Usefulness of Semisupervised Machine-Learning-Based Phenogrouping to Improve Risk Assessment for Patients Undergoing Transcatheter Aortic Valve Implantation

Abstract

Semisupervised machine-learning methods are able to learn from fewer labeled patient data. We illustrate the potential use of a semisupervised automated machine-learning (AutoML) pipeline for phenotyping patients who underwent transcatheter aortic valve implantation and identifying patient groups with similar clinical outcome. Using the Transcatheter Valve Therapy registry data, we divided 344 patients into 2 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. We subsequently applied the semisupervised AutoML to the second cohort for developing automatic phenogroup labels. The patient similarity network identified 5 patient phenogroups with substantial variations in clinical comorbidities and in-hospital and 30-day outcomes. Cumulative assessment of patients from both cohorts revealed lowest rates of procedural complications in Group 1. In comparison, Group 5 was associated with higher rates of in-hospital cardiovascular mortality (odds ratio [OR] 35, 95% confidence interval [CI] 4 to 309, p = 0.001), in-hospital all-cause mortality (OR 9, 95% CI 2 to 33, p = 0.002), 30-day cardiovascular mortality (OR 18, 95% CI 3 to 94, p <0.001), and 30-day all-cause mortality (OR 3, 95% CI 1.2 to 9, p = 0.02) . For 30-day cardiovascular mortality, using phenogroup data in conjunction with the Society of Thoracic Surgeon score improved the overall prediction of mortality versus using the Society of Thoracic Surgeon scores alone (AUC 0.96 vs AUC 0.8, p = 0.02). In conclusion, we illustrate that semisupervised AutoML platforms identifies unique patient phenogroups who have similar clinical characteristics and overall risk of adverse events post-transcatheter aortic valve implantation.