Benjamin Sanchez Terrones started with a question that might sound mundane until you realize its stakes: why do we measure one of the most important markers of our health—blood pressure—only in snapshots, sitting still in a doctor's office, squeezed by an uncomfortable cuff?
The answer has eluded medicine for decades, but now researchers at the University of Utah and University of Illinois Chicago have developed a wearable smartwatch that measures blood pressure and blood flow continuously, without any cuff at all. Published in Nature Communications, their breakthrough combines physics and artificial intelligence to solve what Sanchez Terrones calls the "Holy Grail problem" in cardiovascular monitoring. Elevated blood pressure—the silent killer behind heart attacks, aneurysms, and strokes—finally has a window into continuous tracking.
The technology works through bioimpedance, measuring the electrical properties of blood as it travels through the artery at the wrist. A painless, imperceptible electrical current records tiny fluctuations in how easily electricity flows through blood and tissue, and because blood flow changes with each heartbeat, these electrical signals carry hidden information about underlying pressure. Unlike commercial devices that use light to estimate blood pressure—and often rely on machine learning as a "black box" that's difficult to interpret or clinically trust—this approach is grounded in understood physics.
That distinction matters enormously. Co-author Christel Hohenegger, an associate professor of mathematics at the University of Utah, explains the philosophy: "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." The system harnesses fluid dynamics (how blood flows) and electromagnetism, encoding the physics of pulsating blood and the electromagnetics of the measurement itself. This means the device won't predict something physically impossible—a safeguard that optical approaches lack.
The rigorous testing matters too. Graduate students Henry Crandall, Tyler Schuessler, and Filip Bělík put the device through real-world conditions, testing it on 150 actual people across two environments: intensive care units where patients are critically ill, and the Madsen Health Center, a clinic just off campus in Salt Lake City. By deliberately including both hospital patients and outpatient populations, the team ensured their technology would work on the people who need it most. The device requires no calibration to individual users—it works off the shelf.
Sanchez Terrones offers a vivid analogy to explain what continuous monitoring means: "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." That snapshot is useful, but it captures the least amount of information the human body can provide. A continuous record reveals patterns: how pressure responds to stress, sleep, exercise, medication. It becomes not just a number, but a story.
The University of Utah holds the intellectual property for this physics-informed machine learning technology, and the university's Technology Licensing Office is actively exploring licensing opportunities to bring the device to market. The road from laboratory to clinic has begun, and for millions living with hypertension, the implications are profound: a glimpse into their cardiovascular health not in still frames, but in real time.