Cuffless models to infer blood pressure from bioimpedance

Measurement of blood pressure (BP) is essential for early diagnosis and management of hypertension, a condition that 45% of US adults have and a risk factor for development of heart failure, the leading cause of death in the US. Worldwide, hypertension is one of the largest public health epidemics. Compared to ambulatory BP measurements, frequent out-of-clinic BP measurements are better predictors of cardiovascular events but, today, existing clinically-accurate technologies to measure BP require costly, uncomfortable, and cumbersome devices that prevent their extended use outside of the clinic.

Given substantial healthcare and mortality burden of heart failure, rising healthcare costs, and the aging population, continued technological improvements to aid heart failure prevention, management, and surveillance are extremely important. The goal of this project is to address this need for an accurate, inexpensive, easy-to use device for continuously monitoring BP through the development of a novel wearable watch built for this purpose.

This new technology will be a game-changer to protect at-risk individuals and effectively manage patients with hypertension proactively across the care continuum and reduce hospitalizations associated with hypertension. This study will also serve as fertile ground to support students in continuing their careers at the intersection of STEM and human oriented research.

One tool that is well-suited for unobtrusive BP monitoring is bioimpedance (BioZ). In BioZ, an imperceptible electrical current is passed through the body to obtain insights into how blood flows through arteries and veins. Here, the Investigators propose to develop new measurement methods rooted with fluid and electricity principles to create a new BioZ sensing technology capable of enabling continuous, cuffless, and convenient BP monitoring.

For this, a novel aspect of the approach taken will be the application of BioZ in conjunction with physiological, computational, and machine learning models to establish the underlying biological sources at the cellular level relating both signals. Once the models have been established and optimized to link BP to BioZ, the prediction accuracy will be evaluated in a cohort of individuals representative of a wide range of body indices and age groups.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.