Unsupervised Machine Learning of Computed Tomography Angiography Features Uncovers Unique Subphenotypes of Aortic Stenosis With Differential Risks of Conduction Disturbances Following Transcatheter Aortic Valve Replacement

Authors

Abstract

BackgroundVarious measurements around the aortic valve are typically made on computed tomography angiograms (CTAs) before transcathether aortic valve replacement (TAVR) for aortic stenosis (AS), but their collective prognostic inference on periprocedural conduction disturbances (CDs) is not known. Here, we aimed to use unsupervised machine learning (UML) to analyze a multitude of pre-TAVR CTA features and uncover patient subphenotypes with differential risks of CDs. MethodsTwelve nonredundant features involving the aortic valve, aortic root, and ascending aorta were extracted from the CTAs of 660 AS patients. UML of these features using agglomerative hierarchical clustering was performed on separate male and female datasets, with the optimal number of clusters determined by 30 cluster indices. Multivariable logistic regression was conducted to assess the dependence of CDs on cluster type and the latters incremental prognostic value over conventional risk factors. ResultsThree male clusters were optimally identified (M1-M3): M1 was associated with small valve leaflet calcification loads and aortic root dimensions; both M2 and M3 were associated with large valve leaflet calcification loads and a wide aortic root, but the aortic root was shorter in M2 than M3. Two female clusters were optimally determined (F1-F2): F2 was associated with larger valve leaflet calcification loads and aortic root dimensions. By logistic regression analysis, compared to M1 (reference), M2, but not M3, was more associated with CDs (ORM2/M1=2.15, P=0.032; ORM3/M1=2.12, P=0.085), with no difference between M3 and M2 (ORM3/M2=0.986, P=0.974) or between F1 and F2 (ORF2/F1=1.294, P=0.581). Including cluster type as a predictor in a regression model of CDs containing conventional risk factors as covariates improved the goodness-of-fit (P=0.020). ConclusionsUML of pre-TAVR CTAs can reveal subgroups of male patients with differential risks for CDs and improve prognostication over conventional risk factors. UML-augmented pre-TAVR CTAs may help better guide personalized strategies to minimize CDs.

Tags

Topics