Personalized Cuffless Blood Pressure Measurement based on Arterial 0D-1D Model with Carotid Flow and Radial Pulse

Area of Science:

• Biomedical Engineering
• Cardiovascular Physiology
• Medical Devices

Background:

• Hypertension management is crucial for cardiovascular disease prevention.
• Cuffless blood pressure (BP) monitoring using photoplethysmogram (PPG) signals shows promise but faces generalization challenges due to single-locality data.
• Current PPG-based BP estimation often lacks personalization and struggles with individual variability.

Purpose of the Study:

• To develop a personalized cuffless BP estimation model.
• To integrate central and peripheral cardiovascular information for improved BP measurement accuracy.
• To validate a coupled arterial 0D-1D model for brachial BP estimation.

Main Methods:

• Proposed a coupled arterial 0D-1D model incorporating carotid blood flow and radial artery PPG signals.
• Utilized multimodal signals representing both central and peripheral cardiovascular dynamics.
• Validated the model on the Pulse Wave Dataset, comprising 4374 samples.

Main Results:

• Achieved mean errors of 1.39 ± 2.53 mmHg for systolic BP and -0.47 ± 2.39 mmHg for diastolic BP.
• Demonstrated superior performance compared to traditional machine learning models like decision trees and random forests.
• The 0D-1D model effectively integrated multimodal signals and blood flow path information for personalized BP measurement.

Conclusions:

• The coupled arterial 0D-1D model offers a promising approach for accurate and personalized cuffless BP estimation.
• Integrating central and peripheral cardiovascular data enhances the generalization and reliability of BP monitoring.
• This technology has the potential to revolutionize hypertension management and cardiovascular disease prevention.