• 01005702928
  • acs-egypt.com
  • 7 khan Younis, Giza, Egypt
Senior woman checking blood pressure (hypertension) vai mobile p
EASILY MONITOR YOUR BLOOD PRESSURE FROM FINGERTIP IMAGING.
YOU CAN TRY IT
SVYATKOVSKY.COM

Blood Pressure Monitor App is a simple and easy-to-use tool that helps you monitor your blood pressure.

previous arrow
next arrow

ABOUT US

Who are we?

This innovative application leverages a 20-second fingertip video to extract two critical physiological vital signs: blood pressure (BP) and heart rate (HR). The core concept revolves around estimating remote Photoplethysmography (rPPG) signals from the video, which are then utilized for continuous monitoring of BP and HR. To achieve this, the application employs a novel per-beat rPPG-to-BP mapping scheme based on transfer learning. 10.1007/s10489-024-05354-9.

A key innovation in this approach is the transformation of the 1-D PPG signal into a 2-D image representation. This conversion enables the use of powerful, off-the-shelf image-based models through transfer learning, effectively addressing limitations related to training data size caused by stringent data cleaning requirements.

MISSION

To provide a simple, accurate, and intelligent health monitoring tool that helps users track and manage their blood pressure and heart rate effortlessly. By leveraging cutting-edge vascular imaging and artificial intelligence, we aim to enhance health awareness, improve preventive care, and promote a healthier lifestyle.

VISION

To be the leading digital health companion, empowering individuals to take control of their well-being through innovative and AI-driven blood pressure and heart rate monitoring solutions.

The high-quality beats are then utilized for BP estimation. Experimental results demonstrate that the proposed system outperforms state-of-the-art methods in terms of mean absolute error (MAE) and standard deviation (STD). Specifically, the STD for test data is reduced to 5.4782 for systolic blood pressure (SBP) and 3.8539 for diastolic blood pressure (DBP). Similarly, the MAE is reduced to 2.3453 for SBP and 1.6854 for DBP.

Furthermore, when applied to real-world video data, the system achieves an STD of 8.027882 for SBP and 6.013052 for DBP, with MAE values of 7.052803 for SBP and 5.616028 for DBP. These results highlight the system’s robustness and accuracy in estimating BP and HR from real-world video inputs.

For a more detailed exploration of the methodology and results, please refer to our published paper: