Abstract
Continuous monitoring of blood pressure (BP) is essential for the prediction and the prevention of cardiovascular diseases. Cuffless BP methods based on non-invasive sensors integrated into wearable devices can translate blood pulsatile activity into continuous BP data. However, local blood pulsatile sensors from wearable devices suffer from inaccurate pulsatile activity measurement based on superficial capillaries, large form-factor devices and BP variation with sensor location which degrade the accuracy of BP estimation and the device wearability. This study presents a cuffless BP monitoring method based on a novel bio-impedance (Bio-Z) sensor array built in a flexible wristband with small-form factor that provides a robust blood pulsatile sensing and BP estimation without calibration methods for the sensing location. We use a convolutional neural network (CNN) autoencoder that reconstructs an accurate estimate of the arterial pulse signal independent of sensing location from a group of six Bio-Z sensors within the sensor array. We rely on an Adaptive Boosting regression model which maps the features of the estimated arterial pulse signal to systolic and diastolic BP readings. BP was accurately estimated with average error and correlation coefficient of 0.5 ± 5.0 mmHg and 0.80 for diastolic BP, and 0.2 ± 6.5 mmHg and 0.79 for systolic BP, respectively.
Highlights
The proposed method for cuffless blood pressure (BP) measurements from a wrist-worn device rely on using small-form factor of non-invasive sensors that measure blood pulsatile activity from the arteries and transform them into BP models using regression models
We propose a new wrist-worn method for cuffless BP monitoring based on bio-impedance (BioZ) sensors that monitor the pulsatile activity of the wrist arteries with high accuracy and reliability to provide high fidelity BP estimation
For the proposed method with leave one trial out cross validation, the diastolic BP (DBP) and systolic BP (SBP) error distribution for the three BP error ranges under the thresholds 5 mmHg, 10 mmHg and 15 mmHg are 69%, 94% and 99% for DBP and 60%, 86% and 96% for SBP. These results show that the BP performance is consistent with grade A for both DBP and SBP according to the British Hypertension Society (BHS) s tandard[22] (See Table S6)
Summary
The proposed method for cuffless BP measurements from a wrist-worn device rely on using small-form factor of non-invasive sensors that measure blood pulsatile activity from the arteries and transform them into BP models using regression models. The change of sensing location away from the artery results in changes in pulse signal morphology and BP results These changes are significant for the small-form factor sensors that are integrated into a wrist-worn device because they suffer from frequent position displacements on the wrist due to user movements of the arm and when the user takes off the device and re-attaches it to the wrist at a different location. The autoencoder is an unsupervised machine learning algorithm that finds the lower-dimension representation of the high-dimension input signals This method provides accurate pulsatile activity of the artery independent of the sensing location which improves the BP estimation at different locations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
