Arrhythmias & electrophysiology
Using Machine Learning to Predict Adverse Events in Patients Undergoing Transcatheter Left Atrial Appendage Occlusion
Authors' conclusion
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.
Study context
- Population
- Patients undergoing transcatheter left atrial appendage occlusion (LAAO)
- Participants
- 81,703 LAAO proceduresEvents: 1.39%
- Predictors
- Logistic regression (LR), least absolute shrinkage and selection operator (LASSO) and XGBoost models with 16 variables from the previous LAAO risk model and an expanded set of 51 variables
- Predicted outcome
- Combined in-hospital major adverse events (MAEs) and individual events
Methodological detailsNational Cardiovascular Data Registry LAAO Registry, 70% development and 30% validation cohorts
- National Cardiovascular Data Registry LAAO Registry
- 70% development and 30% validation cohorts
Model performance
As reported in the abstract
AUC
XGBoost, original variablesvalidation
0.648(95% CI: 0.626-0.670)
LR, original variablesvalidation
0.630(95% CI: 0.608-0.642)
LASSO, original variablesvalidation
0.638(95% CI: 0.626-0.670)
XGBoost, expanded variables
0.653(95% CI: 0.635-0.671)
LASSO, expanded variables
0.644(95% CI: 0.628-0.660)
LR, expanded variables
0.515(95% CI: 0.501-0.529)
Further findings
Individual events
- Performance using all methods declined for infrequent events
- XGBoost generally outperformed other methods for individual events, particularly with expanded variables, though not necessarily for rare events
- Mortality prediction using XGBoost was incrementally better
Individual event rate
- Individual event rate
- 0.02% to 1.13%
Original publication
Using Machine Learning to Predict Adverse Events in Patients Undergoing Transcatheter Left Atrial Appendage Occlusion. JACC Adv. Published 20 January 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →