Background: Heart failure (HF) readmission is common post–transcatheter aortic valve replacement (TAVR). Nonetheless, limited data are available regarding its predictors and clinical impact. This study evaluated the incidence, predictors, and impact of HF readmission within 1-year post-TAVR, and assessed the effects of the prescription of HF therapies at discharge on the risk of HF readmission and death. Methods: Patients included in the TAVR registry of a single expert center from 2009 to 2017 were analyzed. Competing-risk and Cox regressions were performed to identify predictors of HF readmission and death. Results: Among 750 patients, 102 (13.6%) were readmitted for HF within 1-year post-TAVR. Overall, 53 patients (7.1%) experienced late readmissions (>30 days post-TAVR), and 17 (2.3%) had multiple readmissions. In ≈30% of readmissions, no trigger could be identified. Predominant causes of readmissions were changes in medication/nonadherence and supraventricular arrhythmia. Independent predictors of HF readmission included diabetes mellitus, chronic lung disease, previous acute HF, grade III or IV aortic regurgitation, and pulmonary hypertension both at discharge from the index hospitalization but not HF therapies. Overall, HF readmission did not significantly impact all-cause mortality (hazard ratio [HR], 1.36 [95% CI, 0.99–1.85]). However, late (HR, 1.90 [95% CI, 1.30–2.78]) and multiple HF readmissions (HR, 2.10 [95% CI,1.17–3.76]) were significantly associated with all-cause mortality. Prescription of renin-angiotensin system inhibitors at discharge was associated with a lower rate of all-cause mortality, especially among patients receiving doses of 25% to <50% (HR, 0.67 [95% CI, 0.48–0.94]) and 75% to 100% (HR, 0.61 [95% CI, 0.37–0.98]) of the optimal daily dose. Conclusions: HF readmission is common within 1-year of TAVR. Late and multiple HF readmissions associate with an increased risk of long-term all-cause mortality. Baseline comorbidities (diabetes, chronic lung disease, previous acute HF) and echocardiographic findings at discharge (grade III or IV aortic regurgitation, pulmonary hypertension) identified patients at high risk of HF readmission.

Aims: To develop an automated deep-learning-based whole heart segmentation of ECG-gated computed tomography data. Methods: After 21 exclusions, CT acquired before transcatheter aortic valve implantation in 71 patients were reviewed and randomly split in a training (n=55 patients), validation (n=8 patients), and a test set (n=8 patients). A fully automatic deep-learning method combining two convolutional neural networks performed segmentation of 10 cardiovascular structures, which was compared with the manually segmented reference by the Dice index. Correlations and agreement between myocardial volumes and mass were assessed. Results:The algorithm demonstrated high accuracy (Dice score=0.920; interquartile range: 0.906-0.925), and a low computing time (13.4 sec, range 11.9-14.9). Correlations and agreement of volumes and mass were satisfactory for most structures. Six of ten structures were well segmented. Conclusion:Deep-learning-based method allowed automated WHS from ECG-gated CT data with a high accuracy. Challenges remain to improve right-sided structures segmentation and achieve daily clinical application.