Search

Transcatheter aortic valve implantation (TAVI) is the routine treatment worldwide for aortic valve stenosis in low-to high-risk patients. Assessing patient risk is essential to identify the most suitable candidates that could benefit from the procedure. Despite the broad use of statistical predictors in patient selection, current machine learning predictors have only been validated on retrospective data collected in single centers. Further, external validation is needed to assess the improvement in accuracy, which is offered by machine learning and deep learning techniques. In this study, we propose a finetuning approach for deep learning models by performing an inter-center cross-validation and finetuning technique, in order to improve the cross-validation accuracy results. We aimed to overcome data exchange and policy-related issues of two medical centers with a dedicated protocol, exploiting the exchange of deep learning models, data processing and validation steps which does not require any patient data sharing. The finetuning is based on the other center's data for further training of the initial model. After finetuning the model, we obtain an average AUC improvement of 13% and 7% with respect to the initial models. This research demonstrates that the predicting capabilities of deep learning models can be extended to and cross-validated with other centers, independent of limitations in data-sharing policies. Moreover, the study shows that finetuning can be exploited to considerably improve the accuracy of the prediction models.

Objectives: The aim of this study was to assess acute regurgitation following transcatheter aortic valve replacement, comparing different implanted transcatheter heart valves. Background: Regurgitation following transcatheter aortic valve replacement influences all-cause mortality. Thus far, no quantitative comparison of regurgitation among multiple commercially available transcatheter heart valves has been performed. Methods: Aortograms from a multicenter cohort of consecutive 3,976 transcatheter aortic valve replacements were evaluated in this pooled analysis. A total of 2,258 (58.3%) were considered analyzable by an independent academic core laboratory using video densitometry. Results of quantitative regurgitation are shown as percentages. The valves evaluated were the ACURATE (n = 115), Centera (n = 11), CoreValve (n = 532), Direct Flow Medical (n = 21), Evolut PRO (n = 95), Evolut R (n = 295), Inovare (n = 4), Lotus (n = 546), Lotus Edge (n = 3), SAPIEN XT (n = 239), and SAPIEN 3 (n = 397). For the main analysis, only valves with more than 50 procedures (7 types) were used. Results: The Lotus valve had the lowest mean regurgitation (3.5 ± 4.4%), followed by Evolut PRO (7.4 ± 6.5%), SAPIEN 3 (7.6 ± 7.1%), Evolut R (7.9 ± 7.4%), SAPIEN XT (8.8 ± 7.5%), ACURATE (9.6 ± 9.2%) and CoreValve (13.7 ± 10.7%) (analysis of variance p < 0.001). The only valves that statistically differed from all their counterparts were Lotus (as the lowest regurgitation) and CoreValve (the highest). The proportion of patients presenting with moderate or severe regurgitation followed the same ranking order: Lotus (2.2%), Evolut PRO (5.3%), SAPIEN 3 (8.3%), Evolut R (8.8%), SAPIEN XT (10.9%), ACURATE (11.3%), and CoreValve (30.1%) (chi-square p < 0.001). Conclusions: In this pooled analysis stemming from daily clinical practice, the Lotus valve was shown to have the best immediate sealing. This analysis reflects the objective evaluation of regurgitation by an academic core laboratory (nonsponsored) in a real-world cohort of patients using a quantitative technique.

Background In a three-month report from the CGA-TAVI registry, we found the Multidimensional Prognostic Index (MPI) and Short Physical Performance Battery (SPPB) to be of value for predicting short-term outcomes in elderly patients undergoing transcatheter aortic valve implantation (TAVI). In the present analysis, we examined the association of these tools with outcomes up to one year post-TAVI. Methods CGA-TAVI is an international, observational registry of geriatric patients undergoing TAVI. Patients were assessed using the MPI and SPPB. Efficacy of baseline values and any postoperative change for predicting outcome were established using logistic regression. Kap-lan-Meier analysis was carried out for each comprehensive geriatric assessment tool, with survival stratified by risk category. Results One year after TAVI, 14.1% of patients deceased, while 17.4% met the combined endpoint of death and/or non-fatal stroke, and 37.7% the combined endpoint of death and/or hospitalisation and/or non-fatal stroke. A high-risk MPI score was associated with an increased risk of all-cause mortality (aOR = 36.13, 95% CI: 2.77-470.78, P = 0.006) and death and/or non-fatal stroke (aOR = 10.10, 95% CI: 1.48-68.75, P = 0.018). No significant associations were found between a high-risk SPPB score and mortality or two main combined endpoints. In contrast to a worsening SPPB, an aggravating MPI score at three months post-TAVI was associated with an increased risk of death and/or non-fatal stoke at one year (aOR = 95.16, 95% CI: 3.41-2657.01). Conclusions The MPI showed value for predicting the likelihood of death and a combination of death and/or non-fatal stroke by one year after TAVI in elderly patients.

The authors regret that Table 1 was incorrect. Regarding the baseline table (Table 1); most of the baseline differences between the groups are incorrect (% men, previous stroke, eGFR 90 year old). In our opinion, these changes leading to less differences between the groups, makes the groups (i.e. >90 and

In patients who underwent transcatheter aortic valve implantation (TAVI), postoperative mortality risk is commonly assessed with risk scores such as the Society of Thoracic Surgeons—Postoperative Risk of Mortality (STS-PROM) and EuroSCORE II, in which age plays a dominant role. However, we reason that in the naturally selected oldest-old patients (nonagenarians), this may not be completely justified and that therefore age should play a minor role in decision-making. The objective of this study was to compare procedural outcome and mid-term mortality of transfemoral (TF)-TAVI patients aged ≥90 years with patients aged