Classification of COPD and normal lung airways using feature extraction of electromyographic signals

Abstract

Airway obstruction is a common component in Chronic Obstructive Pulmonary Disease (COPD). Detection of obstruction and its grading is very essential. Obstruction in the airways, forces the accessory muscles like sternomastoid muscle (SMM) of respiration to work. Normally, only essential muscles of respiration work. In the said paper electromyographic (EMG) analysis of SMM is done for COPD and Normal subjects. We have developed improved slope based onset detection algorithm to detect the onset and offset timing of EMG. Time domain features are extracted for COPD and normal subject. The onset detection algorithm reduces the number of computations by 32.96% and increases accuracy of feature calculation by 40.19%. Dominant time domain features are selected and applied to Support Vector Machine Classifier. The SVM classification algorithm is compared with Threshold and Naïve Bayes classification algorithm. SVM gives the highest accuracy of 87.80%, sensitivity of 89.65% and specificity of 83.33%. Results are also compared with previously used FEV1/FEV6 and Forced Oscillation Technique. The activity of SMM has a significant role in the classification of Normal and COPD subject. Further analysis of SMM can be done to find different grades of COPD.