Stretchy computing device feels like skin – but analyzes health data with artificial intelligence that mimics the brain – EurekAlert | Hot Mobile Press

UChicago Asst.  Prof. Sihong Wang wearable neuromorphic

Image: The wearable neuromorphic chip made of stretchable semiconductors can implement artificial intelligence (AI) to process massive amounts of health information in real time. top asst Prof. Sihong Wang shows a single neuromorphic device with three electrodes.
outlook more

Credit: Photo by John Zick

It’s a smart patch, a smartwatch without a watch, and a leap forward for wearable health tech. Researchers at the University of Chicago’s Pritzker School of Molecular Engineering (PME) have developed a flexible, stretchable computer chip that processes information by mimicking the human brain. The device described in the magazine matteraims to change the way health data is processed.

“With this work, we have bridged wearable technology with artificial intelligence and machine learning to create a powerful device that can analyze health data directly on our own bodies,” said Sihong Wang, materials scientist and assistant professor of molecular engineering.

Today, a visit to a hospital or clinic is required to get a detailed profile of your health. In the future, Wang said, people’s health could be continuously tracked by wearable electronics that can detect diseases even before symptoms appear. Unobtrusive, wearable computing devices are a step towards making this vision a reality.

A flood of data
The future of healthcare Wang – and many others – envision includes wearable biosensors to track complex indicators of health, including oxygen, sugar, metabolite and immune molecules in people’s blood. One of the keys to the viability of these sensors is their ability to conform to the skin. As such skin-like wearable biosensors emerge and begin to collect more and more information in real time, analysis becomes exponentially more complex. A single piece of data needs to be placed in the broader perspective of medical history and other health parameters.

Today’s smartphones are unable to perform the type of complex analysis required to learn a patient’s basic health metrics and identify key disease signals. However, cutting-edge artificial intelligence platforms that integrate machine learning to recognize patterns in extremely complex data sets can do a better job. However, sending information from one device to a central AI location is not ideal.

“Sending health data wirelessly is slow and raises a number of privacy concerns,” he said. “It’s also incredibly energy inefficient; The more data we collect, the more energy these transmissions will consume.”

skin and brain
Wang’s team set out to create a chip that could collect data from multiple biosensors and use cutting-edge machine learning approaches to draw inferences about a person’s health. It was important to them that it could be worn on the body and fit seamlessly into the skin.

“With a smartwatch, there’s always a gap,” Wang said. “We wanted something that could make very close contact and accommodate the movement of the skin.”

Wang and his colleagues turned their attention to polymers, which can be used to build semiconductors and electrochemical transistors, but also have the ability to stretch and bend. They assembled polymers into a device that enabled artificial intelligence-based analysis of health data. Instead of working like a typical computer, the chip — called a neuromorphic computer chip — works more like a human brain, capable of storing and analyzing data in an integrated way.

testing the technology
To test the usefulness of their new device, Wang’s group used it to analyze electrocardiogram (ECG) data, which depicts the electrical activity of the human heart. They trained the device to classify EKGs into five categories – healthy signals or four types of abnormal signals. Then they tested it on new EKGs. Regardless of whether the chip was stretched or bent, they showed that it could accurately classify heartbeats.

Further work is needed to test the device’s ability to infer health and disease patterns. But eventually, it could be used to send alerts to either patients or doctors, or to automatically optimize medications.

“For example, if you can get real-time information about blood pressure, this device could decide very intelligently when to adjust the patient’s blood pressure medication,” Wang said. This type of automatic feedback loop is already used by some implantable insulin pumps, he added.

He’s already planning new iterations of the device to expand both the types of devices it can integrate with and the types of machine learning algorithms used.

“Integrating artificial intelligence into wearable electronics is becoming a very active landscape,” Wang said. “This isn’t finished research, it’s just a start.”


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of the press releases published on EurekAlert! by contributing institutions or for the use of information about the EurekAlert system.

Leave a Comment