A team of engineers at the University of California, San Diego has developed the first fully integrated wearable ultrasound system, which can be used for deep tissue monitoring and can also be worn during exercise. This system has promoted the advancement of life-saving cardiovascular monitoring technology, and the related paper was published in the 22nd issue of Nature Biotechnology. This fully integrated autonomous wearable ultrasound patch system (USoP) is based on the research team's previous work on soft ultrasound sensor design, and can wirelessly perceive vital signs of deep tissues. Previously, soft ultrasound sensors required tethered cables to transmit data and power, which greatly limited user mobility. The new system includes a small and flexible control circuit that communicates with an ultrasonic transducer array to collect and transmit data wirelessly. Machine learning components help interpret data and track subjects in motion. According to laboratory data, the ultrasound patch system can continuously track physiological signals of tissues up to 164 millimeters deep, continuously measure blood pressure, heart rate, cardiac output, and other physiological signals for up to 12 hours. Researchers say this technology has great potential in improving and even saving lives. This sensor can evaluate human cardiovascular function during exercise. When people are resting or exercising, the outlier of blood pressure and cardiac output are signs of heart failure. For healthy individuals, the new device can measure the cardiovascular response during exercise in real-time, providing insight into each individual's actual exercise intensity and developing personalized training plans. USoP also represents a breakthrough in the development of the medical Internet of Things, which involves wireless transmission of physiological signals to the cloud for calculation, analysis, and professional diagnosis. In addition, when the wearer moves, relative motion occurs between the wearable ultrasonic sensor and the target. The team developed a machine learning algorithm to automatically analyze received signals and select the most suitable channel to track moving targets without the need for frequent manual adjustments. (New News Agency)