Reproduce “Arterial Blood Pressure Feature Estimation Using Photoplethysmography” 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
Armin Soltan Zadi, Raichel Alex, Rong Zhang, Donald E. Watenpaugh, Khosrow Behbehani
Researchers at The University of Texas at Arlington developed an Autoregressive Moving Average (ARMA) modeling framework for continuous, non-invasive estimation of systolic, diastolic, and mean arterial pressure using only photoplethysmography (PPG) signals. Their method achieved root mean square errors below 5 mmHg for modeling and under 8 mmHg for prediction, effectively tracking blood pressure changes during normal breathing and breath-hold induced physiological perturbations.
Key insights
- ARMA models effectively capture the dynamic and time-delayed relationships inherent in physiological systems, allowing for robust BP estimation from PPG alone, even under non-stationary conditions.
- The proposed method can accurately track the overall trends and higher-frequency modulations of SBP, DBP, and MAP during both normal breathing and induced physiological perturbations.
- The high inter-subject consistency of the error metrics indicates the potential generalizability of the ARMA modeling approach across different individuals.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.