Identification and grading of spasticity by using AdaBoost and k-NN techniques

Spasticity is a disorder that causes movement constraints in daily life and induced by upper neuron syndrome. Although spasticity is a well-known motor disorder, there are related diagnostic and assessment problems. The lack of common rating in assessment of spasticity causes significant differences between the interpretations of the specialists. In this study, it is aimed to conduct a highly accurate evaluation based on the Ashworth scale, which is one of the most accepted scales for assessment and grading of the spasticity. In this study, Electromyogram (EMG) signals obtained in Rectus Femoris and Biceps Femoris muscles are used to trigger Patela-T reflexes in spastic patients. 26 features are derived by calculating five features in both time and frequency domains from measured EMG signals and six features of Pendulum movement to recognize the normal person and patients with Ashworth 1-Ashworth 2 spasticity levels. Finally, spasticity is graded by using k-nearest neighbor (k-NN) algorithm and AdaBoost method. The performance of the proposed study is evaluated by calculating accuracy, sensitivity, precision and specificity criteria. Simulation results are demonstrated that the study has crucial importance to assess and grade the spasticity.