This All-In-One Wearable Ultrasound Can Monitor You As You Walk, Run, and Even Cycle

Operating for up to 12 hours per charge, this fully-wearable ultrasonic sensor can peer deep beneath your skin even while you exercise.

Researchers from the University of California San Diego, Massachusetts Institute of Technology, Yale University, and Stanford University have developed what they claim to be the world's first full-integrated wearable ultrasound system — designed to capture images of deep tissue while the wearer is walking, running, or even cycling.

"This project gives a complete solution to wearable ultrasound technology — not only the wearable sensor, but also the control electronics are made in wearable form factors," explains first author Muyang Lin, Ph.D. candidate in the Department of Nanoengineering at UC San Diego and the study's first author. "We made a truly wearable device that can sense deep tissue vital signs wirelessly."

While other projects have worked to create a functional ultrasonic sensor from soft and flexible electronics, including teams under nanoengineering professor Shen Xu, corresponding author of this latest work, they have all required the user to be tethered to a monitoring and recording system. The fully-integrated version described in this latest study, though, is wholly wearable and wireless — allowing continuous ultrasound monitoring of deep tissue even during physical activity, running for up to 12 hours on a charge.

"This technology has lots of potential to save and improve lives," says Lin. "The sensor can evaluate cardiovascular function in motion. Abnormal values of blood pressure and cardiac output, at rest or during exercise, are hallmarks of heart failure. For healthy populations, our device can measure cardiovascular responses to exercise in real time and thus provide insights into the actual workout intensity exerted by each person, which can guide the formulation of personalized training plans."

“At the very beginning of this project, we aimed to build a wireless blood pressure sensor. Later on, as we were making the circuit, designing the algorithm and collecting clinical insights, we figured that this system could measure many more critical physiological parameters than blood pressure, such as cardiac output, arterial stiffness, expiratory volume and more, all of which are essential parameters for daily health care or in-hospital monitoring."

To compensate for movement of the sensor during physical activity, the team developed a machine learning algorithm which could analyze incoming signals and automatically switch between channels to keep the sensor on-target. This proved a challenge: training the algorithm on data captured from one subject isn't necessarily directly transferable to another, resulting in below-average performance without long-winded manual training on each user.

"We eventually made the machine learning model generalization work by applying an advanced adaptation algorithm," explains co-first author Ziyang Zhang of the team's solution. "This algorithm can automatically minimize the domain distribution discrepancies between different subjects, which means the machine intelligence can be transferred from subject to subject. We can train the algorithm on one subject and apply it to many other new subjects with minimal retraining."

In testing, the wearable proved effective even while its user was cycling at speed down the street. (📹: Lin et al)

The team tested the device on what co-first author Xiaoxiang Gao calls "a small but diverse population," finding it capable of capturing data from tissues as deep as 164mm (around 6.45") beneath the skin and of accurately recording central blood pressure, heart rate, and cardiac output while its users were engaged in a range of activities — the most impressive, perhaps, being cycling at speed, something impossible with the sensor's tethered predecessors.

The researchers' work has been published in the journal Nature Biotechnology under closed-access terms. The deep learning model used in the project, meanwhile, is available on GitHub under the permissive MIT license.

Main article image courtesy of Muyang Lin.

Gareth Halfacree
Freelance journalist, technical author, hacker, tinkerer, erstwhile sysadmin. For hire: freelance@halfacree.co.uk.
Latest articles
Sponsored articles
Related articles
Latest articles
Read more
Related articles