AI-Powered Wearable Sensors Offer Non-Invasive Blood Pressure Monitoring
Wearable sensors paired with artificial intelligence can generate blood pressure readings nearly as well as the invasive arterial lines traditionally relied upon in intensive care units, according to research published in Computers in Biology and Medicine. Developed by a team at Johns Hopkins University, the newly tested system offers a non-invasive alternative that could expand continuous hemodynamic monitoring beyond high-acuity hospital settings.
- The system, named MOSAIC, uses a chest sensor and a finger sensor to track heart electrical activity and blood flow without catheter insertion.
- In an initial study of 28 intensive care unit patients at Johns Hopkins Hospital, the technology produced continuous waveforms that closely matched standard arterial catheters.
- Researchers plan to validate the sensors in a larger patient cohort, with a long-term goal of enabling continuous blood pressure tracking for individuals managing hypertension outside the hospital.
The Clinical Need for Continuous Monitoring Alternatives
Patients admitted to intensive care environments often experience rapid, volatile fluctuations in blood pressure. Sustained hypertension can trigger strokes, heart attacks, and kidney damage, while severe hypotension deprives vital organs of necessary perfusion. To manage these risks, clinicians rely on arterial lines—catheters threaded directly into an artery in the arm or groin. While these lines supply real-time pressure data, they introduce substantial clinical risks, including clotting, bleeding, and infection, alongside restricting patient mobility.
“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,” says lead author Carl Harris, a PhD student in biomedical engineering at Johns Hopkins University, in the published findings. “We wanted to find a better way.” Traditional upper-arm cuff inflations avoid trauma but only provide intermittent snapshots, leaving critical diagnostic gaps between measurements.
How the MOSAIC Sensor System Works
To bridge the gap between continuous risk and intermittent measurement, the Johns Hopkins investigators engineered the MOSAIC system. The technology relies on a dual-sensor architecture: one sensor rests on the patient’s chest to record cardiac electrical signals, while a second sensor on the finger tracks peripheral blood flow dynamics. These synchronized physiological streams feed into a deep-learning algorithm that translates the data into a continuous pressure waveform.
“We reconstruct waveform data in a way that’s meaningful, accurate, reliable and, most importantly, non-invasive,” states senior author Robert Stevens, chief of the Division of Informatics, Integration, and Innovation at Johns Hopkins Medicine. “It’s a possible solution for avoiding the current standard of care for measuring blood pressure, arterial lines, a very invasive procedure with a risk of many complications.” In the initial trial involving 28 intensive care patients, the algorithm successfully mirrored the accuracy of indwelling catheters. “We’re very close to hitting that gold standard,” Harris notes. “This demonstrates we can do what we set out to do—and pretty well.”
Expanding Research and Future Ambulatory Applications
Following the completion of the 28-patient pilot trial, the research team is expanding validation efforts across a larger cohort within Johns Hopkins Hospital intensive care units.
Beyond the ICU, investigators envision a paradigm shift for chronic disease management. Hypertension affects millions globally, yet current outpatient tracking relies on single-point office visits or home cuffs. By adapting wearable sensors for daily use—drawing a conceptual parallel to continuous glucose monitors utilized in diabetes care—clinicians might gain continuous visibility into vascular trends. Furthermore, deploying sensors in healthy populations could illuminate baseline physiological fluctuations during daily activities. “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,” Stevens observes. “What happens to their blood pressure day after day? Nobody really knows.”
The underlying research received financial support from the Johns Hopkins Institute for Clinical and Translational Research, backed by the National Institutes of Health’s National Center for Advancing Translational Sciences, the NIH Roadmap for Medical Research, and a National Science Foundation Graduate Research Fellowship.
*Disclaimer: The information provided in this article is for educational and scientific communication purposes only and does not constitute medical advice. Always consult with a qualified healthcare provider regarding any medical condition, diagnosis, or treatment plan.*