Related Experiment Video
Updated: Jun 3, 2025
03:55
Author Spotlight: Enhancing Grasping Abilities for Hemiplegic Patients with Flexible Robotic Limbs
Published on: October 27, 2023
2.0K
Bioinspired Smart Triboelectric Soft Pneumatic Actuator-Enabled Hand Rehabilitation Robot
Wei Li1, Feiling Luo2,3, Yuan Liu4
1State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
Advanced Materials (Deerfield Beach, Fla.)
|January 11, 2025
Summary
A novel soft actuator and AI system accurately assess post-stroke finger spasticity. This technology shows high accuracy in clinical trials, offering a promising tool for digital rehabilitation medicine.
Area of Science:
- Biomedical Engineering
- Rehabilitation Technology
- Artificial Intelligence in Medicine
Background:
- Quantitative assessment of post-stroke spasticity is challenging due to subjective measures like the Modified Ashworth Scale (MAS).
- Variable resistance during passive stretching complicates accurate spasticity evaluation, relying heavily on physician expertise.
Purpose of the Study:
- To develop a novel, high-force-output soft actuator for quantitative spasticity assessment.
- To integrate this actuator with a Convolutional Neural Network (CNN) for automated spasticity level classification and MAS score prediction.
Main Methods:
- Development of a bioinspired triboelectric soft pneumatic actuator (TENG-SPA) mimicking a lobster tail.
- Characterization of TENG-SPA performance under various conditions, including simulated spastic finger stretching.
- Clinical trial with 15 stroke patients using the TENG-SPA-enabled robotic system and CNN for spasticity assessment.
Main Results:
- The TENG-SPA demonstrated robust performance, generating sufficient force for finger stretching and sensing resistance.
- The integrated CNN achieved 93.3% classification accuracy for finger spasticity levels.
- CNN regression model predictions for MAS scores showed a strong linear correlation with actual MAS scores (R² = 0.8451, p < 0.01).
Conclusions:
- The TENG-SPA-based system offers an objective and accurate method for quantitative spasticity assessment.
- This technology holds significant potential for advancing digital rehabilitation medicine, human-machine interaction, and biomedicine.
