New smartwatch tracks blood pressure continuously without a cuff using physics and AI

Smartwatch offers continuous blood pressure monitoring

A new smartwatch developed by researchers at the University of Utah and University of Illinois Chicago promises to transform blood pressure monitoring by eliminating the need for traditional cuffs. The wearable device tracks both blood pressure and blood flow continuously throughout the day, capturing cardiovascular health data during walking, running, sleeping, and other daily activities. Unlike conventional monitors that provide only a single snapshot reading, this technology records blood as a continuous waveform, revealing how pressure changes moment to moment1

1

2

2

.

"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, who developed the technology while at the University of Utah before relocating to the University of Illinois Chicago. The device addresses a critical gap in managing high blood pressure, which affects millions globally and often goes undetected until it causes heart attacks, aneurysms, or strokes.

Electrical bioimpedance replaces traditional cuff technology

The cuffless blood pressure system relies on electrical bioimpedance, a method that measures how electricity flows through blood and tissue. When the heart beats, blood volume in the wrist artery changes, altering electrical conductivity. The smartwatch sends an imperceptible electrical current through the skin—so small users cannot feel it—and sensors detect minute changes in how the wrist responds1

1

.

This approach differs fundamentally from existing wearable devices that use light sensors to estimate blood pressure. Those devices often function as "black boxes," relying on machine learning without clear scientific foundations, making their outputs difficult to interpret and clinically trust. Movement, wrist position, hydration, and individual body differences can compromise their accuracy2

2

.

Extracting meaningful data from the wrist proves challenging because the signal from a single artery must be separated from surrounding skin, fat, muscle, and bone. The researchers solved this problem by building physics directly into their AI model rather than relying solely on pattern recognition1

1

.

Physics-informed machine learning improves accuracy

The research team first created a model based on fluid dynamics and electromagnetism—how blood actually moves through arteries and conducts electricity. They then trained an AI system constrained by these physical principles, ensuring predictions remain scientifically plausible. "This work shows how combining machine learning with physics can fundamentally change what's possible," said Christel Hohenegger, associate professor 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 healthcare"1

1

.

This physics-informed machine learning approach provides the wearable device with a clear scientific foundation, improving reliability across different users and conditions. The system captures complete waveform data rather than just systolic and diastolic values—the familiar top and bottom numbers like 120/80 that represent maximum pressure during heart contraction and minimum pressure between beats2

2

.

Testing validates continuous measurement capabilities

Researchers tested the prototype on 150 people, including 75 healthy volunteers and 85 patients with various conditions. Healthy participants wore the smartwatch while walking, running, cycling, performing controlled breathing exercises, and changing posture. The team compared results against trusted blood pressure tools and ultrasound measurements1

1

.

Patient testing included individuals with high blood pressure, heart disease, and other health conditions, plus three intensive care patients. "We went the extra mile and measured patients in the intensive care unit as well as the Madsen Health Center because we wanted to test the technology on the target population," Sanchez Terrones explained1

1

. Utah graduate students Henry Crandall, Tyler Schuessler, and Filip Bělík conducted the testing across clinical and outpatient settings2

2

.

The system performed better when adjusted for individual users, suggesting future versions may require a personalized setup step before tracking blood pressure effectively.

Path to market and future implications

"Elevated blood pressure is considered the silent killer because it leads to heart attacks, aneurysms and strokes. It represents a global healthcare burden and it is considered a Holy Grail problem," said Sanchez Terrones1

1

. The University of Utah holds intellectual property rights for this technology, and the Technology Licensing Office is exploring licensing opportunities to commercialize the invention2

2

.

The research will appear in Nature Communications, marking a significant step toward clinical adoption. However, larger studies remain necessary to validate performance across diverse ages, body types, and health conditions before the device can replace traditional cuff-based monitors for cardiovascular health management1

1

.