Stretchy computing device looks like skin and analyzes health data


It’s a smart band-aid, a smartwatch without the watch, and a leap forward in wearable health technology. Researchers at the University of Chicago’s Pritzker School of Molecular Engineering (PME) have developed a flexible and expandable computer chip that processes information by mimicking the human brain. The device, described in the journal Matter, aims to change the way health data is processed.

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

Today, to get a detailed profile of your health, you need to visit a hospital or clinic. In the future, Wang said, people’s health could be tracked continuously by wearable electronic devices that can detect disease even before symptoms appear. Discreet and portable computing devices are a step towards realizing this vision.

A deluge of data

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

Today’s smart phones aren’t capable of performing the kind of complex analysis needed to learn a patient’s basic health metrics and spot important disease signals. However, cutting-edge AI platforms that incorporate machine learning to identify patterns in extremely complex datasets can do a better job. But sending information from a device to a centralized AI location isn’t ideal.

“Sending health data wirelessly is slow and has a number of privacy issues,” he said. “It’s also incredibly energy inefficient; the more data we start collecting, the more energy these transmissions will consume. »

Skin and Brain

Wang’s team set out to design a chip that could collect data from multiple biosensors and draw conclusions about a person’s health using state-of-the-art machine learning approaches. Most of all, they wanted it to be wearable on the body and seamlessly integrate with the skin.

“With a smartwatch, there’s always a gap,” Wang said. “We wanted something that could achieve a very intimate touch and adapt to the movement of the skin.”

Wang and his colleagues turned to polymers, which can be used to make 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. Rather than functioning like a typical computer, the chip, called a neuromorphic computer chip, functions more like a human brain, capable of both storing and analyzing data in an integrated way.

Test the technology

To test the usefulness of their new device, Wang’s group used it to analyze electrocardiogram (ECG) data representing the electrical activity of the human heart. They trained the device to classify ECGs into five categories: healthy signals or four types of abnormal signals. Then they tested it on new ECGs. Whether the chip was stretched or bent or not, they showed that it could accurately classify heartbeats.

More work is needed to test the device’s power to infer patterns of health and disease. But eventually, it could be used either to send alerts to patients or clinicians, or to automatically change medications.

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

It is already planning new iterations of the device to expand both the type of devices it can integrate with and the types of machine learning algorithms it uses.

“The integration of artificial intelligence with wearable electronics is becoming a very active landscape,” Wang said. “It’s not a finished search, it’s just a starting point.”


About Author

Comments are closed.