Transcatheter aortic valve replacement (TAVR) has become the predominant treatment for symptomatic severe tricuspid aortic stenosis for patients at all levels of surgical risk [ , ]. Risk prediction models are essential for appropriate patient selection prognostication [ ]. Traditional prediction models generated in a “derivation cohort” and assessed in a “validation cohort” are limited by their immutable dependence on conventional statistical analytics. Such models are suboptimal when applied to large data sets with dynamic variables [ ]. Machine learning algorithms, a product of artificial intelligence, have recently emerged as tools to predict adverse outcomes among patients undergoing cardiovascular interventions [ ]. The broad applicability of machine learning algorithms to TAVR remains uncertain. The aim of this study was to assess the accuracy of machine learning algorithms in predicting in-hospital mortality after TAVR.