Classification of Myopathy and Normal Electromyogram (EMG) Data with a New Deep Learning Architecture

Abstract

Electromyograms (EMG) are recorded movements of nerves and muscles that help diagnose muscles and nerve-related disorders. It is frequently used in the diagnosis of neuromuscular diseases such as myopathy, which causes many changes in EMG signal properties. The most useful auxiliary test in the diagnosis of myopathy is EMG. Therefore, it has become imperative to identify computer-assisted anomalies with full accuracy and to develop an efficient classifier. In this study, a new machine learning method with a deep learning architecture that can score normal and myopathy EMG from the EMGLAB database is proposed. Using the discrete wavelet transform Coiflets 5 (Coif 5) wavelet, the EMG signals are decomposed into subbands and various statistical features are obtained from the wavelet coefficients. The success rates of the decision tree C4.5 algorithm, which is one of the traditional learning architectures, and the Long Short-term Memory (LSTM) algorithm, which is one of the deep learning architectures, were compared. Unlike the studies in the literature, with the LSTM algorithm, a 100% success rate was achieved with the proposed model. In addition, a real-time approach is presented by analyzing the test data classification time of the model.

Keywords

• Deep learning
• EMG
• Myopathy
• Neuromuscular disorder
• Wavelet.

References

1. [1] Frederikse A., “The role of different EMG methods in evaluating myopathy.” Clinical Neurophysiology 2006, 117(6), 1173-1189.
2. [2] Dubey R., Kumar M, Upadhyay A, Pachori RB. “Automated diagnosis of muscle diseases from EMG signals using empirical mode decomposition based method.” Biomedical Signal Processing and Control 2022, 71, 103098.
3. [3] Torres-Castillo J.R., López-López C.O., Padilla-Castañeda M.A., “Neuromuscular disorders detection through time-frequency analysis and classification of multi-muscular EMG signals using Hilbert-Huang transform.” Biomedical Signal Processing and Control 2022, 71, 103037.
4. [4] Bentick G., Fairley J., Nadesapillai S., Wicks I., Day J., “Defining the clinical utility of PET or PET-CT in idiopathic inflammatory myopathies, A systematic literature review.” Seminars in Arthritis and Rheumatism 2022, 57, 152107.
5. [5] Kukker A., Sharma R., Malik H. “Forearm movements classification of EMG signals using Hilbert Huang transform and artificial neural networks.” IEEE 7th Power India International Conference (PIICON) 2016, 1-6.
6. [6] Bakiya A., Anitha A., Sridevi T., Kamalanand K., Classification of myopathy and amyotrophic lateral sclerosis electromyograms using bat algorithm and deep neural networks. Behavioural Neurology 2022, 3517872.
7. [7] Belkhou A., Achmamad A., Jbari A., “Myopathy detection and classification based on the continuous wavelet transform.” Journal of Communıcatıons Software and Systems 2019, 15(4), 336-342.
8. [8] Patidar M., Jain N., Parikh A., “Classification of normal and myopathy EMG signals using BP neural network.” International Journal of Computer Applications 2013, 69(8), 12-16.

9. [9] Jose S., George S.T., Subathra MSP, Handiru VS. “Robust classification of intramuscular EMG signals to aid the diagnosis of neuromuscular disorders.” Engineering in Medicine and Biology 2020, 1, 235-242.
10. [10] Belkhou A., Jbari A., Badlaoui O.E., “A computer-aided-diagnosis system for neuromuscular diseases using mel frequency cepstral coefficients.” Scientific African 2021, 13, e00904.
11. [11] Nikolic M., “Detailed analysis of clinical electromyography signals EMG decomposition, findings and firing pattern analysis in controls and patients with myopathy and amytrophic lateral sclerosis,” PhD Thesis 2021. Faculty of Health Science, University of Copenhagen.
12. [12] Hurtik P., Molek V., Hula H., “Data preprocessing technique for neural networks based on ımage represented by a fuzzy function.” in IEEE Transactions on Fuzzy Systems 2020, 28(7), 1195-1204.
13. [13] Tuncer E., Bolat E.D. “EEG signal based sleep stage classification using discrete wavelet transform.” International Conference on Chemistry, Biomedical and Environment Engineering (ICCBEE'14) 2014, 57-61.
14. [14] Tuncer E., Bolat E.D. “Classification of epileptic seizures from electroencephalogram (EEG) data using bidirectional short-term memory (Bi-LSTM) network architecture.” Biomedical Signal Processing and Control 2022, 73, 103462.
15. [15] Phinyomark A., Quaine F., Charbonnier S., Serviere C., Tarpin-Bernard F., Laurillau Y., “Feature extraction of the first difference of EMG time series for EMG pattern recognition.” Computer Methods and Programs in Biomedicine 2014, 117(2), 247-256.
16. [16] Tuncer E., “Ictal-interictal epileptic state classification with traditional and deep learning architectures.” International Journal of Research Publication and Reviews 2022, 3(9), 1972-1977.
17. [17] Yilmaz M. "Wavelet Based and Statistical EEG Analysis in Patients with Schizophrenia." Traitement du Signal, 2021, 38(5), 1477-1483.
18. [18] Constable R., Thornhill R.J., Pandv M.G., “Using the continuous discrete wavelet transform for time-frequency analysis of the surface EMG signal.” Journal of Biomechanics 1994, 27(6), 723.
19. [19] Oner IV, Yesilyurt M.K., Yilmaz E.C., “Wavelet analysis techniques and application areas.” Ordu University Journal of Science and Tecnology 2017, 7(1), 42-56.
20. [20] URL , https,//www.mathworks.com/help/wavelet/gs/introduction-to-the-wavelet-families.html#f3-998398.
21. [21] Inik O., Ulker E., “Deep learning and deep learning models used in ımage analysis.” Gaziosmanpasa Journal of Scientific Research 2017, 6(3), 85-104.
22. [22] Tosunoglu E., Yılmaz R., Ozeren E., Saglam Z., “Machine learning in education, a study on current trends in researchs.” Journal of Ahmet Kelesoglu Education Faculty 2021, 3(2), 178-199.
23. [23] Gumuscu A., Tasaltin R., Aydilek I.B. “C4.5 decision tree pruning using genetic algorithm.” Dicle University Journal of the Institute of Natural and Applied Science 2016, 5(2), 77-80.
24. [24] Kokver Y, Barıscı N., Ciftci A., Ekmekci Y., “Determining affecting factors of hypertension with data mining techniques.” NWSA-Engineering Sciences 2014, 9(2), 15-25.
25. [25] Meng X., Zhang P., Xu Y., Xie H. “Construction of decision tree based on C4.5 algorithm for online voltage stability assessment.” International Journal of Electrical Power & Energy Systems 2020, 118, 105793.
26. [26] Gokgoz E, Subasi A. “Comparison of decision tree algorithms for EMG signal classification using DWT.” Biomedical Signal Processing and Control 2015, 18, 138-144.
27. [27] Tuncer E., Bolat E.D., “Channel based epilepsy seizure type detection from electroencephalography (EEG) signals with machine learning techniques.” Biocybernetics and Biomedical Engineering, 2022, 42, 575– 595.
28. [28] Arslankaya S., Toprak S., “Using machine learning and deep learning algorithms for stock price prediction.” International Journal of Engineering Research and Development 2021, 13(1), 178-192.
29. [29] Supakar R., Satvaya P., Chakrabarti P., “A deep learning based model using RNN-LSTM for the Detection of Schizophrenia from EEG data.” Computers in Biology and Medicine 2022, 151,106225.
30. [30] Vapnik V.N, “Methods of Pattern Recognition: In The Nature of Statistical Learning Theory.” Springer, 2000, New York-USA, 123–180.
31. [31] Kecman V., “Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models.” MIT Press, 2001, Cambridge, MA-USA, 121-189.
32. [32] Wu X, Kumar V, Ross Q.J., Ghosh J., Yang Q., Motoda H., Steinberg D., “Top 10 Algorithms in Data Mining.” In Knowledge and Information Systems, 2008, 14 (1), 1-37.
33. [33] Cover T., Hart P., “Nearest Neighbor Pattern Classification.” IEEE Transactions on Information Theory, 1967, 21-27.
34. [34] Demir F., “Deep autoencoder-based automated brain tumor detection from MRI data. Artificial Intelligence-Based Brain-Computer Interface” Academic Press, 2022, 317-351.
35. [35] Fawcett T. “An introduction to ROC analysis. Pattern Recognition Letters” 2006, 27(8), 861-874.
36. [36] Bue B.D., Merényi E., Killian J., “Classification and diagnosis of myopathy from EMG signals.” 2nd Workshop on Data Mining for Medicine and Healthcare, in Conjunction with the 13th SIAM International Conference on Data Mining, 2013, Austin, TX.
37. [37] Belkhou A., Achmamad A., Jbari A., “Classification and diagnosis of myopathy EMG signals using the continuous wavelet transform.” Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) 2019, 1-4. DOI, 10.1109/EBBT.2019. 8742051.