A quantitative lower limb function assessment method based on fusion of surface EMG and inertial data in stroke patients during cycling task

Abstract

ObjectiveQuantitative methods provide an accurate way to determine lower-limb motor function level that is essential for post-stroke rehabilitation protocol setup. Due to less requirement of postural stability and balance control, cycling task is more suitable for stroke patients in acute period compared to gait tasks. However, the feasibility of motor function assessment under cycling task has been rarely studied. In this study, we investigated the locomotor performance under cycling task with comparing to a lower-limb movement sequence task and developed a motor assessment framework based on fusion of surface electromyography (sEMG) and inertial features. MethodsTen post-stroke hemiparetic patients were enrolled where sEMG signals and inertial data were measured and derived in both tasks. The task effect was investigated using one-way analysis of variance and feature difference between the affected and unaffected limbs was furtherly statistically analyzed. Ratios of feature were calculated based on which a motor function assessment model was built using a K-nearest neighbor regression algorithm. ResultsResults showed that patients had more significant differences in bilateral muscle activations and ratios of features in the cycling task had higher correlation with Fugl-Meyer assessment scores. The proposed model obtained a high accuracy prediction with a significant correlation (R2 = 0.99, MAE = 0.15, p < 0.001) in lower-limb motor score prediction. ConclusionThe study provides a novel motor assessment framework that validates the usability and feasibility of cycling task and has great potential in practical clinical assessment.