A wearable smart insole that combines pressure sensing, self-powered operation, and artificial intelligence (AI) analysis may support continuous gait monitoring and detection of lower limb dysfunction, according to a recent study of a bioinspired diagnostic system.
Gait analysis is an important tool for assessing lower extremity function, but current methods are often limited to laboratory settings and short observation periods. This study aimed to develop a wearable device that can monitor gait continuously in real-world conditions.
The system consists of a flexible insole embedded with 16 pressure sensors positioned across the foot. The sensors are designed using a bioinspired structure based on mantis legs, allowing them to detect a wide range of pressures – from very low levels (0.10 Pa) to high forces (1.4 MPa) seen during walking or physical activity. The sensors also showed stability over more than 12,000 cycles, supporting their use in long-term monitoring.
This wide detection range is clinically relevant, as it enables identification of both subtle and more pronounced changes in plantar pressure. The system can detect pressure patterns associated with movement and physiological signals, supporting detailed assessment of gait and balance.
The insole is powered by an integrated energy system combining solar cells and rechargeable batteries, allowing continuous operation without external charging. This supports uninterrupted data collection in both indoor and outdoor environments, which is important for capturing real-life gait patterns.
Data from the sensors are analyzed using embedded AI models. In testing, the system identified foot arch abnormalities with 96 percent accuracy and classified 12 different gait patterns with 97.6 percent accuracy. These included clinically relevant patterns such as limping, shuffling gait, and toe walking. The system was able to distinguish between normal and abnormal gait patterns with clear separation of data.
The findings highlight the potential role of wearable diagnostics in providing continuous, objective data on patient movement. This approach may complement traditional diagnostic methods by identifying early or subtle changes in gait that are not easily captured during clinic-based assessments.
Potential applications include monitoring patients with diabetic neuropathy, osteoarthritis, or neurologic conditions, as well as supporting rehabilitation and remote patient follow-up.
The study has limitations, including validation in controlled and relatively small study settings. Further research is needed to assess performance in larger and more diverse patient populations.
Overall, the study demonstrates that combining high-resolution sensing, self-powered operation, and AI analysis in a wearable device may support more accessible and continuous gait diagnostics.
Newsletters
Receive the latest pathologist news, personalities, education, and career development – weekly to your inbox.
