Tracking vital signs, such as heart rate, blood pressure, and cardiac output, requires precise and continuous measurements. A new ultrasound breakthrough could ensure effective cardiovascular monitoring and improve healthcare outcomes.
Researchers at the University of California San Diego have developed a wearable ultrasonic sensor system that overcomes the challenges of limited sensors in healthcare practice. Published on Nature Biotechnology, the team’s work presents an innovative solution for wireless and autonomous vital sign sensing.
Led by Professor Sheng Xu from the UC San Diego Jacobs School of Engineering, the team created a fully integrated wearable ultrasonic system-on-patch (USoP) that overcomes the limitations of previous soft ultrasonic sensors. Earlier developments required tethering cables for data and power transmission, thus limiting mobility.
The newly-found system has a small, flexible control circuit with an ultrasound transducer array that enables wireless data collection and transmission. In addition, it’s integrated with a machine learning component to interpret the data and track subjects in motion.
With this advanced USoP technology, tracking vital signs from tissues can extend as deep as 164mm, allowing for continuous monitoring. It enables real-time measurements of essential parameters such as central blood pressure, heart rate, cardiac output, and other vital signs, all for up to twelve hours.
The breakthrough USoP technology has life-saving potential and improves healthcare outcomes. By evaluating cardiovascular function during movement, the sensor detects abnormalities in blood pressure and cardiac output, serving as an early indicator of heart failure. It also measures cardiovascular responses to exercise, offering insights into individual workout intensity and personalized training plans.
The new development in the Internet of Medical Things (IoMT) has opened up exciting possibilities for healthcare providers. It wirelessly connects medical devices, transmitting physiological signals to the cloud for analysis, computing, and professional diagnosis. This integration enhances remote patient monitoring, personalized healthcare, reducing costs, and more.
To address the challenge of maintaining accurate measurements during motion, the research team developed a machine-learning algorithm. It automatically analyzes received signals and selects the appropriate channel to track the moving target, reducing manual readjustment.
An advanced adaptation algorithm ensures the model’s generalization across different subjects, making it reliable and transferable.
The wearable ultrasonic sensor system will undergo testing with larger populations and be commercialized by Softsonics, LLC. This company aims to bring this groundbreaking technology to market, as its potential to enhance cardiovascular monitoring and transform healthcare is remarkable.
Source: UC San Diego
Photo by Muyang Lin for the Jacobs School of Engineering at UC San Diego.