Skip to main content

Advertisement

SpringerLink
Log in

Gaussian mixture model based clustering of Manual muscle testing grades using surface Electromyogram signals

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

Muscle strength testing has long been an important assessment procedure in rehabilitation setups, though the subjectivity and standardization of this procedure has been widely debated. To address this issue, this study involves the use of Electromyogram (EMG) features that are intuitively related to muscle strength to classify Manual muscle testing (MMT) grades of ‘4 −’, ‘4’, ‘4 + ’ and ‘5’ of the Medical Research Council scale. MMT was performed on Tibialis anterior muscle of 50 healthy participants whose MMT grades and EMG were simultaneously acquired. Chi square goodness of fit and Spectrum Decomposition of Graph Laplacian (SPEC) feature selection algorithms are used in selecting five features, namely Integrated EMG, Root Mean Square EMG, Waveform Length, Wilsons’ amplitude and Energy. Gaussian Mixture Model (GMM) approach is used for unsupervised clustering into one of the grades. Internal cluster evaluation resulted in Silhouette score of 0.76 and Davies Bouldin Index of 0.42 indicating good cluster separability. Agreement between the machine-based grade and manual grade has been quantified using Cohens’ Kappa coefficient. A value of ‘0.44’ has revealed a moderate agreement, with greater differences reported in grading ‘4’ and ‘4 + ’ strength levels. The comparative advantage of EMG based grading over the manual method has been proved. The suggested method can be extended for muscle strength testing of all muscles across different age groups to assist physicians in evaluating patient strength and plan appropriate strength conditioning exercises as a part of rehabilitative assessment.

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
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Juneja P, Hubbard JB (2020) Anatomy, Bony Pelvis and Lower Limb, Tibialis Anterior Muscles. StatPearls Publishing, Treasure Island (FL) https://www.ncbi.nlm.nih.gov/books/NBK513304

  2. Hayes KW, Falconer J (1992) Reliability of hand-held dynamometry and its relationship with manual muscle testing in patients with osteoarthritis in the knee. J Orthop Sports Phys Ther 16(3):145–149

    CAS  PubMed  Google Scholar 

  3. Medical Research Council of the United Kingdom (1976) Aids to the Examination of the peripheral nervous system. The White Rose Press, London

    Google Scholar 

  4. Clarkson HM (2000) Musculoskeletal assessment: joint range of motion and manual muscle strength. Lippincott Williams & Wilkins, Philadelphia

    Google Scholar 

  5. Conable KM, Rosner AL (2011) A narrative review of manual muscle testing and implications for muscle testing research. J Chiropr Med 10(3):157–165

    PubMed  PubMed Central  Google Scholar 

  6. Durfee WK, Iaizzo PA (2006) Rehabilitation and muscle testing. encyclopedia of medical devices and instrumentation https://onlinelibrary.wiley.com/doi/abs/10.1002/0471732877.emd226

  7. Paternostro-Sluga T, Grim-Stieger M, Posch M, Schuhfried O, Vacariu G, Mittermaier C (2008) Reliability and validity of the Medical Research Council (MRC) scale and a modified scale for testing muscle strength in patients with radial palsy. J Rehabil Med 40(8):665–671

    PubMed  Google Scholar 

  8. Fisher MI, Harrington S (2015) Research round-up: manual muscle testing. Rehabil Oncol 33(3):51

    Google Scholar 

  9. Bohannon RW (2019) Considerations and practical options for measuring muscle strength: a narrative review. Biomed Res 2019:8194537. https://doi.org/10.1155/2019/8194537

    Article  Google Scholar 

  10. Le-Ngoc L, Janssen J (2011) Validity and reliability of a hand-held dynamometer for dynamic muscle strength assessment. Rehabil Med, InTech 4:53–66

    Google Scholar 

  11. Kelln BM, Mckeon PO, Gontkof LM, Hertel J (2008) Hand-held dynamometry: reliability of lower extremity muscle testing in healthy, physically active, young adults. J Sport Rehabil 17:160–170

    PubMed  Google Scholar 

  12. Komi P (1986) Training of muscle strength and power: interaction of neuromotoric, hypertrophic, and mechanical factors. Int J Sports Med 7:10–15

    PubMed  Google Scholar 

  13. Li H, Zhao G, Zhou Y, Chen X, Ji Z, Wang L (2014) Relationship of EMG/SMG features and muscle strength level: an exploratory study on tibialis anterior muscles during plantar-flexion among hemiplegia patients. Biomed Eng Online 13(1):1–15

    CAS  Google Scholar 

  14. Ahamed NU, Sundaraj K, Ahmad B, Rahman M, Ali MA, Islam MA (2014) Surface electromyographic analysis of the biceps brachii muscle of cricket bowlers during bowling. Australas Phys Eng Sci Med 37(1):83–95

    PubMed  Google Scholar 

  15. Naik GR, Arjunan S, Kumar D (2011) Applications of ICA and fractal dimension in sEMG signal processing for subtle movement analysis: a review. Australas Phys Eng Sci Med 34(2):179–193

    PubMed  Google Scholar 

  16. Purushothaman G, Vikas R (2018) Identification of a feature selection based pattern recognition scheme for finger movement recognition from multichannel EMG signals. Australas Phys Eng Sci Med 41(2):549–559

    PubMed  Google Scholar 

  17. Drechsler WI, Cramp MC, Scott OM (2006) Changes in muscle strength and EMG median frequency after anterior cruciate ligament reconstruction. Eur J Appl Physiol 98(6):613–623

    PubMed  Google Scholar 

  18. Son J, Ryu J, Ahn S, Kim EJ, Lee JA, Kim Y (2016) Effects of 4-week intensive active-resistive training with an EMG-based exoskeleton robot on muscle strength in older people: a pilot study. Biomed Res Int. https://doi.org/10.1155/2016/1256958

    Article  PubMed  PubMed Central  Google Scholar 

  19. Watanabe K, Kouzaki M, Ogawa M, Akima H, Moritani T (2018) Relationships between muscle strength and multi-channel surface EMG parameters in eighty-eight elderly. J Aging Phys Act 15(1):1–10

    CAS  Google Scholar 

  20. Demura S, Miyaguchi K, Shin S, Uchida Y (2010) Effectiveness of the 1RM estimation method based on isometric squat using a back-dynamometer. J Strength Cond Res 24(10):2742–2748

    PubMed  Google Scholar 

  21. Parai M, Shenoy P, Velayutham S, Seng C, Yee CF (2016) Isometric muscle strength as a predictor of one repetition maximum in healthy adult females: a crossover trial. Clin Transl Orthop 1(2):71–78

    Google Scholar 

  22. O’Neill S, Jaszczak SLT, Steffensen AKS, Debrabant B (2017) Using 4+ to grade near-normal muscle strength does not improve agreement. Chiropr Manual Ther 25:28

    Google Scholar 

  23. Alqudah AM, Albadarneh A, Abu-Qasmieh I, Alquran H (2019) Developing of robust and high accurate ECG beat classification by combining Gaussian mixtures and wavelets features. Australas Phys Eng Sci Med 42(1):149–157

    PubMed  Google Scholar 

  24. Nazarpour K, Al-Timemy AH, Bugmann G, Jackson A (2013) A note on the probability distribution function of the surface electromyogram signal. Brain Res Bull 90(1):88–91

    PubMed  PubMed Central  Google Scholar 

  25. Kendall FB, McCreary EK, Provance PG, Rodgers MM, Romani WA (2005) Muscles testing and function with posture and pain, 5th edn. Lippincott Williams & Wilkins, Baltimore

    Google Scholar 

  26. Hodges PW, Bui BH (1996) A comparison of computer-based methods for the determination of onset of muscle contraction using electromyography.  Electroencephalogr Clin Neurophysiol 101:511–519

    CAS  PubMed  Google Scholar 

  27. Kaiser F, Street S (1990) On a simple algorithm to calculate the ‘energy’ of a signal. IEEE Explore 2(10):381–384

    Google Scholar 

  28. Li X, Zhou P, Aruin AS (2007) Teager–Kaiser Energy operation of surface EMG improves muscle activity onset detection. Ann Biomed Eng 35:1532–1538

    PubMed  Google Scholar 

  29. Farfán FD, Politti JC, Felice CJ (2010) Evaluation of EMG processing techniques using information theory. Biomed Eng Online 9(1):1–18

    Google Scholar 

  30. Phinyomark A, Phukpattaranont P, Limsakul C (2012) Feature reduction and selection for EMG signal classification. Expert Syst Appl 39(8):7420–7431

    Google Scholar 

  31. Zhao Z, Liu H (2008) Spectral feature selection for supervised and unsupervised learning. Proceedings of the 24th International Conference on Machine Learning. ICML, Corvallis, pp 1151–1157

    Google Scholar 

  32. Nadzri AABA, Ahmad SA, Marhaban MH, Jaafar H (2014) Characterization of surface electromyography using time domain features for determining hand motion and stages of contraction. Australas Phys Eng Sci Med 37(1):133–137

    Google Scholar 

  33. Metral S, Cassar G (1981) Relationship between force and integrated EMG activity during voluntary isometric anisotonic contraction. Eur J Appl Physiol 46(2):185–198

    CAS  Google Scholar 

  34. Dennis T, He H, Todd K (2010) Study of stability of time-domain features for electromyographic pattern recognition. J Neuroeng Rehabil 7(21):1–13

    Google Scholar 

  35. Al-Angari HM, Kanitz G, Tarantino S, Cipriani C (2016) Distance and mutual information methods for EMG feature and channel subset selection for classification of hand movements. Biomed Signal Process Control 27:24–31

    Google Scholar 

  36. Bishop CM (2006) Pattern recognition and machine learning. Springer, New York

    Google Scholar 

  37. Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65

    Google Scholar 

  38. Davies DL, Bouldin DW (1979) A cluster separation method. IEEE Trans Pattern Anal Mach Intell 1(2):224–227

    CAS  PubMed  Google Scholar 

  39. Raj A, Cai C, Xie X, Palacios E, Owen J, Mukherjee P, Nagarajan S (2019) Spectral graph theory of brain oscillations. Biorxiv. https://doi.org/10.1101/589176

    Article  Google Scholar 

  40. Feng D, Chen F, Xu W (2013) Efficient leave-one-out strategy for supervised feature selection. Tsinghua Sci Technol 18(6):629–635

    Google Scholar 

  41. Al-Omar S, Diab A, Nader N, Khalil M, Karlsson B, Marque C (2015) Detecting labor using graph theory on connectivity matrices of uterine EMG. 37th Annual International conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, Milan, pp 2195–2198

    Google Scholar 

  42. Tootooni MS, Rao PK, Chou CA, Kong Z (2018) A spectral graph theoretic approach for monitoring multivariate time series data from complex dynamical processes. IEEE Trans Autom Sci Eng 15(1):127–144

    Google Scholar 

  43. Dolnicar S (2002) A Review of unquestioned standards in using cluster analysis for data-driven market segmentation. Proceedings of the Australian and New Zealand marketing academy conference. Deakin University, Melbourne

    Google Scholar 

  44. Siddiqui K (2013) Heuristics for sample size determination in multivariate statistical techniques. World Appl Sci J 27(2):285–287

    Google Scholar 

  45. Formann AK (1984) The latent-class analysis: introduction to theory and application. Beltz, Weinheim

    Google Scholar 

  46. Watanabe K, Kouzaki M, Ogawa M, Akima H, Moritani T (2018) Relationships between muscle strength and multi-channel surface EMG parameters in eighty-eight elderly. Eur Rev Aging Phys Act 15:3

    PubMed  PubMed Central  Google Scholar 

  47. Marson RA (2012) Relationships between surface electromyography and strength during isometric ramp contractions. Computational intelligence in electromyography analysis—a perspective on current applications and future challenges. Rijeka, InTech, pp 53–64

    Google Scholar 

  48. Chaffin DB, Lee M, Freivalds A (1980) Muscle strength assessment from EMG analysis. Med Sci Sports Exerc 12(3):205–211

    CAS  PubMed  Google Scholar 

  49. Kuthe C, Uddanwadiker RV, Ramteke AA (2018) Surface electromyography based method for computing muscle strength and fatigue of biceps brachii muscle and its clinical implementation. Inform Med 12:34–43

    Google Scholar 

  50. Meldrum D, Cahalane E, Conroy R, Fitzgerald D, Hardiman O (2007) Maximum voluntary isometric contraction: Reference values and clinical application. Amyotroph Lateral Scler 8(1):47–55

    PubMed  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the volunteers who participated in the study. We are also obliged to Dr.Saraswathy, for having taken special interest in the study and Dr.Sathish, physiotherapist who helped in the experimental protocol and evaluated all our subjects.

Funding

There is no funding/grant received from any funding agency.

Author information

Authors and Affiliations

  1. Department of ECE, Anna University, Chennai, India

    S. Saranya & S. Poonguzhali

  2. Institute of Advanced Spine Sciences, Gleaneagles Global Health City, Chennai, India

    S. Karunakaran

Authors
  1. S. Saranya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. Poonguzhali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Karunakaran
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Saranya.

Ethics declarations

Conflict of interest

The authors do not have conflicts of interest to disclose.

Ethical approval

All procedures performed in this study involving human participants were in accordance with the ethical standards of the Institutional Ethics Committee (Global Health City Chennai, Ref. no. HR/2017/MS/001) and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix 1

Integral EMG (IEMG)

IEMG represents the integral of rectified EMG signal. It gives information on the nature of muscle fiber recruitment and the strength of contraction [13, 33]

$$IEMG=\sum_{j=1}^{J-1}\left|{x}_{j}\right|$$

where xj is the rectified EMG signal in window segment j and J is the total no. of segments.

Root Mean square (RMS) EMG

As the name suggests, it corresponds to the root mean square value of the EMG segment in consideration. RMS has been related to constant force in isometric contraction [32, 43].

$$RMS=\sqrt{\frac{1}{J }{\sum }_{j=1}^{J}{{x}_{j}}^{2}}$$

Waveform Length (WL)

It is the cumulative length of the waveform within the given EMG time segment. WL gives insight into the complexity of the signal as contraction progresses and hence an optimal indicator of muscle strength [31, 34].

$$WL=\sum_{j=1}^{J-1}\left|{x}_{j+1}-{x}_{j}\right|$$

Signal Energy (E)

This feature also known as Simple square integral (SSI) or integral square [35] represents the energy contained in the signal. It is the sum of squared value of absolute EMG signal.

$$E=\sum_{j=1}^{J-1}{\left|{x}_{j}\right|}^{2}$$

Willisons’/Wilsons’ Amplitude (WAMP)

It is the number of times that the difference between two adjacent amplitude values exceed a predefined threshold [31]. It is an indirect indicator of Motor Unit Firing rate and therefore a good estimator of muscle strength information.

$$WAMP=\sum_{j=1}^{J-1}f\left(\left|{x}_{j+1}-{x}_{j}\right|\right)$$

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Saranya, S., Poonguzhali, S. & Karunakaran, S. Gaussian mixture model based clustering of Manual muscle testing grades using surface Electromyogram signals. Phys Eng Sci Med 43, 837–847 (2020). https://doi.org/10.1007/s13246-020-00880-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-020-00880-5

Keywords

Search

Navigation