April 7, 2025 | A real-time extended reality platform for personalized coronary intervention planning using machine learning and CFD.
We are excited to announce the publication of our latest work on HarVI, a real-time Virtual Intervention platform. Building on our lab’s prior tools—HARVEY for large-scale blood flow simulation and HarVis for immersive visualization—HarVI integrates machine learning with one-dimensional computational fluid dynamics (1D CFD) to deliver immediate predictions of fractional flow reserve (FFR), flow rate, and wall shear stress. Ph.D. candidate Cyrus Tanade led the development of this framework that supports same-day planning for both simple and serial coronary lesions, significantly reducing turnaround time to an average of just 62 minutes. HarVI’s XR interface allows clinicians to intuitively interact with vessel geometry and visualize hemodynamic feedback in real time, offering a powerful new approach to precision cardiology.
Read the full publication here: https://duke.is/jcsharvi
Tanade, C. & Randles, A., Real-time virtual intervention for simple and serial coronary artery disease using the HarVI framework, Journal of Computational Science, 2025. https://doi.org/10.1016/j.jocs.2025.102570