Background: Standard cardiovascular risk models generally have limited performance and cannot predict rare outcomes. Machine learning may overcome these limitations. Objectives: This study sought to determine how predictive performance varies for standard and machine learning methods in the National Cardiovascular Data Registry Left Atrial Appendage Occlusion (LAAO) Registry. Methods: Logistic regression (LR), least absolute shrinkage and selection operator (LASSO), and eXtreme Gradient Boosting (XGBoost) were used to predict combined in-hospital major adverse events (MAEs) and individual events in patients undergoing transcatheter LAAO. Randomly selected 70% development and 30% validation cohorts were used for model creation and assessment with 16 variables from the previous LAAO risk model and an expanded set of 51 variables. Results: The study included data from 81,703 LAAO procedures. The composite MAE rate was 1.39% (individual event rate 0.02% to 1.13%). XGBoost performed best for MAE using original model variables (validation AUC 0.648 [95% CI: 0.626-0.670] vs LR 0.630 [95% CI: 0.608-0.642] and LASSO 0.638 [95% CI: 0.626-0.670]). With expanded variables, XGBoost (AUC 0.653 [95% CI: 0.635-0.671]) performed marginally better than LASSO (AUC 0.644 [95% CI: 0.628-0.660]) for MAE, while LR performed poorly (AUC 0.515 [95% CI: 0.501-0.529]). 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. Conclusions: 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.

Left atrial appendage occlusion (LAAO) has become an important therapeutic target for stroke prevention in patients with nonvalvular atrial fibrillation. Over the past 2 decades, several advancements in LAAO devices (percutaneous and surgical) have been made for stroke prevention and arrhythmia therapy. However, there are several unanswered questions regarding optimal patient selection, the preferred LAAO approach and device, the management of periprocedural and postprocedural complications, including pericardial effusion, device-related thrombus, and device leaks. This review focuses on fundamental foundational concepts in various aspects of the left atrial appendage and management strategies as they relate to current clinical needs.

BACKGROUND:Atrial fibrillation (AF) is common among patients with obstructive hypertrophic cardiomyopathy (oHCM), although the impact of AF on health care resource use and costs is not well defined. METHODS:We performed a retrospective analysis of claims data from 2016 to 2021 and used International Classification of Diseases, Tenth Revision (ICD-10) codes to identify adult patients with symptomatic oHCM and classify their status with respect to AF as follows: (1) prevalent AF, (2) incident AF, and (3) no AF. Health care resource use and costs for each cohort were analyzed and expressed as per person per year (PPPY). RESULTS:Of 22 216 patients with symptomatic oHCM, 6677 had prevalent AF (30.1%), 2879 had incident AF (13.0%), and 12 660 were without AF (57.0%). Patients with incident AF incurred mean total health care costs that were similar to those with prevalent AF but substantially greater than those without AF (mean, $66 619 [95% CI, $59 702-$74 336] versus $63 937 [95% CI, $59 803-$68 356] versus $46 686 [95% CI, $43 901-$49 648] per person per year, P<0.0001). After adjusting for age, sex, major comorbidities, and septal reduction therapy, mean total health care costs remained greater in the groups with incident and prevalent AF than the group without AF, with trends toward even greater relative costs in the group with incident AF. Similar trends were present in adjusted costs related to hospitalizations, surgeries, and urgent care. CONCLUSIONS:The diagnosis of AF in the setting of symptomatic oHCM not only has important implications for patient management but also substantial economic impacts, as it is associated with significantly greater health care costs and resource use relative to patients with symptomatic oHCM and no AF.