Scientists at the University of Chicago just created a new skin patch that can act as an instant personal doctor by using the power of artificial intelligence (AI).
Unlike conventional wearables, this patch executes AI calculations within milliseconds – without needing to transfer information over a wireless connection.
The findings, which were published in the peer-reviewed journal Nature Electronics, suggest that instant medical insights and accurate heart monitoring through a high-powered wearable are not far away.
An updated approach to wearables
The problem with conventional wearables is the time lag. Devices such as smartwatches and monitoring rings can track metrics like your heart rate and movement, but the data analysis takes place on external servers.
The delay between recording the information and sending it to the servers can be an issue in situations where instantaneity can save lives.
The patch was made through manufacturing techniques that permit organic electrochemical transistors to be printed onto flexible materials.
“The future that we’re trying to realise is to make wearable and implantable devices smarter,” Sihong Wang, an associate professor of molecular engineering at the Pritzker School of Molecular Engineering at the University of Chicago and co-senior author of the study, told SciTechDaily. “It’s helping people have a personal, instantaneous doctor integrated into their devices.”
Wang and his team have spent years developing the electronics that can flex and move similarly to human skin with the hopes of one day creating intelligent devices that can attach to biological tissue.
Stretchable electronics
Previous studies had found that stretchable electronic components for these wearables were possible – but only with a limited number of transistors. Scaling to a practical system remained a challenge.
The scientists in this study chose organic electrochemical transistors that operate differently from the transistors in conventional computer chips.
These devices process information in an unconventional way – data goes through both electrical currents and the movements of ions within a gel-like electrolyte layer.
Since the electrolyte can retain the information over time, every transistor contains its own memory. This is similar to how brain synapses can strengthen or weaken over time to store learned patterns.
The researchers developed a polymer gel that bypasses the traditional obstacles posed by heat, solvents, and different states of matter. The gel hardens into precise structures when exposed to ultraviolet light and allows up to about 64,500 electrochemical transistors per square inch.
They then used a flexible electronic patch to run a smart, pre-programmed system that helps treat a dangerous type of irregular heartbeat. This condition can cause out-of-control electrical activity in the heart. The treatments currently in place rely on delivering powerful shocks to the entire heart, but now, researchers are proposing a more targeted approach that can track the abnormal waves and apply small, corrective pulses before they spread.
The primary issue here is the speed at which these wavefronts move. Because they’re so fast, analysis needs to occur within milliseconds, so external information processing is impossible.
Using data from a donated human heart, the researchers found that the stretchable array could identify the locations of the waves with 99.6% accuracy.
Implications for the future of health monitoring
Wang told Inc that these findings could, down the road, “enable closed-loop medical devices that require the use of AI to perform real-time analysis of complex sensing data to generate immediate intervention decisions.”
This means the wearables may be able to monitor other conditions too, including neurological disorders, prosthetic-control systems, diabetes care, and sleep-management issues.
Since the device can already perform real-time neural-network analysis using parallel data panels, further development could see product production in the next three to five years. In regards to mass manufacturing, the fabrication process can be scaled up shortly.
“This is actually a major breakthrough enabled by this work,” Wang told Inc. “Through a standard lithography-based fabrication method, mass manufacturing is readily achievable. The rough cost of our current data should be under US$50 (RM203.90).” – Inc/TNS
