Artificial Intelligence-Enabled ECG Analysis to Predict Incident Heart Failure
ECG2HF is a publicly available 12-lead ECG-based artificial intelligence model that discriminates the risk of future HF with favorable and consistent performance across 3 large health care samples from the northeastern United States. ECG2HF may enable efficient prioritization of high-risk individuals for HF-related preventive measures.
Authors
- Christopher Reeder (ORCID: https://orcid.org/0000-0002-3893-2423)
- Leah Kosyakovsky (ORCID: https://orcid.org/0000-0003-2482-0444)
- Athar Roshandelpoor
- Mitra Chitsazan (ORCID: https://orcid.org/0000-0002-3755-8644)
- Daniel Pipilas (ORCID: https://orcid.org/0000-0001-9577-2801)
- Mahnaz Maddah (ORCID: https://orcid.org/0000-0002-9837-6000)
- Navid A. Nafissi (ORCID: https://orcid.org/0000-0003-0706-9548)
- Shaan Khurshid
- J T Ramo
- Jonathan W. Waks
- Jennifer E. Ho
- Mostafa Amer Al-Alusi
- S Kany
- Valentina D’Souza
- Steven A. Lubitz
- Patrick T. Ellinor
- Emily S. Lau
- Anthony A. Philippakis
- Pulkit Singh
Institutions
- Broad Institute (US)
- Brigham and Women's Hospital (US)
- Beth Israel Deaconess Medical Center (US)
- Harvard University (US)
- Universität Hamburg (DE)
- University of California, San Francisco (US)
- Boston Foundation (US)
- Massachusetts General Hospital (US)
- University Medical Center Hamburg-Eppendorf (DE)
- Institute of Human Genetics (PL)
- Institute for Molecular Medicine Finland (FI)
Publication Details
- Journal
- Circulation Heart Failure
- Published
- 2026-02-23
- DOI
- https://doi.org/10.1161/circheartfailure.125.013927
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00