| Jul 07, 2025 |
Boron nitride nanotubes power precise knee motion tracking in wearable device
A new wearable uses boron nitride nanotubes and AI to monitor knee torque in real time, offering accurate, low-cost joint health tracking in daily environments.
(Nanowerk News) A research team from the University of Oxford and University College London has developed a wearable device that can track joint torque with precision, potentially transforming the way clinicians and patients monitor joint health.
|
|
Reported in Nano-Micro Letters ("AI-Enabled Piezoelectric Wearable for Joint Torque Monitoring"), the new technology integrates advanced materials and artificial intelligence to provide real-time data from everyday movements.
|
|
The device relies on boron nitride nanotubes (BNNTs) embedded in a soft polymer called polydimethylsiloxane (PDMS). These nanotubes possess exceptional mechanical strength and piezoelectric properties, meaning they generate electrical signals in response to movement or pressure. When worn on the knee, the composite material responds to joint motion by producing signals that can be interpreted to measure torque—the rotational force exerted on the joint.
|
 |
| Schematic illustration of AI-assisted knee joint monitoring. a Design, synthesis, fabrication, and integration of BNNT/PDMS-based flexible sensors for ergonomic knee adaptation and sensitive dynamic motion capture. b AI-assisted estimation of joint injury risk based on dynamic joint signals. (Image: Reprinted from DOI:10.1007/s40820-025-01753-w, CC BY) (click on image to enlarge)
|
|
Traditional tools for measuring joint torque often require bulky lab setups or are limited to clinical environments. This wearable, in contrast, is lightweight, portable, and can operate continuously outside the lab. Its design includes an inverse-structured material with a negative Poisson’s ratio, allowing it to better match the movement dynamics of the knee and maintain close contact during activity. This helps ensure that the data captured remains consistent and accurate under a range of conditions.
|
|
The signals from the piezoelectric film are processed in real time by a neural network embedded in the device. This AI algorithm interprets the complex data to estimate joint torque, angle, and load. The result is a detailed picture of how the joint behaves during motion—information that can be critical in managing musculoskeletal conditions, guiding rehabilitation programs, and preventing injuries.
|
|
Because the materials are low-cost and compatible with low-power electronics, the device has strong potential for use in a wide range of settings, including resource-limited environments. The researchers suggest it could be especially useful for elderly users, patients recovering from injury, and athletes looking to monitor joint performance or reduce injury risk.
|
|
Looking ahead, the team plans to refine the materials and algorithms to improve accuracy and adaptability. Future versions may integrate with wearable robotics or exoskeletons, expanding the device’s role in movement assistance and therapeutic applications.
|
|
By combining advanced sensing materials with real-time AI processing, this new wearable marks a step forward in making joint health monitoring more accessible, affordable, and effective outside the clinical setting.
|
