Skip to main content

Advertisement

SpringerLink
Log in

Multiscale entropy-based approach to automated surface EMG classification of neuromuscular disorders

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

We introduce a novel method for an automatic classification of subjects to those with or without neuromuscular disorders. This method is based on multiscale entropy of recorded surface electromyograms (sEMGs) and support vector classification. The method was evaluated on a single-channel experimental sEMGs recorded from biceps brachii muscle of nine healthy subjects, nine subjects with muscular and nine subjects with neuronal disorders, at 10%, 30%, 50%, 70% and 100% of maximal voluntary contraction force. Leave-one-out cross-validation was performed, deploying binary (healthy/patient) and three-class classification (healthy/myopathic/neuropathic). In the case of binary classification, subjects were distinguished with 81.5% accuracy (77.8% sensitivity at 83.3% specificity). At three-class classification, the accuracy decreased to 70.4% (myopathies were recognized with a sensitivity of 55.6% at specificity 88.9%, neuropathies with a sensitivity of 66.7% at specificity 83.3%). The proposed method is suitable for fast and non-invasive discrimination of healthy and neuromuscular patient groups, but it fails to recognize the type of pathology.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.

References

  1. Anand N, Chad D (2007) Electrophysiology of myopathy. In: Blum AS, Rutkove SB (eds) The clinical neurophysiology primer. Humana Press, New Jersey, pp 325–352

    Chapter  Google Scholar 

  2. Christodoulou CI, Pattichis CS (1999) Unsupervided pattern recognition for the classification of EMG signals. IEEE Trans Biomed Eng 46:169–178

    Article  CAS  PubMed  Google Scholar 

  3. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Google Scholar 

  4. Costa M, Goldberger AL, Peng CK (2005) Multiscale entropy analysis of biological signals. Phys Rev E 71(2):021906

    Article  Google Scholar 

  5. De Michele G, Sello S, Carboncini MC, Rossi B, Strambi SK (2003) Cross-correlation time-frequency analysis for multiple EMG signals in Parkinson’s disease: a wavelet approach. Med Eng Phys 25:361–369

    Article  PubMed  Google Scholar 

  6. Dimitrova NA, Dimitrov GV (2003) Interpretation of EMG changes with fatigue: facts, pitfalls, and fallacies. J Electromyogr Kinesiol 13:13–36

    Article  CAS  PubMed  Google Scholar 

  7. Disselhorst-Klug C, Silny J, Rau G (1998) Estimation of the relationship between the noninvasively detected activity of single motor units and their characteristic pathological changes by modelling. J Electromyogr Kinesiol 8:323–335

    Article  CAS  PubMed  Google Scholar 

  8. Dobrowolski A, Tomczykiewicz K, Komur P (2007) Spectral analysis of motor unit action potentials. IEEE Trans Biomed Eng 54:2300–2302

    Article  PubMed  Google Scholar 

  9. Drost G, Stegeman DF, Schillings ML, Horemans HLD, Janssen HMHA, Massa M, Nollet F, Zwarts MJ (2004) Motor unit characteristics in healthy subjects and those with postpoliomyelitis syndrome: a high-density surface EMG study. Muscle Nerve 30:269–276

    Article  PubMed  Google Scholar 

  10. Drost G, Stegeman DF, van Engelen BGM, Zwarts MJ (2006) Clinical applications of high-density surface EMG: a systematic review. J Electromyogr Kinesiol 16:586–602

    Article  PubMed  Google Scholar 

  11. Fuglsang-Frederiksen A (2006) The role of different EMG methods in evaluating myopathy. Clin Neurophysiol 117:1173–1189

    Article  PubMed  Google Scholar 

  12. Gazzoni M, Farina D, Merletti R (2004) A new method for the extraction and classification of single motor unit action potentials from surface EMG signals. J Neurosci Methods 136:165–177

    Article  PubMed  Google Scholar 

  13. Güler NF, Koçer S (2005) Classification of EMG signals using PCA and FFT. J Med Syst 29:241–250

    Article  PubMed  Google Scholar 

  14. Huppertz HJ, Disselhorst-Klug C, Silny J, Rau G, Heimann G (1997) Diagnostic yield of noninvasive high spatial resolution electromyography in neuromuscular diseases. Muscle Nerve 20:1360–1370

    Article  CAS  PubMed  Google Scholar 

  15. Kaplanis PA, Pattichis CS, Christodoulou CI, Hadjileontiadis LJ, Roberts CV, Kyriakides T (2004) A surface electromyography classification system. In: IFMBE proceedings of 10th mediterranean conference on medical and biological engineering and computing and Health Telematics, vol 6, pp 278–281

  16. Katsis CD, Goletsis Y, Likas A, Fotiadis DI, Sarmas I (2006) A novel method for automated EMG decomposition and MUAP classification. Artif Intell Med 37:55–64

    Article  CAS  PubMed  Google Scholar 

  17. Katsis CD, Exarchos TP, Papaloukas C, Goletsis Y, Fotiadis DI, Sarmas I (2007) A two-stage method for MUAP classification based on EMG decomposition. Comput Biol Med 37:1232–1240

    Article  PubMed  Google Scholar 

  18. Kaufman M, Zurcher U, Sung PS (2007) Entropy of electromyography time series. Physica A 386:698–707

    Article  Google Scholar 

  19. Keenan KG, Farina D, Maluf KS, Merletti R, Enoka RM (2005) Influence of amplitude cancellation on the simulated surface electromyogram. J Appl Physiol 98:120–131

    Article  PubMed  Google Scholar 

  20. Kosmidou VE, Hadjileontiadis LI (2009) Using sample entropy for automated sign language recognition on sEMG and accelerometer data. Med Biol Eng Comput 48(3):255–267

    Article  PubMed  Google Scholar 

  21. Lauer RT, Stackhouse CA, Shewokis PA, Smith BT, Tucker CA, McCarthy J (2007) A time-frequency based electromyographic analysis technique for use in cerebral palsy. Gait Posture 26:420–427

    Article  PubMed  Google Scholar 

  22. Lindeman E, Spaans F, Reulen JPH, Leffers P, Drukker J (1999) Surface EMG of proximal leg muscles in neuromuscular patients and in healthy controls. Relations to force and fatigue. J Electromyogr Kinesiol 9:299–307

    Article  CAS  PubMed  Google Scholar 

  23. Meekins GD, So Y, Quan D (2008) American association of neuromuscular and electrodiagnostic medicine evidenced-based review: use of surface electromyography in the diagnosis and study of neuromuscular disorders. Muscle Nerve 38:1219–1224

    Article  PubMed  Google Scholar 

  24. Merletti R, Holobar A, Farina D (2008) Analysis of motor units with high-density surface electromyography. J Electromyogr Kinesiol 18:879–890

    Article  PubMed  Google Scholar 

  25. Mewett DT, Reynold KJ, Nazeran H (2004) Reducing power line interference in digitized electromyogram recordings by spectrum interpolation. Med Biol Eng Comput 42(4):524–531

    Article  CAS  PubMed  Google Scholar 

  26. Nielsen M, Kamavuako EN, Andersen MM, Lucas MF, Farina D (2006) Optimal wavelets for biomedical signal compression. Med Biol Eng Comput 44(7):561–568

    Article  PubMed  Google Scholar 

  27. Pattichis CS, Pattichis MS (1999) Time-scale analysis of motor unit action potentials. IEEE Trans Biomed Eng 46:1320–1329

    Article  CAS  PubMed  Google Scholar 

  28. Pope MH, Aleksiev A, Panagiotacopulos ND, Lee JS, Wilder DG, Friesen K, Stielau W, Goel VK (2000) Evaluation of low back muscle surface EMG signals using wavelets. Clin Biomech 15:567–573

    Article  CAS  Google Scholar 

  29. Rainoldi A, Galardi G, Maderna L, Comi G, Lo Conte L, Merletti R (1999) Repeatability of surface EMG variables during voluntary isometric contractions of the biceps brachii muscle. J Electromyogr Kinesiol 9:105–119

    Article  CAS  PubMed  Google Scholar 

  30. Rau G, Disselhorst-Klug C (1997) Principles of high-spatial-resolution surface EMG (HSR-EMG): single motor unit detection and application in the diagnosis of neuromuscular disorders. J Electromyogr Kinesiol 7:233–239

    Article  PubMed  Google Scholar 

  31. Rau G, Schulte E, Disselhorst-Klug C (2004) From cell to movement: to what answers does EMG really contribute? J Electromyogr Kinesiol 14:611–617

    Article  CAS  PubMed  Google Scholar 

  32. Roeleveld K, Sandberg A, Stĺlberg EV, Stegeman DF (1998) Motor unit size estimation of enlarged motor units with surface electromyography. Muscle Nerve 21:878–886

    Article  CAS  PubMed  Google Scholar 

  33. Schillings ML, Kalkman JS, Janssen HMHA, van Engelen BGM, Bleijenberg G, Zwarts MJ (2007) Experienced and physiological fatigue in neuromuscular disorders. Clin Neurophysiol 118:292–300

    Article  CAS  PubMed  Google Scholar 

  34. Stalberg E, Karlsson L (2001) Simulation of EMG in pathological situations. Clin Neurophysiol 112:869–878

    Article  CAS  PubMed  Google Scholar 

  35. Strang G, Nguyen T (1995) Wavelets and filter banks. Cambridge Press, Wellesley

    Google Scholar 

  36. Wang G, Wang Z, Chen W, Zhuang J (2006) Classification of surface EMG signals using optimal wavelet packet method based on Davies-Bouldin criterion. Med Biol Eng Comput 44(10):865–872

    Article  PubMed  Google Scholar 

  37. Wimalaratna HS, Tooley MA, Churchill E, Preece AW, Morgan HM (2002) Quantitative surface EMG in the diagnosis of neuromuscular disorders. Electromyogr Clin Neurophysiol 42:167–174

    PubMed  Google Scholar 

  38. Yaar I, Niles L (1992) Muscle fiber conduction velocity and mean power spectrum frequency in neuromuscular disorders and in fatigue. Muscle Nerve 15:780–787

    Article  CAS  PubMed  Google Scholar 

  39. Zwarts MJ, Stegeman DF (2003) Multichannel surface EMG: basic aspects and clinical utility. Muscle Nerve 28:1–17

    Article  PubMed  Google Scholar 

  40. Zwarts MJ, Drost G, Stegeman DF (2000) Recent progress in the diagnostic use of surface EMG for neurological diseases. J Electromyogr Kinesiol 10:287–291

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported by the Slovenian Ministry of Higher Education, Science and Technology (Contract No. 1000-05-310083 and Programme Funding P2-0041) and bilateral Slovenian-Cypriot research project DePaSSE (Detection of pathological changes in sEMGs using statistical and entropy-based approaches).

Author information

Authors and Affiliations

  1. Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, SI-2000, Maribor, Slovenia

    Rok Istenič & Damjan Zazula

  2. The Cyprus Institute of Neurology and Genetics, P.O. Box 23462, CY-1683, Nicosia, Cyprus

    Prodromos A. Kaplanis

  3. Department of Computer Science, University of Cyprus, P.O. Box 20537, CY-1678, Nicosia, Cyprus

    Constantinos S. Pattichis

Authors
  1. Rok Istenič
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Prodromos A. Kaplanis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Constantinos S. Pattichis
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Damjan Zazula
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rok Istenič.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Istenič, R., Kaplanis, P.A., Pattichis, C.S. et al. Multiscale entropy-based approach to automated surface EMG classification of neuromuscular disorders. Med Biol Eng Comput 48, 773–781 (2010). https://doi.org/10.1007/s11517-010-0629-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-010-0629-7

Keywords

Search

Navigation