Using Machine Learning to Predict Adverse Events in Patients Undergoing Transcatheter Left Atrial Appendage Occlusion
In a nationwide LAAO cohort, XGBoost enhanced discrimination of composite MAE and several individual events. Prediction of rare mortality events was improved, although this was not consistently the case for other rare outcomes.
Authors
- Daniel J. Friedman (ORCID: https://orcid.org/0000-0001-5791-1954)
- Kamil F. Faridi (ORCID: https://orcid.org/0000-0002-9276-9110)
- Jeptha P. Curtis (ORCID: https://orcid.org/0000-0002-6872-0501)
- Bobak J. Mortazavi (ORCID: https://orcid.org/0000-0002-2655-2095)
- Sicong Huang (ORCID: https://orcid.org/0009-0009-3596-5244)
- Rohan Khera
- Harlan M. Krumholz
- James V. Freeman
- Sarah Zimmerman
Institutions
- Duke University (US)
- Yale University (US)
- Yale New Haven Health System (US)
- Texas A&M University (US)
Publication Details
- Journal
- JACC Advances
- Published
- 2026-01-20
- DOI
- https://doi.org/10.1016/j.jacadv.2025.102540
- Primary Topic
- Atrial Fibrillation Management and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00