Pattern recognition based forearm motion classification for patients with chronic hemiparesis

Abstract

To make full use of electromyography (EMG) that contains rich information of muscular activities in active rehabilitation for motor hemiparetic patients, a couple of recent studies have explored the feasibility of applying pattern recognition technique to the classification of multiple motion classes for stroke survivors and reported some promising results. However, it still remains unclear if kinematics signals could also bring good motion classification performance, particularly for patients after traumatic brain damage. In this study, the kinematics signals was used for motion classification analysis in three stroke survivors and two patients after traumatic brain injury, and compared with EMG. The results showed that an average classification error of 7.9 ± 6.8% for the affected arm over all subjects could be achieved with a linear classifier when they performed multiple fine movements, 7.9% lower than that when using EMG. With either kind of signals, the motor control ability of the affected arm degraded significantly in comparison to the intact side. The preliminary results suggested the great promise of kinematics information as well as the biological signals in detecting user's conscious effort for robot-aided active rehabilitation.