AI-Powered Wearable Electronics Could Detect Emerging Health Problems

Flexible, wearable electronics are becoming more common, but their full potential has yet to be realized. Ultimately, this technology could be utilized to create precision medical sensors applied to the skin and used to monitor and diagnose health problems.

A skin-like device is being created in a collaboration between the DOE’s Argonne National Laboratory and the University of Chicago’s Pritzker School of Molecular Engineering (PME). Sihong Wang, an assistant professor in UChicago PME with a joint appointment in Argonne’s Nanoscience and Technology division, headed the research.

When worn regularly, future wearable electronics could recognize emergent health risks like heart disease, cancer, or multiple sclerosis even before noticeable symptoms appear. The device might also perform a tailored analysis of the tracked health data, reducing the need for wireless transmission.

The diagnosis for the same health measurements could differ depending on the person’s age, medical history and other factors. Such a diagnosis, with health information being continuously gathered over an extended period, is very data intensive.

Sihong Wang, Assistant Professor, Pritzker School of Molecular Engineering, University of Chicago

Such a device would need to collect and process a vast amount of data, well above what even the best smartwatches can do today. Moreover, it would have to do this data crunching with very low power consumption and within a very tiny space.

To meet that requirement, the researchers turned to neuromorphic computing. This AI system mirrors brain function by training on previous data sets, learning from experience. Its benefits include compatibility with flexible materials, lower energy usage, and higher processing speed than other types of AI.

The team also encountered a significant challenge in incorporating the electronics onto a skin-like stretchy material. A semiconductor is the most important component of any electronic device. This is often a solid silicon chip in today’s rigid electronics, found in cell phones and computers. Stretchable electronics necessitate a semiconductor that is both very flexible and electrically conductible.

The skin-like neuromorphic “chip” developed by the team comprises a thin sheet of a plastic semiconductor mixed with stretchy gold nanowire electrodes. Even when stretched to double its regular size, their technology performed as expected with no breaks.

In one experiment, the researchers created an AI device and programmed it to distinguish between healthy electrocardiogram (ECG) data and four distinct signals signifying health issues. After training, the device was more than 95% accurate at recognizing ECG signals.

The plastic semiconductor was also tested on beamline 8-ID-E at Argonne’s Advanced Photon Source (APS), a DOE Office of Science user facility. The molecules that make up the skin-like device material rearrange after doubling in length, as revealed by exposure to a strong X-ray beam. These findings gave molecular-level information to help researchers better comprehend the material's characteristics.

The planned upgrade of the APS will increase the brightness of its X-ray beams by up to 500 times. We look forward to studying the device material under its regular operating conditions, interacting with charged particles and changing electrical potential in its environment. Instead of a snapshot, we’ll have more of a movie of the structural response of the material at the molecular level.

Joe Strzalka, Physicist, Argonne National Laboratory

The increased beamline brightness and improved detectors will enable measurement of how soft or hard the material gets in response to environmental influences.

While still requiring further development on several fronts, our device could one day be a game changer in which everyone can get their health status in a much more effective and frequent way.

Sihong Wang, Assistant Professor, Pritzker School of Molecular Engineering, University of Chicago

The study was published in the journal Matter.

The research was supported by the US Office of Naval Research, the National Science Foundation, and a start-up fund from the University of Chicago.

Journal Reference:

Dai, S., et al. (2022) Intrinsically stretchable neuromorphic devices for on-body processing of health data with artificial intelligence. Matter. doi.org/10.1016/j.matt.2022.07.016.

Source: https://www.anl.gov/