Comparison of selected classification methods based on machine learning as a diagnostic tool for knee joint cartilage damage based on generated vibroacoustic processes

• Autorzy: Karpiński Robert , Krakowski Przemysław , Jonak Józef , Machrowska Anna , Maciejewski Marcin

Identyfikatory

DOI

10.35784/acs-2023-40

• Języki publikacji: EN

Abstrakty

EN

Osteoarthritis is one of the most common cause of disability among elderly. It can affect every joint in human body, however, it is most prevalent in hip, knee, and hand joints. Early diagnosis of cartilage lesions is essential for fast and accurate treatment, which can prolong joint function. Available diagnostic methods include conventional X-ray, ultrasound and magnetic resonance imaging. However, those diagnostic modalities are not suitable for screening purposes. Vibroarthrography is proposed in literature as a screening method for cartilage lesions. However, exact method of signal acquisition as well as classification method is still not well established in literature. In this study, 84 patients were assessed, of whom 40 were in the control group and 44 in the study group. Cartilage status in the study group was evaluated during surgical treatment. Multilayer perceptron - MLP, radial basis function - RBF, support vector method - SVM and naive classifier – NBC were introduced in this study as classification protocols. Highest accuracy (0.893) was found when MLP was introduced, also RBF classification showed high sensitivity (0.822) and specificity (0.821). On the other hand, NBC showed lowest diagnostic accuracy reaching 0.702. In conclusion vibroarthrography presents a promising diagnostic modality for cartilage evaluation in clinical setting with the use of MLP and RBF classification methods.

Słowa kluczowe

EN

vibroacoustic signal; VAG; osteoarthritis; knee joint; kinetic chain; Artificial Neural Network; multilevel perceptron; MLP; Radial Basis Function; RBF; SVM; naive Bayes classifier

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2023
• Tom: Vol. 19, no 4
• Strony: 136--150
• Opis fizyczny: Bibliogr. 52 poz., fig., tab.

Twórcy

autor

Karpiński Robert

• Lublin University of Technology, Faculty of Mechanical Engineering, Department of Machine Design and Mechatronics, Poland

• https://orcid.org/0000-0003-4063-8503

autor

Krakowski Przemysław

• Medical University of Lublin, Chair and Department of Traumatology and Emergency Medicine, Poland, Orthopaedic and Sports Traumatology Department, Carolina Medical Center, Poland

• https://orcid.org/0000-0001-7137-7145

autor

Jonak Józef

• Lublin University of Technology, Faculty of Mechanical Engineering, Department of Machine Design and Mechatronics, Poland

• https://orcid.org/0000-0003-4658-4569

autor

Machrowska Anna

• Lublin University of Technology, Faculty of Mechanical Engineering, Department of Machine Design and Mechatronics, Poland

• https://orcid.org/0000-0003-3289-2421

autor

Maciejewski Marcin

• Lublin University of Technology, Faculty of Electrical Engineering and Computer Science, Institute of Electronics and Information Technology, Poland

• https://orcid.org/0000-0001-9116-5481

Bibliografia

• [1] Andersen, R. E., Arendt-Nielsen, L., & Madeleine, P. (2016). A review of engineering aspects of vibroarthography of the knee joint. Critical Reviews in Physical and Rehabilitation Medicine, 28(1–2), 13–32. https://doi.org/10.1615/CritRevPhysRehabilMed.2016017185
• [2] Ashoorion, V., Sadeghirad, B., Wang, L., Noori, A., Abdar, M., Kim, Y., Chang, Y., Rehman, N., Lopes, L. C., Couban, R. J., Aminilari, M., Malektojari, A., Ghazizadeh, S., Rehman, Y., Ghasemi, M., Adili, A., Guyatt, G. H., & Busse, J. W. (2023). Predictors of persistent post-surgical pain following total knee arthroplasty: A systematic review and meta-analysis of observational studies. Pain Medicine, 24(4), 369–381. https://doi.org/10.1093/pm/pnac154
• [3] Aziz, N., Akhir, E. A. P., Aziz, I. A., Jaafar, J., Hasan, M. H., & Abas, A. N. C. (2020). A study on gradient boosting algorithms for development of AI monitoring and prediction systems. 2020 International Conference on Computational Intelligence (ICCI) (pp. 11–16). IEEE. https://doi.org/10.1109/ICCI51257.2020.9247843
• [4] Barnett, A. J., & Toms, A. D. (2012). Revision total hip and knee replacement. Clinics in Geriatric Medicine, 28(3), 431-446. https://doi.org/10.1016/j.cger.2012.05.008
• [5] Bennasar, M., Setchi, R., Hicks, Y., & Bayer, A. (2014). Cascade classification for diagnosing dementia. 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 2535–2540). IEEE. https://doi.org/10.1109/SMC.2014.6974308
• [6] Bose, B. K. (2007). Neural network applications in power electronics and motor drives - An introduction and perspective. IEEE Transactions on Industrial Electronics, 54(1), 14–33. https://doi.org/10.1109/TIE.2006.888683
• [7] Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, 6. https://doi.org/10.1186/s12864-019-6413-7
• [8] Chih-Wei, H., & Chih-Jen, L. (2002). A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks, 13(2), 415–425. https://doi.org/10.1109/72.991427
• [9] Emadi Andani, M., & Salehi, Z. (2024). An affordable and easy-to-use tool to diagnose knee arthritis using knee sound. Biomedical Signal Processing and Control, 88, 105685. https://doi.org/10.1016/j.bspc.2023.105685
• [10] Figueroa, D., Calvo, R., Vaisman, A., Carrasco, M. A., Moraga, C., & Delgado, I. (2007). Knee chondral lesions: incidence and correlation between arthroscopic and magnetic resonance findings. Arthroscopy: The Journal of Arthroscopic & Related Surgery, 23(3), 312-315. https://doi.org/10.1016/j.arthro.2006.11.015
• [11] Ghahramani, Z., & Kim, H. C. (2003). Bayesian classifier combination. Gatsby Computational Neuroscience Unit University College London.
• [12] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
• [13] Huang, Y., & Li, L. (2011). Naive Bayes classification algorithm based on small sample set. 2011 IEEE International Conference on Cloud Computing and Intelligence Systems (pp. 34–39). IEEE. https://doi.org/10.1109/CCIS.2011.6045027
• [14] Jonak, J., Karpinski, R., Machrowska, A., Krakowski, P., & Maciejewski, M. (2019). A preliminary study on the use of EEMD-RQA algorithms in the detection of degenerative changes in knee joints. IOP Conference Series: Materials Science and Engineering, 710, 012037. https://doi.org/10.1088/1757-899X/710/1/012037
• [15] Karpiński, R. (2022). Knee joint osteoarthritis diagnosis based on selected acoustic signal discriminants using machine learning. Applied Computer Science, 18(2), 71–85. https://doi.org/10.35784/acs-2022-14
• [16] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2021a). Analysis of differences in vibroacoustic signals between healthy and osteoarthritic knees using EMD algorithm and statistical analysis. Journal of Physics: Conference Series, 2130, 012010. https://doi.org/10.1088/1742-6596/2130/1/012010
• [17] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2021b). Estimation of differences in selected indices of vibroacoustic signals between healthy and osteoarthritic patellofemoral joints as a potential non-invasive diagnostic tool. Journal of Physics: Conference Series, 2130, 012009. https://doi.org/10.1088/1742-6596/2130/1/012009
• [18] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2022a). Diagnostics of articular cartilage damage based on generated acoustic signals using ANN - Part I: Femoral-tibial joint. Sensors, 22(6), 2176. https://doi.org/10.3390/s22062176
• [19] Karpiński, R., Krakowski, P., Jonak, J., Machrowska, A., Maciejewski, M., & Nogalski, A. (2022b). Diagnostics of articular cartilage damage based on generated acoustic signals using ANN - Part II: Patellofemoral joint. Sensors, 22(10), 3765. https://doi.org/10.3390/s22103765
• [20] Karpiński, R., Machrowska, A., & Maciejewski, M. (2019). Application of acoustic signal processing methods in detecting differences between open and closed kinematic chain movement for the knee joint. Applied Computer Science, 15(1), 36–48. https://doi.org/10.23743/acs-2019-03
• [21] Kotsiantis, S. B. (2013). Decision trees: A recent overview. Artificial Intelligence Review, 39, 261–283. https://doi.org/10.1007/s10462-011-9272-4
• [22] Krakowski, P., Karpiński, R., Jojczuk, M., Nogalska, A., & Jonak, J. (2021a). Knee MRI underestimates the Grade of cartilage lesions. Applied Sciences, 11(4), 1552. https://doi.org/10.3390/app11041552
• [23] Krakowski, P., Karpiński, R., Jonak, J., & Maciejewski, R. (2021b). Evaluation of diagnostic accuracy of physical examination and MRI for ligament and meniscus injuries. Journal of Physics: Conference Series, 1736, 012027. https://doi.org/10.1088/1742-6596/1736/1/012027
• [24] Krakowski, P., Karpiński, R., Maciejewski, R., & Jonak, J. (2021c). Evaluation of the diagnostic accuracy of MRI in detection of knee cartilage lesions using Receiver Operating Characteristic curves. Journal of Physics: Conference Series, 1736, 012028. https://doi.org/10.1088/1742-6596/1736/1/012028
• [25] Lemon, S. C., Roy, J., Clark, M. A., Friedmann, P. D., & Rakowski, W. (2003). Classification and regression tree analysis in public health: Methodological review and comparison with logistic regression. Annals of Behavioral Medicine, 26(3), 172–181. https://doi.org/10.1207/S15324796ABM2603_02
• [26] Liu, R., Yang, B., Zio, E., & Chen, X. (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108, 33–47. https://doi.org/10.1016/j.ymssp.2018.02.016
• [27] Luque, A., Carrasco, A., Martín, A., & De Las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 216–231. https://doi.org/10.1016/j.patcog.2019.02.023
• [28] Łysiak, A., Froń, A., Bączkowicz, D., & Szmajda, M. (2020). Vibroarthrographic signal spectral features in 5-class knee joint classification. Sensors, 20(17), 5015. https://doi.org/10.3390/s20175015
• [29] Machrowska, A., Karpiński, R., Jonak, J., Szabelski, J., & Krakowski, P. (2020a). Numerical prediction of the component-ratio-dependent compressive strength of bone cement. Applied Computer Science, 16(3), 88-101. https://doi.org/10.23743/acs-2020-24
• [30] Machrowska, A., Karpiński, R., Krakowski, P., & Jonak, J. (2019). Diagnostic factors for opened and closed kinematic chain of vibroarthrography signals. Applied Computer Science, 15(3), 34-44. https://doi.org/10.23743/acs-2019-19
• [31] Machrowska, A., Szabelski, J., Karpiński, R., Krakowski, P., Jonak, J., & Jonak, K. (2020b). Use of Deep Learning Networks and statistical modeling to predict changes in mechanical parameters of contaminated bone cements. Materials, 13(23), 5419. https://doi.org/10.3390/ma13235419
• [32] Meng Joo Er, Shiqian Wu, Juwei Lu, & Hock Lye Toh. (2002). Face recognition with radial basis function (RBF) neural networks. IEEE Transactions on Neural Networks, 13(3), 697–710. https://doi.org/10.1109/TNN.2002.1000134
• [33] Nalband, S., Prince, A., & Agrawal, A. (2018). Entropy‐based feature extraction and classification of vibroarthographic signal using complete ensemble empirical mode decomposition with adaptive noise. IET Science, Measurement & Technology, 12(3), 350–359. https://doi.org/10.1049/iet-smt.2017.0284
• [34] Nevalainen, M. T., Veikkola, O., Thevenot, J., Tiulpin, A., Hirvasniemi, J., Niinimäki, J., & Saarakkala, S. S. (2021). Acoustic emissions and kinematic instability of the osteoarthritic knee joint: Comparison with radiographic findings. Scientific Reports, 11, 19558. https://doi.org/10.1038/s41598-021-98945-2
• [35] Prior, J., Mascaro, B., Shark, L. K., Stockdale, J., Selfe, J., Bury, R., Cole, P., & Goodacre, J. A. (2010). Analysis of high frequency acoustic emission signals as a new approach for assessing knee osteoarthritis. Annals of the Rheumatic Diseases, 69, 929–930. https://doi.org/10.1136/ard.2009.112599
• [36] Rangayyan, R. M., Oloumi, F., Wu, Y., & Cai, S. (2013). Fractal analysis of knee-joint vibroarthrographic signals via power spectral analysis. Biomedical Signal Processing and Control, 8(1), 23-29. https://doi.org/10.1016/j.bspc.2012.05.004
• [37] Riecke, B. F., Christensen, R., Torp-Pedersen, S., Boesen, M., Gudbergsen, H., & Bliddal, H. (2014). An ultrasound score for knee osteoarthritis: A cross-sectional validation study. Osteoarthritis and Cartilage, 22(10), 1675–1691. https://doi.org/10.1016/j.joca.2014.06.020
• [38] Rogala, M., Gajewski, J., & Ferdynus, M. (2019). Numerical analysis of the thin-walled structure with different trigger locations under axial load. IOP Conference Series: Materials Science and Engineering, 710, 012028. https://doi.org/10.1088/1757-899X/710/1/012028
• [39] Rogala, M., Gajewski, J., & Górecki, M. (2021). Study on the effect of geometrical parameters of a hexagonal trigger on energy absorber performance using ANN. Materials, 14(20), 5981. https://doi.org/10.3390/ma14205981
• [40] Schlüter, D. K., Spain, L., Quan, W., Southworth, H., Platt, N., Mercer, J., Shark, L. K., Waterton, J. C., Bowes, M., Diggle, P. J., Dixon, M., Huddleston, J., & Goodacre, J. (2019). Use of acoustic emission to identify novel candidate biomarkers for knee osteoarthritis (OA). PLOS ONE, 14(10), e0223711. https://doi.org/10.1371/journal.pone.0223711
• [41] Shaik, A. B., & Srinivasan, S. (2019). A brief survey on random forest ensembles in classification model. In S. Bhattacharyya, A. E. Hassanien, D. Gupta, A. Khanna & I. Pan (Eds.), International Conference on Innovative Computing and Communications (Vol. 56, pp. 253–260). Springer Singapore. https://doi.org/10.1007/978-981-13-2354-6_27
• [42] Shidore, M. M., Athreya, S. S., Deshpande, S., & Jalnekar, R. (2021). Screening of knee-joint vibroarthrographic signals using time and spectral domain features. Biomedical Signal Processing and Control, 68, 102808. https://doi.org/10.1016/j.bspc.2021.102808
• [43] Singh, J. A., Yu, S., Chen, L., & Cleveland, J. D. (2019). Rates of total joint replacement in the United States: future projections to 2020–2040 using the National Inpatient Sample. The Journal of Rheumatology, 46(9), 1134–1140. https://doi.org/10.3899/jrheum.170990
• [44] Solivetti, F. M., Guerrisi, A., Salducca, N., Desiderio, F., Graceffa, D., Capodieci, G., Romeo, P., Sperduti, I., & Canitano, S. (2016). Appropriateness of knee MRI prescriptions: Clinical, economic and technical issues. La Radiologia Medica, 121, 315-322. https://doi.org/10.1007/s11547-015-0606-1
• [45] Szabelski, J., Karpiński, R., & Machrowska, A. (2022). Application of an Artificial Neural Network in the modelling of heat curing effects on the strength of adhesive joints at elevated temperature with imprecise adhesive mix ratios. Materials, 15(3), 721. https://doi.org/10.3390/ma15030721
• [46] W-Dahl, A., Kärrholm, J., Rogmark, C., Mohaddes, M., Carling, M., Sundberg, M., Bülow, E., Nåtman, J., Carlsen, H., Isaksson, R., & Rolfson, O. (2022). Annual Report 2022. Swedish Arthroplasty Register. https://registercentrum.blob.core.windows.net/refdocs/10.18158/BklrLg8NOo.pdf
• [47] Williams, J., & Pierre-Louis, K. (2024). Osteoarthritis of the Knee. Physician Assistant Clinics, 9(1), 59–69. https://doi.org/10.1016/j.cpha.2023.08.003
• [48] Wu, Y., Cai, S., Yang, S., Zheng, F., & Xiang, N. (2013). Classification of knee joint vibration signals using bivariate feature distribution estimation and maximal posterior probability fecision criterion. Entropy, 15(4), 1375-1387. https://doi.org/10.3390/e15041375
• [49] Wu, Z., & Huang, N. E. (2009). Ensemble empirical mode decomposition: A noise-assisted data analysis method. Advances in Adaptive Data Analysis, 01(01), 1–41. https://doi.org/10.1142/S1793536909000047
• [50] Yang, S., Cai, S., Zheng, F., Wu, Y., Liu, K., Wu, M., Zou, Q., & Chen, J. (2014). Representation of fluctuation features in pathological knee joint vibroarthrographic signals using kernel density modeling method. Medical Engineering & Physics, 36(10), 1305–1311. https://doi.org/10.1016/j.medengphy.2014.07.008
• [51] Zhang, S., Li, X., Zong, M., Zhu, X., & Cheng, D. (2017). Learning k for kNN classification. ACM Transactions on Intelligent Systems and Technology, 8(3), 1–19. https://doi.org/10.1145/2990508
• [52] Zhang, Y. (2012). Support vector machine classification algorithm and its application. In C. Liu, L. Wang, & A. Yang (Eds.), Information Computing and Applications (Vol. 308, pp. 179–186). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-34041-3_27