PREDICTION OF CERVICAL DISC HERNIATION DISEASE UTILIZING TRAPEZIUS sEMG SIGNALS WITH MACHINE LEARNING TECHNIQUES BASED ON FREQUENCY DOMAIN FEATURE EXTRACTION

Yıl 2023, Cilt: 11 Sayı: 1, 205 - 219, 01.03.2023

Burak Yılmaz Güzin Özmen Hakan Ekmekci

https://doi.org/10.36306/konjes.1185629

Öz

Cervical disk herniation (CDH) is a disease that affects the quality of life of many people due to the neck pain it causes. The aim of this study was to develop an automatic prediction system to aid in diagnosis by evaluating the change in the surface electrical activity of the trapezius muscle in SDH disease in order to find an answer to the question: 'Can the surface electromyogram (sEMG) recorded from the trapezius muscle be an effective indicator for the diagnosis of SDH disease?'. To this end, a dataset will be created using preprocessing and feature extraction methods from sEMG signals from CDH patients and healthy individuals. In the first step, the Savitsky-Golay filter is used to denoise the sEMG signals and the dominant frequency signals between 20 and 150 Hz are included in the study using the Butterworth filter design. Twenty PSD-based features in the frequency domain were then obtained from the signals to which we applied the Burg method. Eleven of the most significant features based on the information gain, gain ratio, and Gini values are selected to be submitted to the classifiers. 80% of all new feature areas are used for classification and the rest for prediction. The best classification accuracy of 91.6% was obtained with the Tree classifier using 10-fold cross-validation for classification. In addition, neural networks and CN2 rule inducer provided 87.5% classification accuracy for prediction using 20% of the remaining data that the classifiers had not seen before. The experimental results demonstrate that the trapezius muscle has different surface electrical activity in CDH patients and healthy subjects and that the frequency domain characteristics of this activity are important for disease prediction.

Anahtar Kelimeler

EMG, Machine Learning, Classification, Prediction, Frequency Domain

Frekans Alanı Öznitelik Çıkarımına Dayalı Makine Öğrenme Teknikleri ile Trapezius Yüzey EMG Sinyallerini Kullanarak Servikal Disk Fıtığı Hastalığının Tahmini

Öz

Servikal Disk Hernisi (SDH), neden olduğu boyun ağrısı ile birçok kişinin günlük yaşam kalitesini düşüren bir hastalıktır. Asıl sorumuz şudur: ‘Trapezius kasından alınan yüzey Elektromiyogram (yEMG) sinyali SDH hastalığının tanısında etkili bir gösterge olabilir mi?’. Bu çalışma, SDH hastalığının Trapezius kasındaki yüzey elektriksel aktivite değişimini değerlendirerek tanıya yardımcı olan otomatik bir tahmin sistemi tasarlamayı amaçlamaktadır. Bu amaçla, SDH hastalarından ve sağlıklı deneklerden toplanan yEMG sinyallerinden ön işleme ve özellik çıkarma yöntemleri kullanılarak bir veri seti hazırlanmıştır. İlk aşamada, yEMG sinyallerini gürültüden arındırmak için Savitsky-Golay filtresi kullanılmış ve Butterworth filtre tasarımı ile 20-150 Hz aralığındaki baskın frekans sinyalleri çalışmaya dahil edilmiştir. Daha sonra Burg yöntemi uygulanan sinyallerden frekans alanında yirmi PSD tabanlı öznitelik elde edilmiştir. Bilgi Kazancı, Kazanç Oranı ve Gini değerlerine dayalı en önemli on bir özellik, sınıflandırıcılara sunulmak üzere seçilmiştir. Tüm yeni özellik uzaylarının %80' i sınıflandırma için, geri kalanı ise tahmin için kullanılmıştır. Sınıflandırma için 10 kat çapraz doğrulama uygulanarak Ağaç sınıflandırıcı ile %91.6' lık en iyi sınıflandırma doğruluğu elde edilmiştir. Ayrıca, Sinir ağları ve CN2 kuralı başlatıcısı, sınıflandırıcıların daha önce görmediği kalan verilerin %20' sini kullanarak tahmin için %87.5 sınıflandırma doğruluğu sağlamıştır. Deneysel sonuçlar, trapezius kasının SDH hastalarında ve sağlıklı kişilerde farklı yüzey elektriksel aktivitesine sahip olduğunu ve bu aktivitenin frekans alanı özelliklerinin hastalık tahmininde ayırt edici olduğunu ortaya koymaktadır.

Anahtar Kelimeler

EMG, Makine Öğrenimi, Sınıflandırma, Tahmin, Frekans alanı

Kaynakça

• [1] Mochida, Kiyoshi, Hiromichi Komori, Atsushi Okawa, Takeshi Muneta, Hirotaka Haro, and Kenichi Shinomiya. “Regression of Cervical Disc Herniation Observed on Magnetic Resonance Images.” Spine 23 (9): 990–95. https://doi.org/10.1097/00007632-199805010-00005, 1998.
• [2] Yeung, Jacky T., John I. Johnson, and Aftab S. Karim. “Cervical Disc Herniation Presenting with Neck Pain and Contralateral Symptoms: A Case Report.” Journal of Medical Case Reports 6 (1): 166. https://doi.org/10.1186/1752-1947-6-166, 2012.
• [3] Sharrak, Samir, and Yasir Al Khalili. “Cervical Disc Herniation.” StatPearls [Internet], 2020.
• [4] Kamibayashi, Lynne K, and Frances J.R. Richmond. “Morphometry of Human Neck Muscles.” Spine 23 (12): 1314–23. https://doi.org/10.1097/00007632-199806150-00005, 1998.
• [5] Takebe, Kyoichi, Mathias Vitti, and John V Basmajian. “The Functions of Semispinalis Capitis and Splenius Capitis Muscles: An Electromyographic Study.” The Anatomical Record 179 (4): 477–80. https://doi.org/10.1002/ar.1091790407, 1974.
• [6] Bernhardt, P, H-J. Wilke, K.H. Wenger, B Jungkunz, A Böhm, and L.E. Claes. “Multiple Muscle Force Simulation in Axial Rotation of the Cervical Spine.” Clinical Biomechanics 14 (1): 32–40. https://doi.org/10.1016/S0268-0033(98)00031-X, 1999.
• [7] Sommerich, Carolyn M., Sharon M.B. Joines, Veerle Hermans, and Samuel D. Moon. “Use of Surface Electromyography to Estimate Neck Muscle Activity.” Journal of Electromyography and Kinesiology 10 (6): 377–98. https://doi.org/10.1016/S1050-6411(00)00033-X, 2000.
• [8] Bronzino, Joseph D. Biomedical Engineering Handbook 2. Vol. 2. Springer Science & Business Media, 2000.
• [9] Luca, Carlo J De. “The Use of Surface Electromyography in Biomechanics.” Journal of Applied Biomechanics 13 (2): 135–63. https://doi.org/10.1123/jab.13.2.135, 1997.
• [10] Subasi, Abdulhamit. “Classification of EMG Signals Using PSO Optimized SVM for Diagnosis of Neuromuscular Disorders.” Computers in Biology and Medicine 43 (5): 576–86. https://doi.org/10.1016/j.compbiomed.2013.01.020, 2013.
• [11] Subasi, Abdulhamit, Emine Yaman, Yara Somaily, Halah A. Alynabawi, Fatemah Alobaidi, and Sumaiah Altheibani. “Automated EMG Signal Classification for Diagnosis of Neuromuscular Disorders Using DWT and Bagging.” Procedia Computer Science 140: 230–37. https://doi.org/10.1016/j.procs.2018.10.333, 2018.
• [12] Jose, Shobha, S Thomas George, M S P Subathra, Vikram Shenoy Handiru, Poornaselvan Kittu Jeevanandam, Umberto Amato, and Easter Selvan Suviseshamuthu. “Robust Classification of Intramuscular EMG Signals to Aid the Diagnosis of Neuromuscular Disorders.” IEEE Open Journal of Engineering in Medicine and Biology 1: 235–42. https://doi.org/10.1109/OJEMB.2020.3017130, 2020.
• [13] Akef Khowailed, Iman, and Ahmed Abotabl. “Neural Muscle Activation Detection: A Deep Learning Approach Using Surface Electromyography.” Journal of Biomechanics 95 (October): 109322. https://doi.org/10.1016/j.jbiomech.2019.109322, 2019.
• [14] Azzerboni, Bruno, Giovanni Finocchio, Maurizio Ipsale, Fabio La Foresta, and Francesco Carlo Morabito. “A New Approach to Detection of Muscle Activation by Independent Component Analysis and Wavelet Transform.” In Italian Workshop on Neural Nets, 109–16. Springer. https://doi.org/10.1007/3-540-45808-5_11, 2002.
• [15] Karthick, P.A., Diptasree Maitra Ghosh, and S Ramakrishnan. “Surface Electromyography Based Muscle Fatigue Detection Using High-Resolution Time-Frequency Methods and Machine Learning Algorithms.” Computer Methods and Programs in Biomedicine 154 (February): 45–56. https://doi.org/10.1016/j.cmpb.2017.10.024, 2018.
• [16] Subasi, Abdulhamit, and M Kemal Kiymik. “Muscle Fatigue Detection in EMG Using Time–Frequency Methods, ICA and Neural Networks.” Journal of Medical Systems 34 (4): 777–85. https://doi.org/10.1007/s10916-009-9292-7, 2010.
• [17] Silva, Luís, João Rocha Vaz, Maria António Castro, Pedro Serranho, Jan Cabri, and Pedro Pezarat-Correia. “Recurrence Quantification Analysis and Support Vector Machines for Golf Handicap and Low Back Pain EMG Classification.” Journal of Electromyography and Kinesiology 25 (4): 637–47. https://doi.org/10.1016/j.jelekin.2015.04.008, 2015.
• [18] Ostojić, Saša, Stanislav Peharec, Vedran Srhoj-Egekher, and Mario Cifrek. “Differentiating Patients with Radiculopathy from Chronic Low Back Pain Patients by Single Surface EMG Parameter.” Automatika 59 (3–4): 400–407. https://doi.org/10.1080/00051144.2018.1553669, 2018.
• [19] Jiménez-Grande, David, S. Farokh Atashzar, Eduardo Martinez-Valdes, Alessandro Marco De Nunzio, and Deborah Falla. “Kinematic Biomarkers of Chronic Neck Pain Measured during Gait: A Data-Driven Classification Approach.” Journal of Biomechanics 118 (March): 110190. https://doi.org/10.1016/j.jbiomech.2020.110190, 2021.
• [20] Walsh, Kevin A, Sean P Sanford, Brian D Collins, Noam Y Harel, and Raviraj Nataraj. “Performance Potential of Classical Machine Learning and Deep Learning Classifiers for Isometric Upper-Body Myoelectric Control of Direction in Virtual Reality with Reduced Muscle Inputs.” Biomedical Signal Processing and Control 66 (April): 102487. https://doi.org/10.1016/j.bspc.2021.102487, 2021.
• [21] Kumar, Shrawan, and Narasimha Prasad. “Cervical EMG Profile Differences between Patients of Neck Pain and Control.” Disability and Rehabilitation 32 (25): 2078–87. https://doi.org/10.3109/09638288.2010.481029, 2010.
• [22] Ozmen, Guzin, and Ahmet Hakan Ekmekci. “Classification of Cervical Disc Herniation Disease Using Muscle Fatigue Based Surface EMG Signals by Artificial Neural Networks.” International Journal of Intelligent Systems and Applications in Engineering 4 (5): 256–62. https://doi.org/10.18201/ijisae.2017533901, 2017.
• [23] Phinyomark, Angkoon, Pornchai Phukpattaranont, and Chusak Limsakul. “Feature Reduction and Selection for EMG Signal Classification.” Expert Systems with Applications 39 (8): 7420–31. https://doi.org/10.1016/j.eswa.2012.01.102, 2012.
• [24] Qin, Pengjie, and Xin Shi. “Evaluation of Feature Extraction and Classification for Lower Limb Motion Based on SEMG Signal.” Entropy 22 (8). https://doi.org/10.3390/E22080852, 2020.
• [25] Katsis, C.D., Y. Goletsis, A. Likas, D.I. Fotiadis, and I. Sarmas. “A Novel Method for Automated EMG Decomposition and MUAP Classification.” Artificial Intelligence in Medicine 37 (1): 55–64. https://doi.org/10.1016/j.artmed.2005.09.002, 2006.
• [26] Rasheed, Sarbast, Daniel Stashuk, and Mohamed Kamel. “A Software Package for Interactive Motor Unit Potential Classification Using Fuzzy K-NN Classifier.” Computer Methods and Programs in Biomedicine 89 (1): 56–71. https://doi.org/10.1016/j.cmpb.2007.10.006, 2008.
• [27] Gokgoz, E., & Subasi. “Comparison of Decision Tree Algorithms for EMG Signal Classification Using DWT.” Biomedical Signal Processing and Control 18: 138–44. https://doi.org/10.1016/j.bspc.2014.12.005, 2015.
• [28] Kamali, Tahereh, Reza Boostani, and Hossein Parsaei. “A Multi-Classifier Approach to MUAP Classification for Diagnosis of Neuromuscular Disorders.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 22 (1): 191–200. https://doi.org/10.1109/TNSRE.2013.2291322, 2014.
• [29] Artameeyanant, Patcharin, Sivarit Sultornsanee, and Kosin Chamnongthai. “An EMG-Based Feature Extraction Method Using a Normalized Weight Vertical Visibility Algorithm for Myopathy and Neuropathy Detection.” SpringerPlus 5 (1): 2101. https://doi.org/10.1186/s40064-016-3772-2., 2016
• [30] Hazarika, Anil, Lachit Dutta, Meenakshi Boro, Mausumi Barthakur, and Manabendra Bhuyan. “An Automatic Feature Extraction and Fusion Model: Application to Electromyogram (EMG) Signal Classification.” International Journal of Multimedia Information Retrieval 7 (3): 173–86. https://doi.org/10.1007/s13735-018-0149-z, 2018.
• [31] Istenič, Rok, Prodromos A. Kaplanis, Constantinos S. Pattichis, and Damjan Zazula. “Multiscale Entropy-Based Approach to Automated Surface EMG Classification of Neuromuscular Disorders.” Medical & Biological Engineering & Computing 48 (8): 773–81. https://doi.org/10.1007/s11517-010-0629-7, 2010.
• [32] Barmpakos, Dimitrios, Prodormos Kaplanis, Stavros A. Karkanis, and Constantinos Pattichis. “Classification of Neuromuscular Disorders Using Features Extracted in the Wavelet Domain of SEMG Signals: A Case Study.” Health and Technology 7 (1): 33–39. https://doi.org/10.1007/s12553-016-0153-3, 2017.
• [33] Moore, Keith L, A M R Agur, and Arthur F Dalley. Essential Clinical Anatomy. Baltimore, MD: Lippincott Williams & Wilkins, 2011.
• [34] Halaki, Mark. “Normalization of EMG Signals: To Normalize or Not to Normalize and What to Normalize To?” In , edited by Karen Ginn ED1 - Ganesh R Naik, Ch. 7. Rijeka: IntechOpen. https://doi.org/10.5772/49957, 2012.
• [35] Awal, Abdul, Sheikh Shanawaz Mostafa, and Mohiuddin Ahmad. “Performance Analysis of Savitzky-Golay Smoothing Filter Using ECG Signal.” International Journal of Computer and Information Technology 01 (02): 24–29, 2011.
• [36] Bucy, R S. “Burg Technique.” In Lectures on Discrete Time Filtering, 47–54. New York, NY: Springer New York. https://doi.org/10.1007/978-1-4613-8392-5_5, 1994.
• [37] Subasi, A. Practical guide for biomedical signals analysis using machine learning techniques: A MATLAB based approach. Academic Press, 2019
• [38] Altunkaya, Sabri, Sadık Kara, Niyazi Görmüş, and Saadetdin Herdem. “Comparison of First and Second Heart Sounds after Mechanical Heart Valve Replacement.” Computer Methods in Biomechanics and Biomedical Engineering 16 (4): 368–80. https://doi.org/10.1080/10255842.2011.623672, 2013.
• [39] Altunkaya, Sabri. “Yaşlılarda Düşme Riskini Değerlendirmek Için İvmelenme Sinyalinin Frekans Domeni Özellikleri.” European Journal of Science and Technology, no. August: 150–55. https://doi.org/10.31590/ejosat.779590, 2020.
• [40] Wu, Xindong, Vipin Kumar, Quinlan J. Ross, Joydeep Ghosh, Qiang Yang, Hiroshi Motoda, Geoffrey J. McLachlan, et al. Top 10 Algorithms in Data Mining. Knowledge and Information Systems. Vol. 14. https://doi.org/10.1007/s10115-007-0114-2, 2008.
• [41] Clark, Peter, and Tim Niblett. “The CN2 Induction Algorithm.” Machine Learning 3 (4): 261–83. https://doi.org/10.1023/A:1022641700528, 1989.
• [42] Breiman, Leo. “Random Forests.” Machine Learning 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324, 2001.
• [43] Balamareeswaran, M., and D. Ebenezer. “Denoising of EEG Signals Using Discrete Wavelet Transform Based Scalar Quantization.” Biomedical and Pharmacology Journal 8 (1): 399–406. https://doi.org/10.13005/bpj/627, 2015.
• [44] Powers, David M. W. “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation,” no. January 2011. https://doi.org/10.9735/2229-3981, 2020.
• [45] Chowdhury, Suman Kanti. “Discrete Wavelet Transform Analysis of Surface Electromyography for the Objective Assessment of Neck and Shoulder Muscle Fatigue Discrete Wavelet Transform Analysis of Surface Electromyography for the Objective Assessment of Neck and Shoulder Muscle Fatigue”, Statler College of Engineering and Mineral Resources, Master Thesis, https://doi.org/10.33915/etd.4841, 2012.
• [46] Gokgoz, Ercan, and Abdulhamit Subasi. “Effect of Multiscale PCA De-Noising on EMG Signal Classification for Diagnosis of Neuromuscular Disorders.” Journal of Medical Systems 38 (4): 31. https://doi.org/10.1007/s10916-014-0031-3., 2014.
• [47] Pauk, J. “Different Techniques for EMG Signal Processing.” Journal of Vibroengineering 10 (4): 571–76, 2008.
• [48] Akhundov, Riad, David J. Saxby, Suzi Edwards, Suzanne Snodgrass, Phil Clausen, and Laura E. Diamond. “Development of a Deep Neural Network for Automated Electromyographic Pattern Classification.” Journal of Experimental Biology 222 (5): 1–5. https://doi.org/10.1242/jeb.198101, 2019.
• [49] Siqueira, Ailton Luiz Dias, and Alcimar Barbosa Soares. “A Novel Method for EMG Decomposition Based on Matched Filters.” Revista Brasileira de Engenharia Biomedica 31 (1): 44–55. https://doi.org/10.1590/2446-4740.0643, 2015.