Short Time Blood Pressure Estimation Using RGB-NIR Camera.

Area of Science:

• Biomedical Engineering
• Medical Imaging
• Physiological Monitoring

Background:

• Traditional blood pressure measurement methods can be invasive, uncomfortable, and perform poorly in low light.
• There is a need for convenient, non-invasive methods for continuous blood pressure monitoring.

Purpose of the Study:

• To develop and validate a non-contact method for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) using facial video.
• To assess the generalizability and short-time estimation accuracy of the proposed method.

Main Methods:

• Utilized RGB-NIR camera to capture facial video images.
• Extracted pulse wave signals from facial videos.
• Employed a Random Forest algorithm for SBP and DBP estimation.
• Included diverse age groups to ensure generalizability.

Main Results:

• Demonstrated the potential for accurate non-contact blood pressure estimation from facial videos.
• Achieved reliable estimation across various age groups.
• Evaluated short-time estimation accuracy for enhanced daily usability.

Conclusions:

• The proposed non-contact method using RGB-NIR cameras offers a promising solution for continuous, non-invasive blood pressure monitoring.
• This technology can reduce patient burden and improve accessibility in daily life and remote healthcare settings.
• The method shows potential for use in low-light conditions, addressing a key limitation of existing techniques.