Cuff-less Estimation of Blood Pressure from Vibrational Cardiography Using a Convolutional Neural Network

Abstract

Wearable monitoring is important for the diagnosis, prevention, and treatment of cardiovascular diseases and overall cardiac health. A key indicator, Blood pressure (BP), currently relies on cuff-based devices for measurement that are cumbersome for ambulatory monitoring scenarios. Vibrational cardiography (VCG) is an unobtrusive, non-invasive tool which records cardiac vibrations on the surface of the chest. This work proposes using VCG in a novel method to estimate BP from a single point of contact. VCG was recorded by an inertial measurement unit on the xiphoid process of 62 subjects. A convolutional neural network was trained on the VCG waveforms to estimate systolic and diastolic BP. This resulted in an r-squared correlation coefficient of 0.86 and 0.89 and a mean-absolute-error of 3.4 mmHg and 2.2 mmHg for systolic and diastolic BP, respectively. Therefore, this work shows the applicability of using exclusively VCG for BP estimation. It affirms the value of VCG as an all-purpose health monitor, while also improving on the current techniques for continuous BP monitoring. This indicates the potential of VCG in many forms of wearable monitoring including remote healthcare, fitness, and wellness monitoring.