A novel computational method to predict hypoattenuated leaflet thickening post-transcatheter aortic valve replacement using preprocedural computed tomography scans

Objective: Hypoattenuated leaflet thickening (HALT) is a computed tomography (CT) finding after transcatheter aortic valve replacement (TAVR) that is indicative of bioprosthetic valvular thrombosis. There are currently no standardized or validated methods for predicting HALT, which can cause bioprosthetic valve dysfunction and has been associated with adverse patient outcomes. The objective was to develop a novel fast-response, artificial intelligence, and machine learning (ML)-driven computational pipeline to predict HALT using preprocedural CT scans. Methods: The pipeline consisted of (1) pre-TAVR CT reconstruction and reduced order modeling simulations to automatically predict postprocedural geometric parameters, (2) a landmark-guided automated left ventricle segmentation method to predict hemodynamic parameters, and (3) statistical and ML analyses to develop HALT predictive metrics. Results: Pre- and postprocedural scans from 45 patients (21 with HALT, 24 without) were used as inputs for the pipeline. We identified statistically significant relationships between HALT and peak systolic blood velocity (P < .01) and peak systolic blood flow through the bioprosthetic valve (P < .01), left ventricular ejection time (P < .01), ejection volume (P < .05), and right coronary height (P < .05). ML-yielded metrics related to circulation in the neosinuses correlated strongly with HALT occurrence (P < .001) along with the greatest accuracy of 84.40% and area under receiver operating characteristic curve of 0.87. Conclusions: A computational pipeline using pre-procedural CT scans as inputs that outputs post-TAVR geometric and hemodynamic measurements was developed to assess metrics with the potential to predict the risk of HALT. Such a tool may help guide decision-making and understanding of prevention of postprocedural thrombosis.