Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In The American journal of cardiology ; h5-index 64.0

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. We subsequently applied the semi-supervised 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 (OR 35, 95% CI 4-309, P=0.001), in-hospital all-cause mortality (OR 9, 95% CI 2-33, P=0.002), 30-day cardiovascular mortality (OR 18, 95% CI 3-94, P<0.001) and 30-day all-cause mortality (OR 3, 95% CI 1.2-9, P=0.02) . For 30-day cardiovascular mortality, using phenogroup data in conjunction with the Society of Thoracic Surgeon (STS) score improved the overall prediction of mortality versus using the STS scores alone (Area Under the Curve [AUC] 0.96 vs AUC 0.8, P=0.02). In conclusion, we illustrate that semi-supervised AutoML platforms identifies unique patient phenogroups who have similar clinical characteristics and overall risk of adverse events post TAVI.

Ghaffar Yasir Abdul, Osman Mohammed, Shrestha Sirish, Shaukat Faizan, Kagiyama Nobuyuki, Alkhouli Mohammed, Raybuck Bryan, Badhwar Vinay, Sengupta Partho P


Aortic stenosis, Automated machine learning, Patient similarity network, Society of Thoracic Surgeon (STS) risk calculator, Transcatheter aortic valve implantation