Quantification of Upper-Limb Motor Function for Stroke Rehabilitation Through Manifold Similarity of Muscle Synergy

Quantifying post-stroke patient motor function is important for assessing rehabilitation progress and optimizing the behavior of adaptive rehabilitation robots. To this end, researchers have increasing turned to the concept of muscle synergies, which encodes the simplified neuromuscular control strategy employed by the central nervous system in response to post-stroke impairment. In essence, the assessment metrics should possess two key attributes: the ability to differentiate between individuals in the pathological and healthy groups, and the capacity to yield consistent measurements within the same individual, thereby facilitating the refinement of adaptive control algorithms. Recent findings have indicated that employing manifold similarity measurements can enhance the class separability and intra-class compactness for the classification/clustering algorithm. Consequently, we hypothesize that evaluating synergy and synergy activation similarities, while considering the underlying manifold structure, will render a more sensitive and reliable approach for quantifying motor function in post-stroke patients. To validate our hypothesis, we conducted a study involving twenty healthy subjects and ten post-stroke patients. Our results demonstrate that the utilization of manifold similarities leads to superior outcomes compared to conventional metrics based on muscle synergy. Specifically, we observed higher sensitivity ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$g_{w}\ v.s.\ S_{w}$</tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$0.0457\ v.s.\ 0.0030$</tex-math></inline-formula> ), greater intra-subject reliability ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$g_{c}\ v.s.\ S_{c}$</tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$0.6060\ v.s.\ 0.1081$</tex-math></inline-formula> ), and stronger correlations with clinical scores ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$g_{w}\ v.s.\ S_{w}$</tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$0.7588\ v.s.\ 0.6249$</tex-math></inline-formula> ) than conventional metrics. Therefore, the proposed similarity metrics may be promising for transferring to adaptive control of rehabilitation robots.