Decoding movement intent of patient with multiple sclerosis for the powered lower extremity exoskeleton

This study aims to recognize movement intent of patients with multiple sclerosis (MS) by decoding neuromuscular control signals fused with mechanical measurements as a method of powered lower extremity exoskeleton control. Surface electromyographic (EMG) signals recorded from the lower extremity muscles, ground reaction forces measured from beneath both feet, and kinematics from both thigh segments of a single MS patient were used to identify three activities (level-ground walking, sitting, and standing). Our study showed that during activity performance clear modulation of muscle activity in the lower extremities was observed for the MS patient, whose Kurtzke Expanded Disability Status Scale (EDSS) was 6. The designed intent recognition algorithm can accurately classify the subject's intended movements with 98.73% accuracy in static states and correctly predict the activity transitions about 100 to 130 ms before the actual transitions were made. These promising results indicate the potential of designed intent recognition interface for volitional control of powered lower extremity exoskeletons.