Cuffless Wearable Enables Continuous Blood Pressure Monitoring for Hypertension Care

These snapshots miss rapid physiologic changes during activity and recovery, limiting timely interventions in hospital and outpatient settings. Comfortable, continuous monitoring could improve therapy titration and risk assessment. To help address this challenge, researchers have developed a cuffless wearable that measures blood pressure and blood flow continuously using physics‑guided artificial intelligence.

The device was created by an interdisciplinary team at the University of Utah and the University of Illinois Chicago. It is implemented as a smartwatch‑style wearable and was detailed in study published in Nature Communications. The University of Utah holds the intellectual property and its Technology Licensing Office is exploring commercialization pathways.

The system uses bioimpedance, the electrical impedance of blood and tissue, rather than optical signals. A painless, imperceptible electrical current is applied at the wrist, and tiny changes in current flow caused by pulsatile blood are recorded. Those signals are processed by physics‑informed machine learning models that embed fluid dynamics and electromagnetism, guiding the algorithm toward physiologically plausible predictions.

By encoding the physics of pulsating blood and the electromagnetics of bioimpedance into the model, the network avoids “black‑box” behavior seen in some optical wearables. It reconstructs the full blood pressure waveform over time, capturing changes during rest and activity instead of only systolic and diastolic values. The approach is described as not requiring per‑user calibration and is designed for continuous cardiovascular tracking.

Validation included testing on 150 people, spanning intensive care unit patients and outpatients at the Madsen Health Center. According to the team, the goal was to study performance in target clinical populations and typical ambulatory settings. The work highlights potential utility for hospital monitoring where frequent, motion‑tolerant measurements are needed.

"This work shows how combining machine learning with physics can fundamentally change what's possible," said Christel Hohenegger, associate professor of mathematics at the University of Utah. "By building physical principles directly into the model, we can move beyond black-box prediction toward systems that are more accurate, more interpretable, and more broadly applicable in real-world health care."

"Our blood pressure throughout the day is like a movie, but when you put on the cuff, all you get is one snapshot of the picture,"  said Benjamin Sanchez Terrones, associate professor of electrical and computer engineering and biomedical engineering at the University of Illinois Chicago.

"The cuff device is very useful, but at the same time, limited: it only gives you the least amount of useful information because of the way the technology works: systolic readout over diastolic readout, which translates to the maximum and minimum pressure value during the recording. At the end, we are missing 99% of the movie that explains how blood pressure might change in a patient throughout the day while they are walking, running or climbing up stairs," said Sanchez Terrones.

Related Links
University of Utah 
University of Illinois Chicago