Abstract
Sit-to-stand (STS) motion is an important daily activity and many post-stroke patients have difficulty in performing the STS motion. Post-stroke patients who can perform STS independently, still utilize four muscle synergies (synchronized muscle activation) as seen in healthy people. In addition, temporal muscle synergy features can reflect motor impairment of post-stroke patients. However, it has been unclear whether post-stroke patients improve their STS movements in short-term rehabilitation and which muscle synergy features can estimate this improvement. Here, we demonstrate that temporal features of muscle synergies which contribute to body extension and balance maintenance can estimate the effect of short-term rehabilitation based on machine learning methods. By analyzing muscle synergies of post-stroke patients (n = 33) before and with the intervention of physical therapists, we found that about half of the patients who were severely impaired, improved activation timing of muscle synergy to raise the hip with the intervention. Additionally, we identified the temporal features that can estimate whether severely impaired post-stroke patients improve. We conclude that temporal features of muscle synergies can estimate the motor recovery in short-term rehabilitation of post-stroke patients. This finding may lead to new rehabilitation strategies for post-stroke patients that focus on improving activation timing of different muscle synergies.
Original language | English |
---|---|
Article number | 8972459 |
Pages (from-to) | 1796-1802 |
Number of pages | 7 |
Journal | IEEE Robotics and Automation Letters |
Volume | 5 |
Issue number | 2 |
DOIs | |
Publication status | Published - Apr 2020 |
Externally published | Yes |
Keywords
- Stroke
- muscle synergy
- rehabilitation
ASJC Scopus subject areas
- Control and Systems Engineering
- Biomedical Engineering
- Human-Computer Interaction
- Mechanical Engineering
- Computer Vision and Pattern Recognition
- Computer Science Applications
- Control and Optimization
- Artificial Intelligence