Pulse-wave based non-contact continuous blood pressure measurement

• Main Author: Huang, Jiaxing
• Other Authors: Muhammad Faeyz Karim
• Format: Theses and Dissertations
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/78405
• Institution: Nanyang Technological University

Blood pressure measurement is very important for human beings, which directly indicates the status of cardiovascular system. Not only for medical treatment (especially for critical patient during operation), but also for family health care, continuous blood pressure monitoring is best way to reflect the vital signs. The current existing approaches of blood pressure measurement can be divided into two types: invasive method and non-invasive method. Non-invasive blood pressure measurement includes two form: intermittent blood pressure measurement and continuous blood pressure measurement. Although continuous method is much better than intermittent method with the advantages of real-time monitoring and continuous feature information, the large size of measuring device and contacted form are the main drawbacks. According to the main drawbacks of previously traditional method, a new method based on one-channel pulse signal is very necessary. To my best knowledge, it is the first time that pulse-wave based non-invasive and non-contact continuous blood pressure measurement is proposed. Firstly, a millimetre wave sensor (IWR1443 BOOST) is utilized to detect and measure the pulse-wave of the target person (extracted from the displacement waveform of the chest). Secondly, a mathematical regression model is constructed to predict the continuous blood pressure based on continuous data of pulse-wave. This method is demonstrated on the MIMIC database and self-collected data with standard errors 0.71243 and 1.86232 respectively. Obviously, the error from self-collected data is twice as that from MIMIC database, which is probably caused by the noise and interference while collecting the displacement signal of chest through millimetre wave sensor.