Infective endocarditis (IE) after transcatheter aortic valve replacement (TAVR) is a rare but increasingly recognized entity, associated with a 1-year mortality of up to 50% [ ]. Dismal survival associated with TAVR-IE is attributed to an increased frequency of aortic abscess and fistula formation, severe para-valvular regurgitation, and conduction block [ , ]. Furthermore, only a small proportion of TAVR-IE patients undergo surgical treatment, and this is often due to the prohibitive surgical risk of these patients [ ]. In the context of elevated mortality rates for TAVR-IE, a risk prediction model would be helpful to guide clinical decision-making and prognostication. We aimed to develop a machine learning model for predicting in-hospital mortality for TAVR patients developing IE within one-year post procedure.