Related Experiment Video
Updated: Jun 17, 2025
08:58
Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis
Published on: July 7, 2023
265
Distributed Wearable Ultrasound Sensors Predict Isometric Ground Reaction Force
Erica L King1,2,3, Shriniwas Patwardhan1,2,4, Ahmed Bashatah1
1Department of Bioengineering, George Mason University, Fairfax, VA 22030, USA.
Sensors (Basel, Switzerland)
|August 10, 2024
Summary
A new wearable ultrasound device (SMART-US) accurately predicts muscle force during squats. This technology shows promise for rehabilitation by monitoring muscle activation and force production in real-time.
Area of Science:
- Biomedical Engineering
- Musculoskeletal Rehabilitation
- Wearable Technology
Background:
- Rehabilitation from musculoskeletal injuries requires precise monitoring of muscle activation and force production.
- Traditional methods for assessing muscle function can be cumbersome and lack real-time feedback.
- Wearable technology offers potential for unobtrusive, continuous monitoring of physiological parameters.
Purpose of the Study:
- To evaluate a novel wearable device, Simultaneous Musculoskeletal Assessment with Real-Time Ultrasound (SMART-US), for predicting force during isometric squats.
- To compare the predictive performance of the distributed SMART-US system against single-sensor SMART-US configurations and clinical ultrasound.
- To demonstrate the feasibility of using wearable ultrasound for estimating ground reaction force.
Main Methods:
- Five participants performed maximum isometric squats.
- Muscle activation was assessed using clinical musculoskeletal motion mode (m-mode) ultrasound and a distributed SMART-US system with sensors on multiple leg muscles.
- Ultrasound features were extracted and used with a linear ridge regression model to predict ground reaction force.
Main Results:
- The distributed SMART-US model achieved a high predictive accuracy (R² = 0.80 ± 0.04) during model validation.
- The distributed SMART-US model's performance was significantly better than single-sensor SMART-US configurations.
- The distributed SMART-US model's predictive performance was comparable to the clinical m-mode ultrasound.
Conclusions:
- A novel wearable distributed SMART-US system can effectively predict ground reaction force using machine learning.
- This technology demonstrates the feasibility of wearable ultrasound imaging for real-time force estimation in musculoskeletal rehabilitation.
- The findings support the potential of SMART-US for enhancing the assessment and monitoring of muscle function during recovery from injuries.
