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

Over the past several decades, many scholars have investigated muscle synergy as a promising tool for evaluating motor function. However, it is challenging to obtain favorable robustness using the general muscle synergy identification algorithms, namely non-negative matrix factorization (NMF), independent component analysis (ICA), and factor analysis (FA). Some scholars have proposed improved muscle synergy identification algorithms to overcome the shortcomings of these approaches, such as singular value decomposition NMF (SVD-NMF), sparse NMF (S-NMF), and multivariate curve resolution-alternating least squares (MCR-ALS). However, performance comparisons of these algorithms are seldom conducted. In this study, experimental electromyography (EMG) data collected from healthy individuals and stroke survivors were applied to assess the repeatability and intra-subject consistency of NMF, SVD-NMF, S-NMF, ICA, FA, and MCR-ALS. MCR-ALS presented higher repeatability and intra-subject consistencies than the other algorithms. More synergies and lower intra-subject consistencies were observed in stroke survivors than in healthy individuals. Thus, MCR-ALS is considered a favorable muscle synergy identification algorithm for patients with neural system disorders.