Researchers at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME) have created a skin-like computing patch that can process health data using artificial intelligence directly on the body. Unlike conventional wearable devices, the patch performs AI calculations in milliseconds without needing to send information over a wireless connection.

Most smartwatches can monitor metrics such as heart rate and movement, but the actual data analysis takes place on external servers. That delay can be problematic in situations where every millisecond matters, such as detecting ventricular fibrillation, a life-threatening heart rhythm disorder.

Developed and tested with researchers at Argonne National Laboratory, the new device was made possible by manufacturing techniques that allow organic electrochemical transistors to be printed onto flexible materials.

“The future that we’re trying to realize is to make wearable and implantable devices smarter,” said Sihong Wang, an associate professor of molecular engineering at UChicago PME and co-senior author of the new study, published in Nature Electronics. “It’s helping people have a personal, instantaneous doctor integrated into their devices.”

Stretchable Neuromorphic Computing for Human Tissues
Wang’s laboratory has spent years developing electronic components that can stretch and flex like human skin, with the goal of creating intelligent devices that can attach directly to biological tissues. Previous achievements included stretchable transistor arrays and a stretchable OLED display.

For this project, the researchers aimed to build a stretchable neuromorphic computing circuit, a large network of transistors capable of analyzing health information. Earlier studies had shown that the idea could work with a limited number of transistors, but scaling it to a practical system remained a challenge.