Skip to content
Center for Computational and Digital Health Innovation
Contact Us
Give
  • Home
  • Who We AreExpand
    • Letter from the Director
    • Our Team
    • Careers
    • Contact Us
  • Driving TechnologyExpand
    • Wearables
    • Extended Reality
    • High Performance Computing
    • Artificial Intelligence
  • Research
  • Publications
  • EventsExpand
    • Virtual Seminars
    • Past Events
  • NewsroomExpand
    • News
    • Blog
    • Newsletter
    • Videos
    • Press Resources
Center for Computational and Digital Health Innovation

HarVI AI-enabled, Real-time Extended Reality-Based Treatment Planning

Integrating extended reality and machine learning, we transformed coronary intervention planning with real-time, patient-specific insights.

Lead PI:

  • Amanda Randles

Center Researchers:

    Related Publications

    • HarVI: Real-Time Intervention Planning for Coronary Artery Disease Using Machine Learning
    • Real-time virtual intervention for simple and serial coronary artery disease using the HarVI framework

    In the News:

      The Challenge

      Virtual planning tools that provide intuitive user interaction and immediate hemodynamic feedback are crucial for cardiologists to effectively treat coronary artery disease (CAD). Current FDA-approved tools for coronary intervention planning require days of preliminary processing and rely on conventional 2D displays for hemodynamic evaluation. These delays and limitations hinder timely and accurate treatment planning, particularly for complex coronary lesions such as bifurcations.

      Advances in extended reality (XR) have demonstrated the potential to improve intervention planning, offering an immersive and interactive approach beyond traditional 2D displays. However, no existing intervention planning tool combines real-time hemodynamic feedback with intuitive 3D user interaction in an XR environment while maintaining a rapid turnaround time.

      There is a pressing need for a tool that allows interventional cardiologists to interactively experiment with different PCI strategies, visualize their impact on patient-specific hemodynamics, and optimize treatment decisions in real time.

      Our Solution

      To address these challenges, we developed HarVI (HARVEY Virtual Intervention), a groundbreaking AI-powered tool that integrates real-time hemodynamic analysis with extended reality for immersive, intuitive user interaction.

      HarVI enables real-time hemodynamic feedback using a predefined set of 1D CFD simulations for machine learning-based training, allowing instantaneous FFR predictions with an average processing time of just 74 minutes, compared to the 24-48 hours required by existing tools.

      Through integration with Harvis, HarVI provides an extended reality-based interface for seamless anatomical modifications and hemodynamic visualization, ensuring an intuitive and interactive planning process. In a cohort of 50 patients, HarVI demonstrated high accuracy in predicting post-PCI FFR compared to conventional 1D CFD models, ensuring reliable clinical decision support.

      HarVI’s innovative approach allows cardiologists to receive immediate feedback and 3D visualizations, streamlining the planning process and enhancing the precision of clinical decisions. This tool not only simplifies complex procedures but also improves the accessibility and accuracy of coronary artery disease treatment. By merging intuitive user interfaces with advanced machine learning and XR capabilities, HarVI represents a significant advancement in cardiac care, offering a glimpse into the future of virtual planning and intervention in everyday clinical practice.

      For immersive anatomical editing and visualization capabilities, see Harvis.

      Contact Us

      • Home
      • Who We Are
        • Letter from the Director
        • Our Team
        • Careers
        • Contact Us
      • Driving Technology
        • Wearables
        • Extended Reality
        • High Performance Computing
        • Artificial Intelligence
      • Research
      • Publications
      • Events
        • Virtual Seminars
        • Past Events
      • Newsroom
        • News
        • Blog
        • Newsletter
        • Videos
        • Press Resources

      © 2025 Center for Computational and Digital Health Innovation
      Design and Development by Penner Web Design

      Accessibility.Duke.edu

      Linkedin YouTube X Instagram
      • Home
      • Who We Are
        • Letter from the Director
        • Our Team
        • Careers
        • Contact Us
      • Driving Technology
        • Wearables
        • Extended Reality
        • High Performance Computing
        • Artificial Intelligence
      • Research
      • Publications
      • Events
        • Virtual Seminars
        • Past Events
      • Newsroom
        • News
        • Blog
        • Newsletter
        • Videos
        • Press Resources
      Search