Smartwatch Without the Watch: Bendable, Stretchable Chip Can Process Information Like the Human Brain

What's described as a "smartwatch without the watch" is known as "Band-Aid," and a leap ahead for wearable health technologies has recently been developed.

As specified in a EurekAlert! report, scientists at the University of Chicago's Pritzker School of Molecular Engineering have devised a flexible, stretchable computing chip that processes information by emulating the human brain.

This invention aims to change the way health data is processed. According to Sihong Wang, a materials scientist and Molecular Engineering Assistant Professor, with this work, they have bridged wearable technology with artificial intelligence and machine learning to develop a powerful device that can examine health data right on their bodies.

Obtaining an in-depth profile of an individual's health necessitates visiting a clinic or hospital. In the future, explained Wang, people's health could be tracked continuously by wearable devices that can detect diseases even before the appearance of symptoms.

Essentially, hidden, wearable computing electronic devices are a step toward making this vision a reality.

Skin-Like Wearable Biosensors

The future of healthcare that the team, and many other researchers, imagine includes wearable biosensors to follow complex health indicators, including sugar, oxygen, immune molecules, and metabolites in people's blood.

One of the keys to making such sensors possible is their ability to fit onto the skin. As such, skin-like wearable biosensors appear and start collecting more and more information in real-time, and the study turns exponentially more complex.

One piece of data needs to be put into a more expansive perspective of a patient's history and other health parameters.

Today's smartphones "are not capable of the kind of complex analysis" needed to learn the baseline health measurements of a patient and pick out essential indications of diseases.

Cutting-Edge AI

Nonetheless, cutting-edge AI platforms incorporating machine learning to determine patterns in extremely complex datasets can perform better. However, delivering information from a device to a centralized AI site is not ideal.

The professor also explained that sending data wirelessly is slow and demonstrates some privacy concerns. It is incredibly energy efficient, as well. The more data collected, the more energy such transmissions will begin to use.

In the study published in the Matter journal, the team set out to design a chip that could gather data from multiple biosensors and draw conclusions about a person's health using cutting-edge AI approaches. Essentially, the researchers wanted it to be wearable on the body and integrate seamlessly with the skin.

Wang explained that with a smartwatch, there is always a gap. They wanted something that could achieve intimate contact and accommodate the skin's movement.

The Ability to 'Bend' and 'Stretch'

Wang, with his colleagues, turned to polymers that can be used to construct semiconductors and electrochemical but also have the ability to bend and stretch.

The team assembled such polymers into a device that enabled the AI-based analysis of health data. Instead of working like a standard computer, the chip, called a "neuromorphic computer chip," functions more like a human brain that can store and analyze data in an integrated manner.

To test the new device's new ability, Wang's team used it to examine electrocardiogram or ECG data depicting the electrical activity of the human heart, similar Bioengineer.org report said.

They trained the device to categorize ECGs into five classifications: healthy or abnormal signal signs. Then, they had it tested on new ECGs. Whether or not the chip was bent or stretched, they demonstrated, it could accurately classify the heartbeats.

Related information about AI detecting diseases is shown on TED's YouTube video below:

Check out more news and information on Artificial Intelligence in Science Times.