Usefulness of Semi-supervised Machine Learning-based Phenogrouping to Improve Risk Assessment for Patients Undergoing Transcatheter Aortic Valve Implantation

Semi-supervised machine learning methods are able to learn from fewer labeled patient data. We illustrate the potential use of a semi-supervised automated machine learning (AutoML) pipeline for phenotyping patients undergoing Transcatheter Aortic Valve Implantation (TAVI) and identifying patient groups with similar clinical outcome. Using the Transcatheter Valve Therapy registry (TVT) data we divided 344 patients into two sequential cohorts (Cohort 1, n= 211, Cohort 2, n=143). We investigated patient similarity analysis to identify unique phenogroups of patients in the first cohort.

Source: The American Journal of Cardiology - September 13, 2020 Category: Cardiology Authors: Yasir Abdul Ghaffar, Mohammed Osman, Sirish Shrestha, Faizan Shaukat, Nobuyuki Kagiyama, Mohammed Alkhouli, Bryan Raybuck, Vinay Badhwar, Partho P. Sengupta Source Type: research