Using different matrix factorization approaches to identify muscle synergy in stroke survivors

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Science

Background:

• Muscle synergy analysis is crucial for understanding motor control and evaluating motor function.
• Existing algorithms like Non-negative Matrix Factorization (NMF), Independent Component Analysis (ICA), and Factor Analysis (FA) face challenges in robustness.
• Improved algorithms such as Singular Value Decomposition NMF (SVD-NMF), Sparse NMF (S-NMF), and Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) have been proposed, but direct performance comparisons are scarce.

Purpose of the Study:

• To compare the performance of various muscle synergy identification algorithms using experimental electromyography (EMG) data.
• To assess the repeatability and intra-subject consistency of NMF, SVD-NMF, S-NMF, ICA, FA, and MCR-ALS.
• To determine the most suitable algorithm for analyzing muscle synergies in both healthy individuals and stroke survivors.

Main Methods:

• Collected experimental electromyography (EMG) data from healthy individuals and stroke survivors.
• Applied NMF, SVD-NMF, S-NMF, ICA, FA, and MCR-ALS to the EMG data.
• Evaluated the repeatability and intra-subject consistency of each algorithm.

Main Results:

• MCR-ALS demonstrated higher repeatability and intra-subject consistency compared to NMF, SVD-NMF, S-NMF, ICA, and FA.
• Stroke survivors exhibited more identified muscle synergies and lower intra-subject consistencies than healthy individuals.
• The findings highlight significant differences in muscle synergy patterns between healthy and impaired motor control.

Conclusions:

• MCR-ALS is identified as a superior algorithm for muscle synergy identification, offering enhanced robustness and consistency.
• The increased number of synergies and reduced consistency in stroke survivors suggest altered motor control strategies.
• MCR-ALS is recommended as a favorable tool for muscle synergy identification in patients with neural system disorders, aiding in rehabilitation and assessment.