Issue link: https://iconnect007.uberflip.com/i/1050827
30 PCB007 MAGAZINE I NOVEMBER 2018 A team of researchers led by the University of California San Diego has developed a new wearable ultrasound patch that non-invasive- ly continuously monitors central blood pres- sure (BP) in major arteries as deep as four cen- timeters (more than one inch) deep beneath the skin. This could help people detect cardiovascu- lar problems earlier and with greater precision. In tests, the patch performed as well as some clinical methods to measure BP. Applications include continuous real-time monitoring of changes in BP in patients with heart or lung disease, as well as patients who are critically ill or undergoing surgery. The patch uses ultra - sound, so it could potentially be used to non- invasively track other vital signs and physiolog- ical signals from places deep inside the body. "Wearable devices have so far been limited to sensing signals either on the surface of the skin or right beneath it, but this is like seeing just the tip of the iceberg," said Sheng Xu, a professor of nanoengineering at the UC San Di- ego Jacobs School of Engineering and the cor- responding author of the study, "By integrating ultrasound technology into wearables, we can start to capture a whole lot of other signals, bi- ological events, and activities going on way be- low the surface in a non-invasive manner." Physicians involved with the study say the technology would be useful in various inpa- tient procedures. "This has the potential to be a great addition to cardiovascular medicine," said Dr. Brady Huang, a co-author on the paper and radiologist at UC San Diego Health, "In the operating room, especially in complex cardio- pulmonary procedures, accurate real-time as- sessment of central blood pressure is needed, which is where this device has the potential to supplant traditional methods." Central Blood Pressure Measurement The device measures central BP, which dif- fers from peripheral BP measured with an in- Wearable Ultrasound Patch for Blood Pressure Monitoring ing technology that can accurately predict dis- eases using relatively small and incomplete da- tasets. A set of "teacher" data—from which the AI is to learn—is prepared through annotation— the attachment of meanings of objects—and used to train the object detection system. To develop the current system, the researchers used normal heart images to annotate the cor- rect positions of 18 different parts of the heart and peripheral organs and developed a novel fetal heart screening system that allows the au- tomatic detection of heart abnormalities from ultrasound images. When there are differences between the test and learned data, the system judges that there is an abnormality if the differ- ence is higher than a defined confidence val- ue. The process is quick and can be performed in real time with the results appearing imme- diately on the examination screen. The system can also help harmonize diagnoses among dif- ferent hospitals with varying levels of medical expertise or equipment. The researchers now plan to carry out clini- cal trials at university hospitals in Japan, add- ing a larger number of fetal ultrasound im- ages to allow the AI to learn more, improve the screening accuracy, and expand its target. Implementing this system could help correct medical disparities between regions through the training of examiners or by remote diagno- sis using cloud-based systems. PCB007 Figure 1: Ultrasound patch on a finger.