Measuring multi-site pulse transit time with an AI-enabled mmWave radar

Area of Science:

• Biomedical Engineering
• Cardiovascular Physiology
• Artificial Intelligence in Healthcare

Background:

• Pulse Transit Time (PTT) is a validated physiological marker for assessing arterial stiffness and cardiovascular function.
• An inverse relationship exists between PTT and diastolic blood pressure (DBP).
• Current methods for PTT measurement often require physical contact, limiting continuous monitoring and multi-site assessment.

Purpose of the Study:

• To develop and evaluate an AI-enabled, contactless mmWave radar system for simultaneous multi-site PTT measurement and DBP estimation.
• To assess the system's accuracy against established contact-based sensors.
• To determine if the system meets regulatory guidelines for non-invasive blood pressure monitoring.

Main Methods:

• Utilized a single mmWave radar system incorporating beamforming and deep learning algorithms.
• Performed contactless PTT measurements across three physiological pathways: heart-to-radial, heart-to-carotid, and mastoid area-to-radial arteries.
• Validated DBP estimation against reference sensors, comparing results against FDA AAMI guidelines.

Main Results:

• Achieved correlation coefficients of 0.75-0.86 for PTT measurements compared to contact-based sensors.
• Demonstrated high correlation coefficients (0.90-0.91) for DBP estimation.
• Met FDA AAMI guidelines for non-invasive blood pressure monitors with a mean error of -0.62-0.06 mmHg and standard deviation of 4.54-5.20 mmHg.

Conclusions:

• The proposed AI-enabled mmWave radar system offers a promising non-invasive method for assessing cardiovascular health.
• Simultaneous multi-site PTT measurement and DBP estimation can be achieved contactlessly.
• The system's performance meets clinical standards, suggesting potential for widespread application in health monitoring.