Predicting arrhythmia recurrence post-ablation in atrial fibrillation using explainable machine learning
Our SHAP-based explainable machine learning approach is a proof-of-concept clinical tool to explain arrhythmia recurrence risk in patients who underwent ablation by combining patient-specific clinical profiles and LGE-derived data.
Authors
- NAZEM W. AKOUM (ORCID: https://orcid.org/0000-0002-2001-6806)
- Savannah Bifulco (ORCID: https://orcid.org/0000-0001-6679-6716)
- Matthew J Magoon (ORCID: https://orcid.org/0000-0002-5947-3772)
- Fima Macheret (ORCID: https://orcid.org/0000-0002-1277-8712)
- Issac Kim
- Patrick M. Boyle (ORCID: https://orcid.org/0000-0001-9048-1239)
- Yaacoub Chahine (ORCID: https://orcid.org/0000-0002-2752-220X)
Institutions
- California Institute for Regenerative Medicine (US)
- University of Washington (US)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-10-14
- DOI
- https://doi.org/10.1038/s43856-025-01058-4
- Citations
- 2
- Primary Topic
- Atrial Fibrillation Management and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 2.78
Funders
- Achievement Rewards for College Scientists Foundation
- National Institutes of Health
- National Heart, Lung, and Blood Institute