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. This study validates the possibility of extending and refining turns-amplitude analysis using permutation entropy and signal energy. Methods. In this study, we examined needle electromyography in 40 neuropathic individuals and 40 controls. The number of turns, amplitude between turns, signal energy, and "permutation entropy" were used as features for support vector machine classification. Results. The obtained results proved the superior classification performance of the combinations of all of the above-mentioned features compared to the combinations of fewer features. The 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 classification can be used to refine the diagnosis of polyneuropathies examined by needle electromyography.

Department of Computing and Control Engineering Institute of Chemical Technology Technická 5 166 28 Prague 6 Czech Republic

Faculty of Medicine and University Hospital Hradec Králové Charles University Prague Sokolská Street 581 500 05 Hradec Králové Czech Republic

Neurocenter Caregroup Ltd Jiráskova 1389 Rychnov nad Kněžnou Czech Republic

See more in PubMed

Daube J. R., Rubin D. I. Needle electromyography. Muscle & Nerve. 2009;39(2):244–270. doi: 10.1002/mus.21180. PubMed DOI

Rose A. L., Willison R. G. Quantitative electromyography using automatic analysis: studies in healthy subjects and patients with primary muscle disease. Journal of Neurology, Neurosurgery & Psychiatry. 1967;30(5):403–410. doi: 10.1136/jnnp.30.5.403. PubMed DOI PMC

Leonard J. A., Jr., Abel N., Cochrane T., et al. Guidelines for ethical behavior relating to clinical practice issues in neuromuscular and electrodiagnostic medicine. Muscle & Nerve. 2010;42(4):480–486. doi: 10.1002/mus.21761. PubMed DOI

Daube R. D., Jasper R. Turns and amplitude analysis of the interference pattern. In: Smith B. E., editor. Clinical Neurophysiology. New York, NY, USA: Oxford University Press; 2009. pp. 469–471.

Procházka A., Vyšata O., Ťupa O., Yadollahi M., Vališ M. Discrimination of axonal neuropathy using sensitivity and specificity statistical measures. Neural Computing and Applications. 2014;25(6):1349–1358.

Garcia H. A., Milner-Brown H. S., Fisher M. A. Turns analysis in the physiological evaluation of neuromuscular disorders. Journal of Neurology, Neurosurgery & Psychiatry. 1980;43(12):1091–1097. doi: 10.1136/jnnp.43.12.1091. PubMed DOI PMC

Fuglsang-Frederiksen A. The utility of interference pattern analysis. Muscle & Nerve. 2000;23(1):18–36. doi: 10.1002/(SICI)1097-4598(200001)23:1<18::AID-MUS4>3.0.CO;2-B. PubMed DOI

Finsterer J., Mamoli B., Fuglsang-Frederiksen A. Peak-ratio interference pattern analysis in the detection of neuromuscular disorders. Electroencephalography and Clinical Neurophysiology: Electromyography and Motor Control. 1997;105(5):379–384. doi: 10.1016/S0924-980X(97)00039-8. PubMed DOI

Bandt C., Pompe B. Permutation entropy: a natural complexity measure for time series. Physical Review Letters. 2002;88(17)174102 PubMed

Riedl M., Müller A., Wessel N. Practical considerations of permutation entropy: A tutorial review. The European Physical Journal Special Topics. 2013;222(2):249–262. doi: 10.1140/epjst/e2013-01862-7. DOI

Vapnik V. N. An overview of statistical learning theory. IEEE Transactions on Neural Networks and Learning Systems. 1999;10(5):988–999. doi: 10.1109/72.788640. PubMed DOI

Scholkopf B., Burges C. J. C., Smola A. J. Support vector classification. In: Scholkopf B., Burges C. J. C., Smola A. J., editors. Learning with Kernels. Cambridge, MA, UK: MIT Press; 2002. pp. 15–17.

Cortes C., Vapnik V. Support-vector networks. Machine Learning. 1995;20(3):273–297. doi: 10.1007/BF00994018. DOI

Bennett K. P., Campbell C. Support vector machines. ACM SIGKDD Explorations Newsletter. 2000;2(2):1–13. doi: 10.1145/380995.380999. DOI

Kulkarni S. R., Harman G. Statistical learning theory: A tutorial. Wiley Interdisciplinary Reviews: Computational Statistics. 2011;3(6):543–556. doi: 10.1002/wics.179. DOI

Drucker H., Burges C. J. C., Kaufman L., Smola A. J., Vapnik V. Support vector regression machines. In: Mozer M. C., Jordan M. I., Petsche T., editors. Advances in Neural Information Processing Systems. Cambridge, MA, UK: MIT Press; 1997. pp. 155–161.

Ben-Hur A., Horn D., Siegelmann H., Vapnik V. A support vector clustering method. Journal of Machine Learning Research. 2002;2:125–137.

Gao S., Zhang N., Duan G. Y., Yang Z., Ruan J. S., Zhang T. Prediction of function changes associated with single-point protein mutations using support vector machines (SVMs) Human Mutation. 2009;30(8):1161–1166. doi: 10.1002/humu.21039. PubMed DOI