Researchers at Johns Hopkins University have developed a system called MOSAIC that uses wearable sensors and artificial intelligence to monitor arterial blood pressure. Tested on 28 intensive care patients, the technology generates waveforms, offering a potential alternative to traditional arterial catheters.
Intensive care units rely on continuous blood pressure monitoring to protect critically ill patients from dangerous blood pressure extremes. If it’s too high, that can lead to stroke, heart attacks, and kidney damage. Too low might mean not enough blood getting to the brain and vital organs. An arterial line—constituting a catheter placed directly into an artery, usually located in the groin or arm, to deliver real-time, uninterrupted pressure tracking—serves as the present benchmark for continuous blood pressure assessment. The procedure works very well, but comes with a risk of bleeding, clotting, and infection. It also limits mobility.
Traditional arm-wrapped blood pressure cuffs avoid invasiveness, yet they only supply periodic measurements. To bridge this gap, a team at Johns Hopkins created a system called MOSAIC. The system utilizes a dual-sensor architecture: one sensor placed on a patient’s chest, and the other on a finger. By combining signals that track the body’s blood flow alongside the heart’s electrical rhythms, these devices feed data into a deep learning model to produce a continuous blood pressure waveform over time.
“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. The findings are published in the journal Computers in Biology and Medicine.
Evaluating Performance
To validate the MOSAIC system, the research team conducted an initial study of 28 patients in the intensive care unit at Johns Hopkins Hospital. During the study, the system generated waveforms that closely matched those recorded by traditional arterial catheters. “We’re very close to hitting that gold standard,” Harris notes.
“We reconstruct waveform data in a way that’s meaningful, accurate, reliable and, most importantly, non-invasive,” explains senior author Robert Stevens, chief of the Division of Informatics, Integration, and Innovation at Johns Hopkins Medicine. Building upon these preliminary findings, researchers are currently testing the algorithm and sensors on a larger group of intensive care patients at Johns Hopkins.
Looking beyond critical care environments, investigators anticipate that this technology could minimize reliance on invasive gear while enabling continuous blood pressure tracking in diverse settings, including standard hospital units and residential homes. Individuals suffering from hypertension—recognized as one of the most widespread and fatal conditions globally—might utilize these wearable sensors daily to monitor their blood pressure, according to the team’s vision. Ultimately, they hope the sensors will transform hypertension management for millions, mirroring the impact continuous glucose monitors had for diabetes patients.
In Plain English: The Clinical Takeaway
- What MOSAIC does: It combines a chest sensor and a finger sensor with artificial intelligence to track blood pressure continuously.
- Why it matters for ICUs: Traditional arterial lines carry risks of infection, bleeding, and blood clots. This method aims to provide an alternative.
- Future applications: Researchers hope the technology will eventually allow people with hypertension to monitor their blood pressure continuously.
Furthermore, deploying these sensors on healthy populations could offer valuable perspectives regarding everyday blood pressure variations and patterns during routine 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.”
Comparative Overview of Blood Pressure Monitoring Modalities
| Monitoring Modality | Invasiveness | Temporal Resolution | Primary Clinical Risks |
|---|---|---|---|
| Arterial Catheter | Invasive (Catheter inserted into an artery) | Continuous, real-time | Bleeding, clotting, infection, limited mobility |
| Standard Sphygmomanometer Cuff | Non-invasive | Intermittent | None |
| MOSAIC Sensor System | Non-invasive (Chest and finger sensors) | Continuous | Not specified |
Funding for this research was provided by the Johns Hopkins Institute for Clinical and Translational Research via the National Institutes of Health’s National Center for Advancing Translational Sciences and the NIH Roadmap for Medical Research, alongside a Graduate Research Fellowship from the National Science Foundation.
References
- Johns Hopkins University
- Computers in Biology and Medicine
Disclaimer: This article is for informational purposes only.
