Reproduce “Measuring multi-site pulse transit time with an AI-enabled mmWave radar” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiangyifei Zhu, Kuang Yuan, Akarsh Prabhakara, Yunzhi Li, Gongwei Wang, Kelly Michaelsen, Justin Chan, Swarun Kumar
PolyPulse, developed by researchers at Carnegie Mellon University, introduces the first AI-enabled millimeter-wave radar system that non-invasively measures multi-site Pulse Transit Time (PTT) and estimates diastolic blood pressure (DBP) using a single radar unit. The system achieves high correlation with contact-based sensors and meets stringent FDA AAMI and BHS Grade A clinical guidelines for DBP accuracy.
Key insights
- A single mmWave radar can effectively spatially resolve and track subtle physiological displacements (e.g., ~30 μm for radial artery) from multiple distinct arterial sites simultaneously, even amidst larger body movements.
- Deep learning, specifically a multi-branch DNN with cross-region attention, significantly enhances the robustness and accuracy of cardiac feature detection by leveraging temporal correlations between signals from different body regions.
- Contactless PTT measurements, when combined with subject-specific calibration, can reliably estimate DBP with accuracy levels comparable to gold-standard methods, meeting established clinical validation standards.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.