Researchers at the University of Arizona's Gutorf Lab have developed a comfortable, easy-to-use wearable device that incorporates artificial intelligence to detect subtle warning signs of frailty. This represents a leap forward in elderly care.
“Current treatment models are falling behind,” said Philipp Gutolf, associate chair of the Department of Biomedical Engineering and senior author of the study. “Currently, we often wait for a fall or hospitalization before assessing a patient's frailty. We wanted to shift the paradigm from being reactive to being proactive.”
The project's research, published Dec. 20 in Nature Communications, introduces a soft mesh sleeve worn around the lower thigh that monitors and analyzes leg acceleration, symmetry, and stride length variation.
A 2015 study published in the Journals of Gerontology found that frailty, which is associated with an increased likelihood of falls, disability, and hospitalization, affects 15% of U.S. residents over the age of 65.
“This device allows clinicians to intervene earlier, potentially preventing costly and dangerous outcomes,” Gutruf said.
Form and function define design
This easy-to-use wearable incorporates long-range wireless charging, freeing users from plug-ins.
Associate Professor I have spent the past seven years at U of A developing technology to monitor biomarkers. His lab published research in May on an adhesive-free wearable that measures water vapor and skin gases to track signs of stress.
Applying and extending that technology, the 3D-printed sleeve, about 2 inches wide, lined with tiny sensors is “designed to be invisible,” Gutolf said.
The sleeve simultaneously records and analyzes the wearer's movements and generates AI analysis. The device only sends the results, not the actual hundreds of hours of recorded data, reducing transmissions by 99% and eliminating the need for high-speed internet. Results are transferred to your smart device via Bluetooth. The long-range wireless charging feature also eliminates the need for users to connect devices or replace batteries.
“Continuous, high-fidelity monitoring creates large datasets that typically drain batteries in hours and require extensive internet connectivity to upload. We solved this with Edge AI,” said Kevin Kasper, lead study author and PhD candidate in biomedical engineering.
He added that AI-enabled technology is an “ideal solution for remote patient monitoring in rural and under-resourced communities.”
“We are effectively providing testing to patients, regardless of where they live.”
