Novel Cuffless Blood Pressure Estimation Method Using a Bayesian Hierarchical Model.

Area of Science:

• Biomedical Engineering
• Cardiovascular Physiology
• Signal Processing

Background:

• Continuous blood pressure (BP) monitoring is crucial for cardiovascular disease prevention and diagnosis.
• Cuffless BP estimation using pulse arrival time (PAT) is an emerging research area for continuous BP measurement.
• Existing methods often require frequent calibration or are limited in accuracy.

Purpose of the Study:

• To develop and validate a hierarchical model for cuffless systolic blood pressure (SBP) estimation using PAT.
• To assess the model's accuracy with minimal calibration measurements.
• To enable continuous and non-invasive BP monitoring.

Main Methods:

• Simultaneous acquisition of electrocardiogram (ECG) and photoplethysmogram (PPG) signals from ten healthy subjects.
• Utilized a cuff-based Finometer PRO for continuous reference BP data.
• Applied a hierarchical model to estimate parameters of a nonlinear model for SBP estimation using PAT.

Main Results:

• The proposed hierarchical model achieved a mean absolute difference (MAD) of 4.35±1.43 mmHg for SBP estimation with three calibration measurements.
• Similar accuracy (MAD of 4.36±1.17 mmHg) was observed with only one calibration measurement.
• The model demonstrates effective SBP estimation with limited calibration needs.

Conclusions:

• A hierarchical model provides accurate cuffless SBP estimation using PAT.
• The method is effective even with a single calibration measurement, simplifying practical application.
• This approach holds promise for continuous, non-invasive cardiovascular health monitoring.