Jenab, Yaser

Background/Objectives: Transcatheter aortic valve replacement (TAVR) has been introduced as an optimal treatment for patients with severe aortic stenosis, offering a minimally invasive alternative to surgical aortic valve replacement. Predicting these outcomes following TAVR is crucial. Artificial intelligence (AI) has emerged as a promising tool for improving post-TAVR outcome prediction. In this systematic review and meta-analysis, we aim to summarize the current evidence on utilizing AI in predicting post-TAVR outcomes. Methods: A comprehensive search was conducted to evaluate the studies focused on TAVR that applied AI methods for risk stratification. We assessed various ML algorithms, including random forests, neural networks, extreme gradient boosting, and support vector machines. Model performance metrics—recall, area under the curve (AUC), and accuracy—were collected with 95% confidence intervals (CIs). A random-effects meta-analysis was conducted to pool effect estimates. Results: We included 43 studies evaluating 366,269 patients (mean age 80 ± 8.25; 52.9% men) following TAVR. Meta-analyses for AI model performances demonstrated the following results: all-cause mortality (AUC = 0.78 (0.74–0.82), accuracy = 0.81 (0.69–0.89), and recall = 0.90 (0.70–0.97); permanent pacemaker implantation or new left bundle branch block (AUC = 0.75 (0.68–0.82), accuracy = 0.73 (0.59–0.84), and recall = 0.87 (0.50–0.98)); valve-related dysfunction (AUC = 0.73 (0.62–0.84), accuracy = 0.79 (0.57–0.91), and recall = 0.54 (0.26–0.80)); and major adverse cardiovascular events (AUC = 0.79 (0.67–0.92)). Subgroup analyses based on the model development approaches indicated that models incorporating baseline clinical data, imaging, and biomarker information enhanced predictive performance. Conclusions: AI-based risk prediction for TAVR complications has demonstrated promising performance. However, it is necessary to evaluate the efficiency of the aforementioned models in external validation datasets.

ABSTRACTBackgroundComparisons of outcomes after transcatheter aortic valve replacement with balloon‐expandable (BEV) versus self‐expanding (SEV) valves are limited.HypothesisThis study aimed to compare clinical and hemodynamic outcomes of BEV and SEV at short‐term (30 days), midterm (1 year), and long‐term (> 1 year) endpoints.MethodsPubMed, Embase, Scopus, and Cochrane Library databases were searched until July 2024 for randomized controlled trials. Random‐effect model (DerSimonian–Laird method) was used to pool the risk ratios (RR), mean differences, and 95% confidence intervals (CI).ResultsA total of 10 studies comprising 4325 patients (2295 BEV, 2030 SEV) were included. In short‐term, cardiovascular (RR: 0.56, 95% CI: 0.36–0.87) and all‐cause mortality (RR: 0.54, 95% CI: 0.35–0.81) were lower in the BEV group. Risk of moderate to severe paravalvular leak (PVL) was lower among BEV patients in short‐term (RR: 0.28, 95% CI: 0.17–0.49) and long‐term (RR: 0.28, 95% CI: 0.1–0.79). A limited number of studies showed a greater risk of clinical valve thrombosis on BEV in midterm and long‐term. The need for permanent pacemaker implantation was lower in BEV at both short‐term (RR: 0.56, 95% CI: 0.37–0.87), and midterm (RR: 0.78, 95% CI: 0.64–0.94). The SEV group had a larger effective orifice area with lower mean transvalvular pressure gradient at all endpoints.ConclusionsBEV is associated with reduced risk of clinical outcomes in short‐term; however, most differences diminish in longer evaluations, except for moderate to severe PVL, which remains elevated for SEV. SEVs had better hemodynamic results and lower risk of clinical valve thrombosis.

Abstract Background The standard modifiable cardiovascular risk factors (SMuRFs: hypertension, diabetes mellitus, dyslipidemia, and cigarette smoking) are known to play a major role in the pathogenesis of coronary heart disease (CHD). Despite endeavors aiming at primary and secondary prevention of these risk factors, CHD has remained a leading cause of mortality and morbidity worldwide. A considerable proportion of patients admitted with acute coronary syndrome (ACS) have no SMuRFs, the outcomes of whom following percutaneous coronary intervention (PCI) are debated. Further, sex differences within this population have yet to be established. Purpose The present study aimed to evaluate the association between SMuRF-less status and post-PCI outcomes among patients with ACS. Further, we sought to determine possible sex differences in the post-PCI outcomes related to the SMuRF-less status. Methods This retrospective cohort study included 7847 patients with ACS who underwent PCI. The study outcomes were all-cause mortality and major adverse cardio-cerebrovascular events (MACCE). The association between the absence of SMuRFs (SMuRF-less status) and outcomes among all the patients and each sex was assessed using logistic and Cox proportional hazard regressions. A separate landmark analysis with the landmark (cutoff) set at 30 days after the index procedure was performed as well. Models were adjusted for age, sex, body mass index, chronic obstructive pulmonary disease, cerebrovascular accident, previous myocardial infarction, estimated glomerular filtration rate, ejection fraction, and left main disease. Results Approximately 11% of the study population had none of the SMuRFs. The SMuRF-less and SMuRF+ groups aged 63.10 ±8.91 (85.1% males) and 62.53 ± 10.91 years (74.9% males), respectively. During 12.13 [11.99-12.36] months of follow-up, the followings were respective event numbers in the SMuRF-less and SMuRF+ groups: all-cause mortality: 35 (4.1%) and 273 (3.9%); MACCE: 99 (11.6%) and 898 (12.8%). All-cause mortality (adjusted-hazard ratio (HR): 1.01, 95%CI: 0.88-1.46, P: 0.731), and MACCE (adjusted-HR: 0.93, 95%CI:0.81-1.12, P: 0.412) did not differ between patients with and without SMuRFs (Figure 1). Sex-stratified analyses recapitulated similar outcomes between SMuRF+ and SMuRF-less men. In contrast, SMuRF-less women had significantly higher all-cause mortality (adjusted-HR:1.41, 95%CI: 1.02-3.21, P: 0.008) than SMuRF+ women (Figure 1). Notably, following landmark analyses, this significant association among women disappeared (adjusted-HR: 0.99, 95%CI: 0.41-2.59, P:0.991), implying that its significance stemmed, to some extent, from higher 30-day mortality (Figure 1,2). Conclusions Almost one in 10 patients with ACS who underwent PCI had no SMuRFs. The absence of SMuRFs did not confer any benefit in terms of in-hospital mortality, one-year mortality, and MACCE. Even worse, SMuRF-less women paradoxically had an excessive risk of one-year mortality.