EMG-based Recognition Method of Finger Movement Impairment Level on Post-Stroke Patient Based on Fugl-Meyer Assessment

Restoring the motor function of the fingers is considered to be difficult during rehabilitation period due to the complexity of the muscles. The Fugl-Meyer Assessment (FMA) method is used by doctors to manually assess the level of impaired finger movement. This leads to subjectivity and the risk of evaluation errors. Therefore, a method that is able to predict the level of impairment is needed. Thus, the doctors could perform more accurate judgments. The aim of this study is to recognize the impairment level of finger movement based on the Fugl-Meyer Assessment. EMG signals were recorded from 4 patients while performing 7 movements based on FMA and feature extraction was performed. SVM and Random Forest were used to classify the level of impairment of each movement. The SVM model obtained good results in the fourth movement with an accuracy of 91.7% and an f1 score of 0.78.