Machine learning prediction of progressive subclinical myocardial dysfunction in moderate aortic stenosis.

Background: Moderate severity aortic stenosis (AS) is poorly understood, is associated with subclinical myocardial dysfunction, and can lead to adverse outcome rates that are comparable to severe AS. Factors associated with progressive myocardial dysfunction in moderate AS are not well described. Artificial neural networks (ANNs) can identify patterns, inform clinical risk, and identify features of importance in clinical datasets. Methods: We conducted ANN analyses on longitudinal echocardiographic data collected from 66 individuals with moderate AS who underwent serial echocardiography at our institution. Image phenotyping involved left ventricular global longitudinal strain (GLS) and valve stenosis severity (including energetics) analysis. ANNs were constructed using two multilayer perceptron models. The first model was developed to predict change in GLS from baseline echocardiography alone and the second to predict change in GLS using data from baseline and serial echocardiography. ANNs used a single hidden layer architecture and a 70%:30% training/testing split. Results: Over a median follow-up interval of 1.3 years, change in GLS (≤ or >median change) could be predicted with accuracy rates of 95% in training and 93% in testing using ANN with inputs from baseline echocardiogram data alone (AUC: 0.997). The four most important predictive baseline features (reported as normalized % importance relative to most important feature) were peak gradient (100%), energy loss (93%), GLS (80%), and DI < 0.25 (50%). When a further model was run including inputs from both baseline and serial echocardiography (AUC 0.844), the top four features of importance were change in dimensionless index between index and follow-up studies (100%), baseline peak gradient (79%), baseline energy loss (72%), and baseline GLS (63%). Conclusions: Artificial neural networks can predict progressive subclinical myocardial dysfunction with high accuracy in moderate AS and identify features of importance. Key features associated with classifying progression in subclinical myocardial dysfunction included peak gradient, dimensionless index, GLS, and hydraulic load (energy loss), suggesting that these features should be closely evaluated and monitored in AS.

Plugging Paravalvular Leak in Transcatheter Aortic Valves.

Paravalvular leak can complicate transcatheter aortic valve replacement with important prognostic implications. Correction of defects requires complex planning and execution. Multiple or irregular lesions, calcified annulus, and high sealing skirts on self-expandable devices are especially challenging. Such defects may be approximated using malleable vascular closure devices. (Level of Difficulty: Intermediate.).

Transcatheter aortic valve implantation for pure severe native aortic valve regurgitation.

OBJECTIVES: This study sought to collect data and evaluate the anecdotal use of transcatheter aortic valve implantation (TAVI) in pure native aortic valve regurgitation (NAVR) for patients who were deemed surgically inoperable BACKGROUND: Data and experience with TAVI in the treatment of patients with pure severe NAVR are limited. METHODS: Data on baseline patient characteristics, device and procedure parameters, echocardiographic parameters, and outcomes up to July 2012 were collected retrospectively from 14 centers that have performed TAVI for NAVR. RESULTS: A total of 43 patients underwent TAVI with the CoreValve prosthesis (Medtronic, Minneapolis, Minnesota) at 14 centers (mean age, 75.3 ± 8.8 years; 53% female; mean logistic EuroSCORE (European System for Cardiac Operative Risk Evaluation), 26.9 ± 17.9%; and mean Society of Thoracic Surgeons score, 10.2 ± 5.3%). All patients had severe NAVR on echocardiography without aortic stenosis and 17 patients (39.5%) had the degree of aortic valvular calcification documented on CT or echocardiography. Vascular access was transfemoral (n = 35), subclavian (n = 4), direct aortic (n = 3), and carotid (n = 1). Implantation of a TAVI was performed in 42 patients (97.7%), and 8 patients (18.6%) required a second valve during the index procedure for residual aortic regurgitation. In all patients requiring second valves, valvular calcification was absent (p = 0.014). Post-procedure aortic regurgitation grade I or lower was present in 34 patients (79.1%). At 30 days, the major stroke incidence was 4.7%, and the all-cause mortality rate was 9.3%. At 12 months, the all-cause mortality rate was 21.4% (6 of 28 patients). CONCLUSIONS: This registry analysis demonstrates the feasibility and potential procedure difficulties when using TAVI for severe NAVR. Acceptable results may be achieved in carefully selected patients who are deemed too high risk for conventional surgery, but the possibility of requiring 2 valves and leaving residual aortic regurgitation remain important considerations.

First-in-man assessment of a dedicated guidewire for transcatheter aortic valve implantation.

AIMS: The aim of this study was to evaluate the safety and performance of a specifically designed, dedicated TAVI guidewire. METHODS AND RESULTS: From May 2011 to August 2012, 39 consecutive patients referred for TAVI were prospectively enrolled in a first-in-man, open label, non-randomised feasibility study to evaluate the safety and performance of a specifically designed, dedicated TAVI guidewire in our institution (mean age 80.4±5.1 years, mean logistic EuroSCORE 26.8±11.7%, n=29 CoreValve transfemoral, n=8 CoreValve direct aortic, n=1 Edwards SAPIEN valve direct aortic, n=1 CoreValve subclavian). The primary safety endpoint was reached successfully with the dedicated TAVI guidewire in all 39 cases with no cases of guidewire displacement from the left ventricle during the procedure. In three cases the wire was repositioned to optimise loop position using a pigtail catheter prior to valve implantation. There were no cases of guidewire-related procedural complications. The mean delivery system tracking time using the guidewire was 1.4±0.6 minutes and the mean deployment time for TAVI was 13.8±7.8 minutes. CONCLUSIONS: This represents the first recorded use of a dedicated TAVI guidewire to treat patients with a transcatheter aortic valve. The wire is easy to place, safe to adjust within the ventricle, and the stiffness of the wire facilitates valve tracking through tortuous anatomy. In this study there were no pericardial complications with the use of this dedicated TAVI guidewire.