Smart insoles could detect disease, correct posture in real time

Smart insoles could detect disease: ©David Pereiras - stock.adobe.com

A new smart insole system developed by researchers at The Ohio State University could revolutionize how people monitor their health by analyzing how they walk.

Using 22 miniature pressure sensors embedded in the insole and powered by tiny solar panels mounted on shoes, the device captures detailed biomechanical data as a person moves. That information is transmitted via Bluetooth to a smartphone for instant analysis—offering a glimpse into a person’s health with each step they take.

“Our bodies carry lots of useful information that we’re not even aware of,” said Jinghua Li, assistant professor of materials science and engineering at Ohio State and co-author of the study. “These statuses also change over time, so it’s our goal to use electronics to extract and decode those signals to encourage better self-health care checks.”

The smart insole, described in the journal Science Advances, stands out for its ability to analyze motion with high precision while powering itself through light exposure. Designed to be flexible, safe, and unobtrusive—similar to a smartwatch—it offers continuous monitoring without disrupting daily activities.

Li and lead author Qi Wang, a PhD student at Ohio State, designed the device to overcome the limitations of earlier attempts at wearable gait sensors, many of which suffered from inconsistent power sources and poor data quality.

“Our device is innovative in terms of high resolution, spatial sensing, self-powering capability, and its ability to combine with machine learning algorithms,” Li said. “So we feel like this research can go further based on the pioneering successes of this field.”

Using advanced machine learning models, the insole can detect and classify eight different motion states, including sitting, standing, running, and squatting. It can distinguish subtle differences in gait, such as how foot pressure is distributed differently when walking versus running—data that may one day be used to flag early signs of conditions such as plantar fasciitis, diabetic foot ulcers, or Parkinson’s disease.

The device also held up under pressure—literally. After 180,000 cycles of compression and decompression, researchers observed no performance decline. “The interface is flexible and quite thin, so even during repetitive deformation, it can remain functional,” said Li.

The team expects the technology could reach consumers in the next three to five years. Further development will focus on enhancing gesture recognition and testing on a broader population to improve its accuracy and applicability.

“We have so many variations among individuals,” said Li, “so demonstrating and training these fantastic capabilities on different populations is something we need to give further attention to.”