Scott, CG

Abstract Funding Acknowledgements Type of funding sources: None. Background Tricuspid regurgitation (TR) is a prevalent valvular lesion with three broad morphologic subtypes: primary due to intrinsic pathology of the valve or subvalvular apparatus; secondary due to pulmonary hypertension; and isolated TR associated with chronic atrial fibrillation. The complex pathophysiological, clinical and echocardiographic features between these subtypes require further investigation. Purpose We aimed to identify the different phenotypes of TR using cluster analysis, and determine differences (if present) in clinical outcomes associated with these phenotypes. Methods We included 13611 patients with ≥ moderate TR, either primary or secondary, in the final analyses. The demographic, clinical and echocardiographic data of these patients were evaluated using Ward’s minimum variance cluster analysis including a total of 38 variables. Survival analysis for all-cause mortality was performed using the Kaplan-Meier method, and groups were compared using the log-rank test. Results The mean age of patients was 72.5 ± 13.4 years, 7590 (56%) were females. The clustering identified 5 distinct phenotypes. Cluster 1 represented "low-risk TR" with lesser severity likely related to chronic atrial fibrillation. This cluster had less severe TR, normal sized right ventricle and fewer comorbidities. Clusters 2-5 represented "higher severity TR", "TR associated with lung disease", "TR associated with coronary artery disease and ischemic cardiomyopathy" and "TR associated with chronic kidney disease" respectively (Figure 1). Cluster 1 had the best overall survival, followed by clusters 2, 3 and 4, and lastly cluster 5, with the worst outcome (Figure 2). Conclusions Cluster analysis identifies 5 phenotypically distinct novel subgroups of TR with differences in all-cause mortality. This phenotype-based classification improves our understanding of interaction of different co-morbidities with this complex valve lesion and can inform clinical decision making. Abstract Figure. Cluster Dendrogram Abstract Figure. Kaplan-Meier survival curves

Abstract Funding Acknowledgements Type of funding sources: None. Background Aortic regurgitation (AR) is a common valvular lesion associated with left ventricular (LV) enlargement and dysfunction and increased risk of death with onset of symptoms, significant LV enlargement, or systolic dysfunction. The current guidelines are based on symptoms, LV size and LV function to evaluate the candidacy for surgery in patients with severe AR. Purpose We propose a machine-learning (ML) based algorithm to identify patients at risk for death from AR independent of aortic valve replacement (AVR) surgery (patients were censored at AVR event unless the operation occurred within 100 days of the first visit, in which case baseline AVR is included as a predictor). Methods The model was trained with 5-fold cross-validation on a dataset of 1035 patients. Model performance is reported on an independent dataset of 207 patients. Optimal predictive performance was observed with a Conditional Random Survival Forest model. A subset of 19 / 41 variables were selected for inclusion in the final model. Variable selection was performed with 10-fold cross validation using Random Survival Forest model; variables that were on an average selected by less than 6/10 splits were excluded. Results The mean age of patients was 60 ± 17 years and 198 (18%) were females. The variables included in the models were age, end-diastolic volume, end systolic dimension, body surface area, ejection fraction, NYHA class, body mass index, diastolic blood pressure, bicuspid valve, regurgitant volume, filling pressure, mid ascending aorta diameter, mitral tissue early relaxation velocity, pulmonary artery systolic pressure, and comorbidities, and the relative variable importances averaged across five splits of cross validation in each repeat were evaluated (Figure). The predictive AUC for predicting survival of the best-performing model was 0.84 at 1 year, 0.86 at 2 years, and 0.87 overall, respectively. Conclusion Using commonly observed echo parameters and patient characteristics we successfully trained a ML model to predict survival in patients with severe AR. This technique could identify high-risk patients who would benefit from early intervention, thereby improving patient outcomes. Abstract Figure.