information from multiple echocardiographic views. Its strong performance generalizes robustly to external cohorts and shows potential as an automated clinical decision support tool.
Authors
- Isabel Kim (ORCID: https://orcid.org/0000-0002-4176-2015)
- Andrew P. Ambrosy (ORCID: https://orcid.org/0000-0002-4563-1071)
- Miloš Vukadinovic (ORCID: https://orcid.org/0000-0002-0431-1493)
- Hirotaka Ieki (ORCID: https://orcid.org/0000-0002-6252-6134)
- Yuki Sahashi (ORCID: https://orcid.org/0000-0003-2260-4166)
- Cheng Pj
- David W. Ouyang
- Meenal Rawlani
- Alan S. Go
- Bryan He
Institutions
- Cedars-Sinai Medical Center (US)
- Kaiser Permanente (US)
- University of California, Los Angeles (US)
- Cardiovascular Institute of the South (US)
- Kaiser Permanente San Francisco Medical Center (US)
- Kaiser Permanente Santa Clara Medical Center (US)
- Cedars-Sinai Smidt Heart Institute (US)
- Stanford University (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-03-04
- DOI
- https://doi.org/10.64898/2026.03.03.26347557
- Primary Topic
- Cardiac Valve Diseases and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Alexion Pharmaceuticals
- National Institutes of Health