Research Article Permutation Entropy and Signal Energy Increase the Accuracy of Neuropathic Change Detection in Needle EMG O. Dostál , 1 O. Vysata , 1,2 L. Pazdera , 3 A. Procházka , 2 J. Kopal , 2 J. Kuchy^ka , 1 and M. Vališ 1 1 Faculty of Medicine and University Hospital Hradec Kr´ alov´ e, Charles University in Prague, Sokolsk´ a Street 581, 500 05 Hradec Kr´ alov´ e, Czech Republic 2 Department of Computing and Control Engineering, Institute of Chemical Technology, Technick´ a 5, 166 28 Prague 6, Czech Republic 3 Neurocenter Caregroup, Ltd., Jir´ askova 1389, Rychnov nad Knˇ eˇ znou, Czech Republic Correspondence should be addressed to O. Vysata; vysatao@gmail.com Received 14 August 2017; Revised 22 December 2017; Accepted 28 December 2017; Published 24 January 2018 Academic Editor: Yudong Cai Copyright © 2018 O. Dost´ al et al. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Background and Objective. Needle electromyography can be used to detect the number of changes and morphological changes in motor unit potentials of patients with axonal neuropathy. General mathematical methods of pattern recognition and signal analysis were applied to recognize neuropathic changes. Tis study validates the possibility of extending and refning turns-amplitude analysis using permutation entropy and signal energy. Methods. In this study, we examined needle electromyography in 40 neuropathic individuals and 40 controls. Te number of turns, amplitude between turns, signal energy, and “permutation entropy” were used as features for support vector machine classifcation. Results. Te obtained results proved the superior classifcation performance of the combinations of all of the above-mentioned features compared to the combinations of fewer features. Te lowest accuracy from the tested combinations of features had peak-ratio analysis. Conclusion. Using the combination of permutation entropy with signal energy, number of turns and mean amplitude in SVM classifcation can be used to refne the diagnosis of polyneuropathies examined by needle electromyography. 1. Introduction Qualitative visual analysis of MUPs and interference patterns may be useful for diagnosis when there are clear changes, but this approach may be misleading in patients with more subtle lesions [1]. Computational processing helps clinicians draw conclusions from large data sets, such as complex waveforms acquired from EMG. Performing single motor unit potential (MUP) analysis during a weak muscle contraction a is time- consuming test. For some of the examined subjects, it is difcult to maintain a constant weak contraction. Te ideal solution for a description of the EMG signal would be perfect decomposition of the action potentials of motor units to determine an interference curve. In clinical practice, the precise decomposition of intramuscular EMG signals still has limited applications. In most cases, the signal is not fully decomposed or only a few representative action potentials are collected. One way of quantifying the electromyographic interference pattern is by measuring the number of turns and the mean amplitude change between successive turns. A turn occurs at a peak at which the signal changes direction and difers by at least 100 V in amplitude from the previous and following turns [2]. A disadvantage of the Willison analysis is that it does not appear to be as sensitive as single MUP analysis. In axonal polyneuropathy, there is a loss of motor units, which leads to simplifcation of EMG curves. Terefore, reductions in signal entropy and energy are expected. While muscle contraction increases, more motor units are fring. Tis leads to an increase in signal entropy. Te aim of this study is to compare the performance of classifcation based on “turns-amplitude” analysis with classifcation derived from an extended number of features, including “permutation entropy” and signal energy. Subse- quently, a supervised learning method called the “support vector machine” is used for binary classifcation of the data. Hindawi Computational Intelligence and Neuroscience Volume 2018, Article ID 5276161, 5 pages https://doi.org/10.1155/2018/5276161