Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement

ObjectivesThis study sought to develop and compare an array of machine learning methods to predict in-hospital mortality after transcatheter aortic valve replacement (TAVR) in the United States.BackgroundExisting risk prediction tools for in-hospital complications in patients undergoing TAVR have been designed using statistical modeling approaches and have certain limitations.MethodsPatient data were obtained from the National Inpatient Sample database from 2012 to 2015. The data were randomly divided into a development cohort (n = 7,615) and a validation cohort (n = 3,268). Logistic regression, artificial neural network, naive Bayes, and random forest machine learning algorithms were applied to obtain in-hospital mortality prediction models.ResultsA total of 10,883 TAVRs were analyzed in our study. The overall in-hospital mortality was 3.6%. Overall, prediction models’ performance measured by area under the curve were good (>0.80). The best model was obtained by logistic regression (area under the curve: 0.92; 95% confidence interval: 0.89 to 0.95). Most obtained models plateaued after introducing 10 variables. Acute kidney injury was the main predictor of in-hospital mortality ranked with the highest mean importance in all the models. The National Inpatient Sample TAVR score showed the best discrimination among available TAVR prediction scores.ConclusionsMachine learning methods can generate robust models to predict in-hospital mortality for TAVR. The National Inpatient Sample TAVR score should be considered for prognosis and shared decision making in TAVR patients.     

Outcomes of Transcatheter Aortic Valve Replacement in Mixed Aortic Valve Disease

ObjectivesThe aim of this study was to compare outcomes after transcatheter aortic valve replacement (TAVR) in patients with pure aortic stenosis (AS) (i.e., no or trivial associated aortic regurgitation [AR]) with those in patients with AS and mild or more severe AR (i.e., mixed aortic valve disease [MAVD]).BackgroundTAVR is indicated in treating patients with severe AS. Limited data exist regarding the outcomes of TAVR in patients with MAVD.MethodsA total of 1,133 patients who underwent TAVR between January 2014 and December 2017 were included. The primary outcome was all-cause mortality. The comparison was adjusted to account for post-TAVR AR development in both groups. The secondary outcomes included composite endpoints of early safety and clinical efficacy as specified in the Valve Academic Research Consortium-2 criteria. Variables were compared using Mann-Whitney, chi-square, and Fisher exact tests, while Kaplan-Meier analyses were used to compare survival.ResultsA total of 688 patients (61%) had MAVD (median age 83 years , 43% women). Among these, 17% developed mild, 2% moderate, and <1% severe post-TAVR AR. Overall, patients with MAVD had better survival compared with patients with pure AS (p = 0.03). Among patients who developed post-TAVR AR, those in the MAVD group had better survival (p = 0.04). In contrast, in patients who did not develop post-TAVR AR, pre-TAVR AR did not improve survival (p = 0.11).ConclusionsPatients with MAVD who underwent TAVR had better survival compared with patients with pure AS. This is explained by the better survival of patients with MAVD who developed post-TAVR AR, likely due to left ventricular adaptation to AR.     

Oral Anticoagulant Type and Outcomes After Transcatheter Aortic Valve Replacement

ObjectivesThe purpose of the study was to investigate the impact of oral anticoagulation (OAC) type on clinical outcomes 1 year after transcatheter aortic valve replacement (TAVR).BackgroundNon–vitamin K oral anticoagulants (NOACs) are superior to vitamin K antagonists (VKAs) in nonvalvular atrial fibrillation (AF), while their comparative performance among patients in need of OAC undergoing TAVR is underinvestigated.MethodsThe study enrolled 962 consecutive patients who underwent TAVR in 4 tertiary European centers and were discharged on either NOACs (n = 326) or VKAs (n = 636). By using propensity scores for inverse probability of treatment weighting (IPTW), the comparison of treatment groups was adjusted to correct for potential confounding.ResultsMean age and Society of Thoracic Surgeons score of the population were 81.3 ± 6.3 years and 4.5% (interquartile range: 3.0% to 7.3%); 52.5% were women and a balloon-expandable valve was used in 62.7% of cases. The primary outcome of interest, combined incidence of all-cause mortality, myocardial infarction, and any cerebrovascular event at 1-year after TAVR, was 21.2% with NOACs versus 15.0% with VKAs (hazard ratio [HR]: 1.44; 95% confidence interval [CI]: 1.00 to 2.07; p = 0.050, IPTW-adjusted). The 1-year incidence of any Bleeding Academic Research Consortium bleeds and all-cause mortality were comparable between the NOAC and VKA groups, 33.9% versus 34.1% (HR: 0.97; 95% CI: 0.74 to 1.26; p = 0.838, IPTW-adjusted) and 16.5% versus 12.2% (HR: 1.36; 95% CI: 0.90 to 2.06; p = 0.136, IPTW-adjusted), respectively.ConclusionsChronic use of both NOACs and VKAs among patients in need of OAC after TAVR are comparable regarding 1-year bleeding risk. The higher ischemic event rate observed with NOACs needs to be evaluated in large randomized trials.     

Coronary Angiography and Percutaneous Coronary Intervention After Transcatheter Aortic Valve Replacement

Transcatheter aortic valve replacement (TAVR) has revolutionized the management of patients with symptomatic severe aortic stenosis, and indications are expanding towards treating younger patients with lower-risk profiles. Given the progressive nature of coronary artery disease and its high prevalence in those with severe aortic stenosis, coronary angiography and percutaneous coronary intervention will become increasingly necessary in patients after TAVR. There are some data suggesting that there are technical difficulties with coronary re-engagement, particularly in patients with self-expanding valves that, by design, extend above the coronary ostia. The authors review the challenges of coronary angiography and percutaneous coronary intervention post-TAVR and examine the geometric interactions between currently approved transcatheter aortic valves and coronary ostia, while providing a practical guide on how to manage these potentially complex situations.     

Thrombotic Risk and Antithrombotic Strategies After Transcatheter Mitral Valve Replacement

Severe mitral regurgitation (MR) is fairly common in the general population and is associated with significant morbidity and mortality. Although surgical mitral valve (MV) repair and replacement are well established treatment options for MV disease, as much as one-half of patients with severe, symptomatic MR are not referred for surgery due to prohibitive procedural risk. Novel transcatheter alternatives are therefore being developed to provide an alternative treatment for these patients. A growing experience with transcatheter MV replacement (TMVR) strategies is accumulating and promising early results have been reported. However, the risk of transcatheter heart valve (THV) thrombosis seems to be relevant after TMVR, potentially higher than that observed after transcatheter aortic valve replacement, and routine anticoagulant therapy appears to be necessary to mitigate this risk. Hereafter, the authors: 1) review available evidence on thrombotic risk after TMVR (including new dedicated THVs for native MV, valve-in-valve, valve-in-ring, and valve-in-mitral annular calcification); and 2) discuss the antithrombotic treatment strategies after TMVR.     

Trends in Isolated Surgical Aortic Valve Replacement According to Hospital-Based Transcatheter Aortic Valve Replacement Volumes

Objectives

This study sought to evaluate the trends in isolated surgical aortic valve replacement (SAVR) procedures across hospitals with different transcatheter aortic valve replacement (TAVR) volumes among Medicare beneficiaries.