Optimized Non-invasive Cuff-less Continuous Blood Pressure Measurement Technique Using Machine Learning
Continuous blood pressure (BP) monitor is highly beneficial for detection and prevention of stroke and cardiovascular disease. The most common BP monitor technique still relies on using a cuff that obstructs the blood flow, which is both uncomfortable and makes continuous monitoring impossible. Furthermore, research has shown that due to the numerous artifacts, the existing cuff-less BP monitoring technologies such as pulse transit time (PTT) and tonometry are not sufficiently accurate. The purpose of this study is to introduce a low-cost, non-invasive, and continuous BP monitoring technique which is capable of estimating BP from dilation and retraction of the wrist radial artery. The mentioned approach utilizes two small optical sensors which can be integrated to any wristband or smartwatch. After calibration, the proposed approach may be used for months to estimate blood pressure in an accurate, easy-to-use and low-cost fashion.