Related Experiment Video
Updated: Jun 24, 2026

Assessing Cerebral Autoregulation via Oscillatory Lower Body Negative Pressure and Projection Pursuit Regression
Published on: December 10, 2014
Non-Invasive BP Estimation via Carotid-Brachial-Radial Coupling: A Physics-Informed Asymmetric Cycle Network Approach
A new physics-informed deep learning model, PIAC-Net, improves cuffless blood pressure monitoring by integrating central carotid artery data with peripheral photoplethysmogram signals. This approach enhances accuracy and interpretability for hypertension management.
Area of Science:
- Biomedical Engineering
- Cardiovascular Physiology
- Artificial Intelligence in Medicine
Background:
- Cuffless blood pressure (BP) monitoring using photoplethysmogram (PPG) shows promise for hypertension management but suffers from accuracy and interpretability issues.
- Limitations stem from PPG's inability to capture central hemodynamic drivers and inherent physical constraints.
Purpose of the Study:
- To develop a novel multimodal, physics-informed deep learning framework (PIAC-Net) for accurate and interpretable cuffless BP monitoring.
- To integrate central arterial information, specifically carotid blood flow velocity, with peripheral PPG signals.
Main Methods:
- A physics-informed deep learning framework (PIAC-Net) was developed, integrating multi-site physiological data from carotid, brachial, and radial arteries.
- Carotid blood flow velocity was incorporated as a central hemodynamic signal, supplementing PPG data.
- Hybrid physical loss functions, combining 1D Navier-Stokes equations and 0D Windkessel boundary conditions, enforced hemodynamic conservation on the brachial waveform.
Main Results:
- PIAC-Net demonstrated superior accuracy compared to existing methods in both synthetic (N=4374) and in-house (N=1765) datasets.
- Mean absolute errors for systolic/diastolic BP were 1.82/1.51 mmHg (synthetic) and 7.08/6.38 mmHg (in-house).
- Integrating carotid data reduced estimation errors by over 50%, highlighting its role as a primary accuracy factor. Physics-based constraints ensured performance even with limited data.
Conclusions:
- The dual-fusion paradigm of "central driver-peripheral response" and "data-physics" integration offers a clinically viable solution for high-precision BP monitoring.
- PIAC-Net provides a significant advancement in cuffless BP monitoring, addressing key limitations of PPG-based methods.
- This approach holds potential for revolutionizing hypertension management through improved accuracy and interpretability.
Related Concept Videos
Assessment of blood pressure in brachial artery(two-step method)
Assessment of blood pressure in brachial artery(one-step method)
Prepare for the Procedure:
Sites for measuring blood pressure
The Brachial Artery: Primary Site for Blood Pressure Measurement
Assessing Blood pressure using a doppler ultrasound
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
Measurement of Blood Pressure
Special considerations while measuring blood pressure
Monitoring Both Arms:
Monitoring BP in both arms during the initial assessment is advisable, as the systolic value may differ by five to ten mm Hg between arms. For subsequent BP assessments, use the arm with the higher reading.
