New AI Wearable Could Replace Risky Arterial Lines For Blood Pressure Monitoring

A team of researchers at Johns Hopkins University has developed a non-invasive monitoring system that uses wearable sensors and artificial intelligence to track arterial blood pressure with a level of precision rivaling the traditional, invasive catheters used in intensive care units.

The new technology, detailed in the journal Computers in Biology and Medicine, could signal a significant shift in clinical care. By replacing arterial lines—catheters that are surgically inserted into a patient’s artery—hospitals may soon be able to eliminate the associated risks of infection, blood clots, and hemorrhaging while allowing for greater patient mobility.

Replacing the invasive standard

In critical care settings, continuous blood pressure monitoring is essential for identifying rapid physiological changes that could lead to organ failure, stroke, or heart attack. Currently, the medical standard involves an arterial line, which provides real-time data but requires invasive insertion into the arm or groin. While highly accurate, the procedure is inherently risky.

“Patients in the ICU need continuous blood pressure monitoring to catch problems early, but it means an arterial line, which comes with a risk of bleeding, clotting, and infection,” explains lead author Carl Harris, a biomedical engineering PhD student at Johns Hopkins.

To overcome these limitations, the researchers developed a system known as MOSAIC. This platform utilizes two sensors: one positioned on the chest and another on the finger. These devices capture the heart’s electrical activity and peripheral blood flow, feeding the raw data into a deep learning model. The AI then synthesizes this information to reconstruct a continuous, real-time waveform of the patient’s blood pressure.

Clinical performance and future implications

In a pilot study involving 28 patients within the Johns Hopkins intensive care unit, the MOSAIC system produced waveforms that closely aligned with those generated by standard invasive catheters. According to senior author Robert Stevens, who serves as chief of the Division of Informatics, Integration, and Innovation at Johns Hopkins Medicine, the system offers a viable, reliable, and non-invasive alternative to current surgical methods.

Beyond the ICU, the research team envisions a future where this technology transforms the management of hypertension. Much like modern continuous glucose monitors have revolutionized diabetes care, these wearable sensors could eventually allow patients with high blood pressure to track their health metrics throughout their daily routines.

“We observe sick patients in the intensive care unit, but we have no idea what’s going on with blood pressure in a healthy person who’s just living their life, going to work and being with their family,” says Stevens. “What happens to their blood pressure day after day? Nobody really knows.”

The research team is now moving forward with validation trials involving a larger cohort of ICU patients. By expanding the data pool, they hope to refine the algorithm and prepare the system for broader clinical application. The project is supported by the Johns Hopkins Institute for Clinical and Translational Research, the National Institutes of Health, and the National Science Foundation.