A team of engineers at the University of California San Diego has made a groundbreaking achievement in the field of wireless ultrasound monitoring. They have developed the first fully integrated wearable ultrasound system for deep-tissue monitoring, specifically designed for subjects in motion. This remarkable development has the potential to revolutionize cardiovascular monitoring and has been hailed as a major breakthrough in wearable ultrasound technology.
The research, led by Professor Sheng Xu, is published in the May 22, 2023 issue of Nature Biotechnology. The team's work focuses on creating a wearable sensor that can monitor deep tissues wirelessly. Unlike previous soft ultrasonic sensors that required tethering cables for data and power transmission, this newly developed system includes a small, flexible control circuit that communicates wirelessly with an ultrasound transducer array. The collected data is then interpreted using machine learning algorithms, allowing for real-time tracking of subjects in motion.
The results of the study show that the wearable ultrasound system-on-patch enables continuous tracking of physiological signals from deep tissues, including central blood pressure, heart rate, and cardiac output, for up to twelve hours at a time. It has the ability to evaluate cardiovascular function even during motion, providing valuable insights into exercise intensity and facilitating the formulation of personalized training plans.
Moreover, this integrated wearable ultrasound system represents a significant advancement in the Internet of Medical Things (IoMT). By wirelessly transmitting physiological signals to the cloud, the system allows for efficient computing, analysis, and professional diagnosis. This technology has the potential to transform healthcare monitoring and improve diagnostics.
The team was pleasantly surprised to discover that the system had additional capabilities beyond its original scope. In addition to measuring blood pressure, the wearable ultrasound technology can assess parameters such as cardiac output, arterial stiffness, and expiratory volume. This expansion of functionality makes it a valuable tool for both daily healthcare and in-hospital monitoring.
To address the challenge of relative movement between the wearable sensor and the tissue target during motion, the team developed a machine learning algorithm. This algorithm automatically analyzes received signals and selects the most appropriate channel to track the moving target. Importantly, the algorithm's learning can be transferred from one subject to another, minimizing the need for retraining and ensuring consistent and reliable results across different individuals.
The development of this fully integrated wearable ultrasound system is a significant achievement that paves the way for wireless ultrasound monitoring of subjects in motion. It has the potential to revolutionize cardiovascular monitoring, improve healthcare diagnostics, and advance the field of wearable ultrasound technology.