Shojaei, Shayan

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.

Background: Coronary in-stent restenosis (ISR) secondary to neointimal hyperplasia or neoatherosclerosis remains a significant challenge following percutaneous coronary interventions (PCI), with no consensus on the optimal revascularization strategy. We compared the outcome of PCI for ISR using drug-coated balloons (DCB) and drug-eluting stents (DES) and investigated the time trends in their clinical outcomes. Methods: PubMed, Embase, Scopus, and the Cochrane Library databases were searched through May 2024. We included randomized controlled trials (RCTs) comparing DCB versus DES among patients with coronary ISR. The primary outcome was target lesion revascularization (TLR). Secondary outcomes included all-cause mortality, myocardial infarction (MI), stent thrombosis, and late lumen loss (LLL). Random-effects models were employed to analyze outcomes within 1-year and beyond 1-year intervals. Meta-regression analysis was used to investigate the effect of age, sex, history of diabetes, hypertension, dyslipidemia, smoking, and ejection fraction on all outcomes by applying mixed-effect models. Results: We included 10 RCTs (1034 patients in the DCB group and 943 patients in the DES group). We found similar incidence of 1-year TLR (odds ratio [OR] 1.36; 95% confidence interval [CI] 0.86, 2.14; P 0.194; I 2 43.3%) and >1-year TLR (OR 0.94; 95% CI 0.57, 1.56; P 0.817; I 2 0%) with the use of DCB versus DES. The risks of all-cause mortality, MI, and stent thrombosis were comparable between DCB and DES in 1-year and beyond 1-year follow-ups. At 6-9 months angiographic follow-up, DCB was associated with non-significantly lower LLL compared to DES (standardized mean difference [SMD] -0.12 millimeters; 95% CI -0.29, 0.05; P 0.170; I 2 71.7%). Meta-regression indicated that higher prevalence of diabetes was associated with an increased risk of 1-year revascularization after DCB compared to DES (Estimate 0.07; P 0.003; I 2 0%). Additionally, male sex was associated with an increased LLL in DCB versus DES (Estimate 0.034; P 0.001; I 2 41.8%). No association was found between other baseline characteristics and measured clinical outcomes. Conclusion: DCB demonstrated comparable PCI outcomes compared to DES in patients with coronary ISR.