ABSTRACT
Transcatheter aortic valve replacement (TAVR) is the gold standard treatment for patients with symptomatic aortic stenosis. The utility of existing risk prediction tools for in-hospital mortality post-TAVR is limited due to two major factors: (a) the predictive accuracy of these tools is insufficient when only preoperative variables are incorporated, and (b) their efficacy is also compromised when solely postoperative variables are employed, subsequently constraining their application in preoperative decision support. This study examined whether statistical/machine learning models trained with solely preoperative information encoded in the administrative National Inpatient Sample database could accurately predict in-hospital outcomes (death/survival) post-TAVR. Fifteen popular binary classification methods were used to model in-hospital survival/death. These methods were evaluated using multiple classification metrics, including the area under the receiver operating characteristic curve (AUC). By analyzing 54,739 TAVRs, the top five classification models had an AUC ≥ 0.80 for two sampling scenarios: random, consistent with previous studies, and time-based, which assessed whether the models could be deployed without frequent retraining. Given the minimal practical differences in the predictive accuracies of the top five models, the L2 regularized logistic regression model is recommended as the best overall model since it is computationally efficient and easy to interpret.
