Remote Estimation of Blood Pressure Using Millimeter-Wave Frequency-Modulated Continuous-Wave Radar

Area of Science:

• Biomedical Engineering
• Medical Devices
• Radar Technology

Background:

• High blood pressure is a major health risk, often detected using cumbersome cuff-based methods.
• Continuous, remote blood pressure monitoring is crucial for early disease detection and management.
• Existing methods are contact-based, non-continuous, and inconvenient for long-term use.

Purpose of the Study:

• To develop a non-invasive, remote blood pressure estimation technique using millimeter-wave radar.
• To investigate the correlation between pulse wave velocity (PWV) and blood pressure.
• To explore the utility of radar signal features, like the area under the curve (AUC), for blood pressure assessment.

Main Methods:

• Utilized a millimeter-wave frequency-modulated continuous-wave radar system.
• Measured PWV via pulse transit time between chest and wrist radar signals.
• Analyzed wrist radar signal's pulse wave shape and calculated the area under the curve (AUC).
• Employed artificial neural networks with PWV and AUC as inputs for blood pressure prediction.

Main Results:

• PWV, derived from radar time delay, showed correlation with blood pressure.
• The AUC feature of the wrist pulse wave signal was strongly correlated with blood pressure.
• Artificial neural networks accurately estimated systolic blood pressure (SBP) and diastolic blood pressure (DBP).
• Achieved root mean square errors of 3.33 mmHg for SBP and 3.14 mmHg for DBP.

Conclusions:

• Millimeter-wave radar offers a viable non-invasive method for remote blood pressure monitoring.
• Combining PWV and radar signal analysis (AUC) enhances blood pressure estimation accuracy.
• This technology holds potential for continuous health monitoring and early cardiovascular disease intervention.