Machine learning-based predictive risk models for 30-day and 1-year mortality in severe aortic stenosis patients undergoing transcatheter aortic valve implantation.

BACKGROUND: Predictive risk score for mortality plays an important role in the decision-making in patient selection and risk stratification for TAVI. Existing established predictive risk scores had poor discrimination performance in the prediction of mortality after the TAVI. OBJECTIVES: The present study aimed to develop machine learning-based predictive models for 30-day and 1-year mortality in severe aortic stenosis patients undergoing TAVI. METHODS: A total of 186 patients in a retrospective cohort study were analyzed. The models were fitted by a decision tree. Each model was tested in 100 iterations of 80:20 stratified random splitting into training/testing samples and 10-fold cross-validation. RESULTS: Variables that predict 30-day mortality are a set of factors driven mainly by height, chronic lung disease, STS score, preoperative LVEF, age, and preoperative LVOT VTI. Variables that predict 1-year mortality are a set of factors consisting of preoperative LVEF, STS score, heart rate, systolic blood pressure, home oxygen use, serum creatinine level, and preoperative LVOT Vmax. This decision tree-generated predictive models for 30-day and 1- year mortality provided the most precise accuracy of 0.97 and 0.90 with the AUC-ROC curves of 0.83 and 0.71 on 30-day and 1-year mortality on testing data and had better discrimination performance compared to the existing established TAVI predictive risk scores. CONCLUSIONS: These machine learning models show excellent accuracy and have a better prediction for 30-day and 1-year mortality than the existing established TAVI predictive risk scores. A customized predictive model deems to be properly developed for better risk discrimination among cohorts.

Machine Learning-Based Predictive Model of Aortic Valve Replacement Modality Selection in Severe Aortic Stenosis Patients.

The current recommendation for bioprosthetic valve replacement in severe aortic stenosis (AS) is either surgical aortic valve replacement (SAVR) or transcatheter aortic valve replacement (TAVR). We evaluated the performance of a machine learning-based predictive model using existing periprocedural variables for valve replacement modality selection. We analyzed 415 patients in a retrospective longitudinal cohort of adult patients undergoing aortic valve replacement for aortic stenosis. A total of 72 clinical variables including demographic data, patient comorbidities, and preoperative investigation characteristics were collected on each patient. We fit models using LASSO (least absolute shrinkage and selection operator) and decision tree techniques. The accuracy of the prediction on confusion matrix was used to assess model performance. The most predictive independent variable for valve selection by LASSO regression was frailty score. Variables that predict SAVR consisted of low frailty score (value at or below 2) and complex coronary artery diseases (DVD/TVD). Variables that predicted TAVR consisted of high frailty score (at or greater than 6), history of coronary artery bypass surgery (CABG), calcified aorta, and chronic kidney disease (CKD). The LASSO-generated predictive model achieved 98% accuracy on valve replacement modality selection from testing data. The decision tree model consisted of fewer important parameters, namely frailty score, CKD, STS score, age, and history of PCI. The most predictive factor for valve replacement selection was frailty score. The predictive models using different statistical learning methods achieved an excellent concordance predictive accuracy rate of between 93% and 98%.