Using Machine-Learning for Prediction of the Response to CRT: the SMART-AV study

Our manuscript is accepted for publication. It was published 8/25/21 in the JACC Clinical Electrophysiology. Using machine learning, we developed and validated a parsimonious model that is comprised of routinely available baseline clinical, ECG, and echocardiographic characteristics. Participants in the 5th quintile compared to those in the 1st quintile of the prediction model had 14-fold higher odds of composite CRT response.