Patients with uncorrected isolated simple shunts associated pulmonary arterial hypertension (PAH) had increased mortality. Treatment strategies for borderline hemodynamics remain controversial. This study aims to investigate pre-closure characteristics and its association with post-closure outcome in this group of patients. Adults with uncorrected isolated simple shunts associated PAH were included. Peak tricuspid regurgitation velocity <2.8m/s with normalized cardiac structures was defined as the favorable study outcome. We applied unsupervised and supervised machine learning for clustering analysis and model constructions. Finally, 246 patients were included. During a median follow-up of 414 days, 58.49% (62/106) of patients with pre-tricuspid shunts achieved favorable outcome while 32.22% (46/127) of patients with post-tricuspid shunts. In unsupervised learning, two clusters were identified in both types of shunts. Generally, the oxygen saturation, pulmonary blood flow, cardiac index, dimensions of the right and left atrium, were the major features that characterized the identified clusters. Specifically, mean right atrial pressure, right ventricular dimension and right ventricular outflow tract helped differentiate clusters in pre-tricuspid shunts while age, aorta dimension and systemic vascular resistance helped differentiate clusters for post-tricuspid shunts. Notably, cluster 1 had better post-closure outcome than cluster 2 (70.83% vs. 32.55%, P<0.001 for pre-tricuspid and 48.10% vs. 16.67%, P<0.001 for post-tricuspid). However, models constructed from supervised learning methods did not achieve good accuracy for predicting the post-closure outcome. There were two main clusters in patients with borderline hemodynamics, in which one cluster had better post-closure outcome than the other. The datasets and analyzed codes are available upon reasonable request from the corresponding author.
Read full abstract