Analysis of neuromuscular disorders using statistical and entropy metrics on surface EMG

Abstract

This paper introduces the surface electromyogram (EMG) classification system based on statistical and entropy metrics. The system is intended for diagnostic use and enables classification of examined subject as normal, myopathic or neuropathic, regarding to the acquired EMG signals. 39 subjects in total participated in the experiment, 19 normal, 11 myopathic and 9 neuropathic. Surface EMG was recorded using 4-channel surface electrodes on the biceps brachii muscle at isometric voluntary contractions. The recording time was only 5 seconds long to avoid muscle fatigue, and contractions at five force levels were performed, i.e. 10, 30, 50, 70 and 100 % of maximal voluntary contraction. The feature extraction routine deployed the wavelet transform and calculation of the Shannon entropy across all the scales in order to obtain a feature set for each subject. Subjects were classified regarding the extracted features using three machine learning techniques, i.e. decision trees, support vector machines and ensembles of support vector machines. Four 2-class classifications and a 3-class classification were performed. The scored classification rates were the following: 64±11% for normal/ abnormal, 74±7% for normal/myopathic, 79±8% for normal /neuropathic, 49±20% for myopathic/neuropathic, and 63±8% for normal/myopathic/neuropathic.