Personalized pre-interventional risk stratification of mortality, length of stay and hospitalization costs in transcatheter aortic valve implantation using a machine learning algorithm a pilot trial

Introduction Risk stratification based on Euroscore II (ESII) is currently used by clinicians to assist their decision to perform transcatheter aortic valve implant (TAVI) procedures. ESII is a generic, non-TAVI-specific metric. We investigated if a TAVI-specific predictive model could achieve improved predictive pre-interventional accuracy of 1-year mortality compared to ESII. Patients & Methods: In this prospective pilot study, 284 participants with severe aortic valve stenosis who underwent TAVI were enrolled. Standard clinicals metrics (ASA, NYHA, ESII) and patient-reported outcome measures (EuroQol-5D-VAS, Kansas City Cardiomyopathy Questionnaire, Clinical Frailty Scale-CFS) were assessed one day before TAVI. Using these data, we tested predictive models (logistic regression, decision tree algorithm- DTA) with 1-year mortality as the dependent variable. Results Logistic regression yielded the best prediction, with ASA and CFS as the strongest predictors. Our logistic regression model score showed significantly better prediction accuracy than ESII (AUC = 0.659 vs. 0.800; p = 0.002). By translating our results to a DTA, cut-off score values regarding 1-year mortality risk emerged: < 0.02 points for low, 0.02 – 0.15 for intermediate, > 0.15 for high risk. Treatment costs and length of stay significantly increased in high-risk patients. Conclusions & significance A novel TAVI-specific model predicts 1-year mortality, LoS and costs after TAVI using simple, established, transparent and inexpensive metrics before implantation. Based on this preliminary evidence, TAVI team members and patients can make informed decisions based on a few key metrics. Validation of this score in larger patient cohorts is needed. Comparison of ROC curves