Real-time virtual intervention for simple and serial coronary artery disease using the HarVI framework

Abstract

Virtual planning tools that provide intuitive user interaction and immediate hemodynamic feedback are crucial for cardiologists to effectively treat coronary artery disease. Current FDA-approved tools for coronary intervention planning require days of preliminary processing and rely on conventional 2D displays for hemodynamic evaluation. Immersion offered by extended reality (XR) has been found to benefit intervention planning over traditional 2D displays. Building on our previous work (Tanade and Randles, 2024), we introduce HarVI, a coronary intervention planner that leverages machine learning for real-time hemodynamic analysis and extended reality for intuitive 3D user interaction. The framework uses a predefined set of 1D steady state computational fluid dynamics (CFD) simulations to perform one-shot training for our machine learning-based blood flow model. In a two-center cohort of 73 patients, 70 with focal lesions and 3 with serial lesions, we calculated fractional flow reserve — the gold standard biomarker of ischemia in coronary disease, flow rate, and wall shear stress using HarVI and 1D CFD models. HarVI was shown to almost perfectly recapitulate the results of 1D CFD simulations through continuous validation scores. In this study, we establish a machine learning-based process for virtual coronary treatment planning with an average turnaround time of just 62 min — around an order of magnitude improvement over literature standards, thus reducing the required time for one-shot training to less than one working day.