Conventional electrophysiological (EP) tests may yield ambiguous or false-negative results in some patients with signs and symptoms of carpal tunnel syndrome (CTS). Therefore, researchers tend to investigate new parameters to improve the sensitivity and specificity of EP tests. We aimed to investigate the mean and maximum power of the compound muscle action potential (CMAP) as a novel diagnostic parameter, by evaluating diagnosis and classification performance using the supervised Kohonen self-organizing map (SOM) network models. The CMAPs were analyzed using the fast Fourier transform (FFT). The mean and maximum power parameters were calculated from the power spectrum. A counter-propagation artificial neural network (CPANN), supervised Kohonen network (SKN) and XY-fused network (XYF) were compared to evaluate the classification and diagnostic performance of the parameters using the confusion matrix. The mean and maximum power of the CMAP were significantly lower in patients with CTS than in the normal group (p < 0.05), and the XYF network had the best total performance of classification with 91.4%. This study suggests that the mean and maximum power of the CMAP can be considered as less time-consuming parameters for the diagnosis of CTS without using additional EP tests which can be uncomfortable for the patient due to poor tolerance to electrical stimulation.
The authors thank the members of the Department of Physical Medicine and Rehabilitation, School of Medicine, Gazi University for collecting data. Moreover, we thank Ankara Yıldırım Beyazıt University for supporting this study with the project number BAP 4043.
Research funding: Authors state no funding involved.
Conflict of interest: Authors state no conflict of interest.
Informed consent: Informed consent is not applicable.
Ethical approval: The conducted research is not related to either human or animal use.
 Aminoff MJ. Electromyography in Clinical Practice. 2nd ed. New York, NY, USA: Churchill Livingstone; 1987:165–96.Search in Google Scholar
 Jablecki CK, Andry MT, So YT, Wilkins DE, Williams FH. Literature review of the usefulness of nerve conduction studies and electromyography for the evaluation of patients with carpal tunnel syndrome. Muscle Nerve 1993;16:1392–414.10.1002/mus.880161220Search in Google Scholar PubMed
 Homan MM, Franzblau A, Werner RA, Albers JW, Armstrong TJ, Bromberg MB. Agreement between symptom surveys, physical examination procedures and electrodiagnostic findings for the carpal tunnel syndrome. Scand J Work Environ Health 1999;25:115–24.10.5271/sjweh.413Search in Google Scholar PubMed
 Lew HL, Date ES, Pan SS, Wu P, Ware PF, Kingery WS. Sensitivity, specificity, and variability of nerve conduction velocity measurements in carpal tunnel syndrome. Arch Phys Med Rehabil 2005;86:12–6.10.1016/j.apmr.2004.03.023Search in Google Scholar PubMed
 Rempel D, Evanoff B, Amadio PC, de Krom M, Franklin G, Franzblau A, et al. Consensus criteria for classification of carpal tunnel syndrome in epidemiologic studies. Am J Publ Health 1998;88:1447–51.10.2105/AJPH.88.10.1447Search in Google Scholar
 Sandin KJ, Asch SM, Jablecki CK, Kılmer DD, Nuckols TK. Clinical quality measures for electrodiagnosis in suspected carpal tunnel syndrome. Muscle Nerve 2010;41:444–52.10.1002/mus.21617Search in Google Scholar PubMed
 Bodofsky EB, Wu KD, Campellone JV, Greenberg WM, Tomaio CA. A sensitive new median-ulnar technique for diagnosing mild carpal tunnel syndrome. Electromyogr Clin Neurophysiol 2005;45:139–44.Search in Google Scholar PubMed
 Kohara N. Clinical and electrophysiological findings in carpal tunnel syndrome. Brain Nerve 2007;59:1229–38.Search in Google Scholar PubMed
 Simovic D, Weinberg DH. The median nerve terminal latency index in carpal tunnel syndrome: a clinical case selection study. Muscle Nerve 1999;22:573–7.10.1002/(SICI)1097-4598(199905)22:5<573::AID-MUS4>3.0.CO;2-ASearch in Google Scholar PubMed
 Ogura T, Kubo T, Okuda Y, Lee K, Kira Y, Aramaki X, et al. Power spectrum analysis of compound muscle action potential in carpal tunnel syndrome patients. J Orthop Surg 2002;10:67–71.10.1177/230949900201000112Search in Google Scholar
 Ogura T, Mori M, Mikami Y, Hase H, Hayashida T, Kubo T, et al. Diagnostic utility of waveform analysis of compound muscle action potentials for carpal tunnel syndrome. J Orthop Surg 2004;12:63–70.10.1177/230949900401200112Search in Google Scholar
 Thaisetthawatkul P, Logigian EL, Herrmann DN. Dispersion of the distal compound muscle action potential as a diagnostic criterion for chronic inflammatory demyelinating polyneuropathy. Neurology 2002;59:1526–31.10.1212/01.WNL.0000034172.47882.20Search in Google Scholar PubMed
 Ide H, Obata S. Feature characterisation of shape from the frequency spectrum of the e.m.g. Med Biol Eng Comput 1983;21:166–71.10.1007/BF02441532Search in Google Scholar PubMed
 Phinyomark A, Thongpanja S, Hu H, Phukpattaranont P, Limsakul C. The usefulness of mean and median frequencies in electromyography analysis. In: Naik GR, editor. Computational Intelligence in Electromyography Analysis – A Perspective on Current Applications and Future Challenges. London: InTech; 2012.10.5772/50639Search in Google Scholar
 Kohonen T. Self-organizing maps. New York, NY, USA: Springer; 2001.10.1007/978-3-642-56927-2Search in Google Scholar
 Padua L, LoMonaco M, Gregori B, Valente EM, Padna R, Tonali P. Neurophysiological classification and sensitivity in 500 carpal tunnel syndrome hands. Acta Neurol Scand 1997;96:211–7.10.1111/j.1600-0404.1997.tb00271.xSearch in Google Scholar PubMed
 Farina D, Fevotte C, Doncarli C, Merletti R. Blind separation of linear instantaneous mixtures of nonstationary surface myoelectric signals. IEEE Trans Biomed Eng 2004;51:1555–67.10.1109/TBME.2004.828048Search in Google Scholar PubMed
 Kilby J, Prasad K. Analysis of surface electromyography signals using discrete Fourier transform sliding window technique. Int J Comput Theory Eng 2013;5:321–5.10.7763/IJCTE.2013.V5.702Search in Google Scholar
 Press WH, Flannery BP, Teukolsky SA, Vetterling WT. Power spectra estimation using the FFT and power spectrum estimation by the maximum entropy (all poles) method. The Art of Scientific Computing. 2nd ed. Cambridge, UK: Cambridge University Press; 1992;54251.Search in Google Scholar
 Melssen W, Wehrens R, Buydens L. Supervised Kohonen networks for classification problems. Chemometr Intell Lab Syst 2006;83:99–113.10.1016/j.chemolab.2006.02.003Search in Google Scholar
 Ballabio D, Vasigh MA. MATLAB toolbox for self-organizing maps and supervised neural network learning strategies. Chemometr Intell Lab Syst 2012;118:24–32.10.1016/j.chemolab.2012.07.005Search in Google Scholar
 Zupan J, Novic M, Ruisánchez I. Kohonen and counter propagation artificial neural networks in analytical chemistry. Chemometr Intell Lab Syst 1997;38:1–23.10.1016/S0169-7439(97)00030-0Search in Google Scholar
 Gomez-Carracedo MP, Ballabio D, Andrade JM, Fernandez-Varela R, Consonni V. Applications of self-organizing maps to address environmental studies. Soft Computing Methods for Practical Solutions: Techniques and Studies 2010;33153.10.4018/978-1-61520-893-7.ch020Search in Google Scholar
 Kuzmanovski I, Novic M. Counter-propagation neural networks in Matlab. Chemometr Intell Lab Syst 2008;90:84–91.10.1016/j.chemolab.2007.07.003Search in Google Scholar
 Palve SS, Palve SB. Impact of aging on nerve conduction velocities and late responses in healthy individuals. J Neurosci Rural Pract 2018;9:112–16.10.4103/jnrp.jnrp_323_17Search in Google Scholar PubMed
 Blumenthal S, Herskovitz S, Verghese J. Carpal tunnel syndrome in older adults. Muscle Nerve 2006;34:78–83.10.1002/mus.20559Search in Google Scholar PubMed
 Bodofsky EB, Campellone JV, Wu KD, Greenberg WM. Age and the severity of carpal tunnel syndrome. Electromyogr Clin Neurophysiol 2004;44:195–9.Search in Google Scholar PubMed
 Bland JDP, Rudolfer SM. Clinical surveillance of carpal tunnel syndrome in two areas of the United Kingdom, 1991–2001. J Neurol Neurosurg Psychiatry 2003;74:1674–9.10.1136/jnnp.74.12.1674Search in Google Scholar PubMed
 Kupa EJ, Roy SH, Kandarian SC, De Luca CJ. Effects of muscle fiber type and size on EMG median frequency and conduction velocity. J Appl Physiol 1995;79:23–32.10.1152/jappl.19220.127.116.11Search in Google Scholar PubMed
 Takayanagi K, Ihara H, Nakayama A, Yoshimura S, Shimobatake H. Characteristics of eccentric and concentric muscular contraction on knee flexors and extensors – examination with power spectrum of surface EMG. Phys Ther 1990;17:3–10.Search in Google Scholar
 Barandun V, von Tscharner V, Meuli-Simmen C, Bowen V, Valderrabano V. Frequency and conduction velocity analysis of the abductor pollicis brevis muscle during early fatigue. J Electromyogr Kinesiol 2009;19:65–74.10.1016/j.jelekin.2007.07.003Search in Google Scholar PubMed
 Gazzoni M, Camelia F, Farina D. Conduction velocity of quiescent muscle fibers decreases during sustained contraction. J Neurophysiol 2005;94:387–94.10.1152/jn.01182.2004Search in Google Scholar PubMed
 Dimitrova NA, Dimitrov GV. Interpretation of EMG changes with fatigue: facts, pitfalls, and fallacies. J Electromyogr Kinesiol 2003;13:13–36.10.1016/S1050-6411(02)00083-4Search in Google Scholar PubMed
 Merletti R, Lo Conte LR. Surface EMG signal processing during isometric contractions. J Electromyogr Kinesiol 1997;7:241–50.10.1016/S1050-6411(97)00010-2Search in Google Scholar PubMed
 Barthakur M, Hazarika A, Bhuyan M. Classification of peripheral neuropathy by using ANN based Nerve Conduction Study (NCS) Protocol. ACEEE Int J Commun 2014;5:31.Search in Google Scholar
 Konuralp I, Übeyli ED, Ilbay G, Budak F. Recurrent neural networks for diagnosis of carpal tunnel syndrome using electrophysiologic findings. J Med Syst 2010;34:643–50.10.1007/s10916-009-9277-6Search in Google Scholar PubMed
 Pattichis CS, Charalambous C, Middleton LT. Efficient training of neural network models in classification of electromyographic data. Med Biol Eng Comput 1995;33:499–503.10.1007/BF02510537Search in Google Scholar PubMed
 Albuquerque V, Alexandria A, Cortez P, Tavares J. Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images. NDT & E Int 2009;42:644–51.10.1016/j.ndteint.2009.05.002Search in Google Scholar
 Kaur A, Singh N, Bahrdwaj A. A comparison of supervised multilayer back propagation and unsupervised self organizing maps for the diagnosis of thyroid disease. Int J Comput Appl 2013;82:39–43.10.5120/14180-2438Search in Google Scholar
 Toor AK, Singh A. Analysis of clustering algorithms based on number of clusters, error rate, computation time and map topology on large data set. Int J Emerging Trends Technol Comput Sci 2013;2:94–8.Search in Google Scholar
©2020 Walter de Gruyter GmbH, Berlin/Boston