Application of Recurrence Quantification Analysis in the Detection of Osteoarthritis of the Knee with the Use of Vibroarthrography

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

Identyfikatory

DOI

10.12913/22998624/189512

• Języki publikacji: EN

Abstrakty

EN

Nowadays, the world is struggling with the problems of an aging society. With the increasing share of older people in the population, degenerative joint diseases are a growing problem. The result of progressive degenerative changes in joints is primarily the deterioration of the patients' quality of life and their gradual exclusion from activity and social life. The ability to effectively, non-invasively and quickly detect cases of chondromalacia of the knee joints is a challenge for modern medicine. The possibility of early detection of progressive degenerative changes allows for the appropriate selection of treatment protocols and significantly increases the chances of inhibiting the development of degenerative diseases of the musculoskeletal system. The article presents a non-invasive method for detecting degenerative changes in the knee joints based on recurrence analysis and classification using neural networks. The result of the analyzes was a classification accuracy of 91.07% in the case of MLP neural networks and 80.36% for RBF networks.

Słowa kluczowe

EN

knee joint; cartilage; lubrication; wear; osteoarthritis; RQA; RBF; MLP

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2024
• Tom: Vol. 18, no 5
• Strony: 19--31
• Opis fizyczny: Bibliogr. 66 poz., fig., tab.

Twórcy

autor

Machrowska Anna

• Department of Machine Design and Mechatronics, Faculty of Mechanical Engineering, Lublin University of Technology, Nadbystrzycka 36, 20-618 Lublin, Poland

autor

Karpiński Robert

• Department of Machine Design and Mechatronics, Faculty of Mechanical Engineering, Lublin University of Technology, Nadbystrzycka 36, 20-618 Lublin, Poland

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

autor

Maciejewski Marcin

• Department of Electronics and Information Technology, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, Nadbystrzycka 36, 20-618 Lublin, Poland

autor

Jonak Józef

• Department of Machine Design and Mechatronics, Faculty of Mechanical Engineering, Lublin University of Technology, Nadbystrzycka 36, 20-618 Lublin, Poland

autor

Krakowski Przemysław

• Department of Trauma Surgery and Emergency Medicine, Medical University of Lublin, Staszica 11, 20-081 Lublin, Poland

autor

Syta Arkadiusz

• Department of Electronics and Information Technology, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, Nadbystrzycka 36, 20-618 Lublin, Poland

Bibliografia

• 1. Cui A, Li H, Wang D, Zhong J, Chen Y, Lu H. Global, regional prevalence, incidence and risk factors of knee osteoarthritis in population-based studies. E Clinical Medicine. 2020 Dec; 29–30: 100587.
• 2. Quicke JG, Conaghan PG, Corp N, Peat G. Os- teoarthritis year in review 2021: epidemiology & therapy. Osteoarthritis and Cartilage. 2022 Feb; 30(2): 196–206.
• 3. Long H, Liu Q, Yin H, Wang K, Diao N, Zhang Y, Lin J., Guo A. Prevalence trends of site‐specific osteoarthritis from 1990 to 2019: Findings From the Global Burden of Disease Study 2019. Arthritis & Rheumatology. 2022 Jul; 74(7): 1172–83.
• 4. Roemer F, Jarraya M, Niu J, Silva J, Frobell R, Guemrazi A. Increased risk for radiographic osteoarthritis features in young active athletes: a cross- sectional matched case–control study. Osteoarthritis and Cartilage. 2015 Feb; 23(2): 239–43.
• 5. Cameron K, Hsiao M, Owens B, Burks R, Svoboda SJ. Incidence of physician-diagnosed osteoarthritis amongactive duty United States military service members. Arthritis & Rheumatology. 2011 Oct; 63(10): 2974–82.
• 6. Grushko G, Schneiderman R, Maroudas A. Some biochemical and biophysical parameters for the study of the pathogenesis of osteoarthritis: a Comparison Between the Processes of Ageing and Degeneration in Human Hip Cartilage. Connective Tissue Research. 1989 Jan; 19(2–4): 149–76.
• 7. Moore AC, Burris DL. Tribological and material properties for cartilage of and throughout the bovine stifle: support for the altered joint kinematics hypothesis of osteoarthritis. Osteoarthritis and Cartilage. 2015 Jan; 23(1): 161–9.
• 8. Link JM, Salinas EY, Hu JC, Athanasiou KA. The tribology of cartilage: Mechanisms, experimental techniques, and relevance to translational tissue engineering. Clinical Biomechanics. 2020 Oct; 79: 104880.
• 9. Cibere J, Sayre EC, Guermazi A, Nicolaou S, Kopec JA, Esdaile JM, Thorne A., Singer J., Wong H. Natural history of cartilage damage and osteoarthritis progression on magnetic resonance imaging in a population-based cohort with knee pain. Osteoar- thritis and Cartilage. 2011 Jun; 19(6): 683–8.
• 10. Kellgren JH, Lawrence JS. Radiological assessment of osteo-arthrosis. Ann Rheum Dis. 1957 Dec; 16(4): 494–502.
• 11. Krakowski P, Karpiński R, Maciejewski R, Jonak J. Evaluation of the diagnostic accuracy of MRI in detection of knee cartilage lesions using Receiver Operating Characteristic curves. J Phys: Conf Ser. 2021 Jan; 1736: 012028.
• 12. Solivetti FM, Guerrisi A, Salducca N, Desiderio F, Graceffa D, Capodieci G, Romeo P., Sperduti I., Canitano S. Appropriateness of knee MRI prescriptions: clinical, economic and technical issues. La radiologia medica. 2016 Apr; 121(4): 315–22.
• 13. Krakowski P, Karpiński R, Jojczuk M, Nogalska A, Jonak J. Knee MRI Underestimates the Grade of Cartilage Lesions. Applied Sciences. 2021 Feb 9; 11(4): 1552.
• 14. Figlus T, Kozioł M, Kuczyński Ł. The effect of selected operational factors on the vibroactivity of upper gearbox housings made of composite materials. Sensors. 2019 Sep 29; 19(19): 4240.
• 15. Figlus T, Szafraniec P, Skrúcaný T. Methods of measuring and processing signals during tests of the exposure of a motorcycle driver to vibration and noise. IJERPH. 2019 Aug 28; 16(17): 3145.
• 16. Blodgett WE. Auscultation of the knee joint. The Boston Medical and Surgical Journal. 1902 Jan 16; 146(3): 63–6.
• 17. Shabani H, Mikaili M, Noori SMR. Assessment of recurrence quantification analysis (RQA) of EEG for development of a novel drowsiness detection system. Biomed Eng Lett. 2016 Aug; 6(3): 196–204.
• 18. Zhao K, Wen H, Guo Y, Scano A, Zhang Z. Feasibility of recurrence quantification analysis (RQA) in quantifying dynamical coordination among muscles. Biomedical Signal Processing and Control. 2023 Jan; 79: 104042.
• 19. Jonak K, Syta A, Karakuła-Juchnowicz H, Krukow P. The clinical application of EEG-signals recurrence analysis as a measure of functional connectiv- ity: Comparative case study of patients with various neuropsychiatric disorders. Brain Sciences. 2020 Jun 16; 10(6): 380.
• 20. Gruszczyńska I, Mosdorf R, Sobaniec P, Żochowska-Sobaniec M, Borowska M. Epilepsy identification based on EEG signal using RQA method. Advances in Medical Sciences. 2019 Mar; 64(1): 58–64.
• 21. Yuan C, Zhu X., Liu G., Lei M. Classification of the surface EMG signal using RQA based representations. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) [Internet]. Hong Kong, China: IEEE; 2008 [cited 2024 Apr 12]. 2106–11. Available from: http://ieeexplore.ieee.org/ document/4634087/
• 22. Mascaro B, Prior J, Shark LK, Selfe J, Cole P, Goo-dacre J. Exploratory study of a non-invasive method based on acoustic emission for assessing the dynamic integrity of knee joints. Medical Engineering & Physics. 2009 Oct; 31(8): 1013–22.
• 23. Kiselev J, Ziegler B, Schwalbe HJ, Franke RP, Wolf U. Detection of osteoarthritis using acoustic emission analysis. Medical Engineering & Physics. 2019 Mar; 65: 57–60.
• 24. Shark LK, Chen H, Goodacre J. Knee acoustic emission: A potential biomarker for quantitative assessment of joint ageing and degeneration. Medical Engineering & Physics. 2011 Jun; 33(5): 534–45.
• 25. Bączkowicz D, Kręcisz K, Borysiuk Z. Analysis of patellofemoral arthrokinematic motion quality in open and closed kinetic chains using vibroarthrography. BMC Musculoskelet Disord. 2019 Dec; 20(1): 48.
• 26. Rangayyan RM, Oloumi F, Wu Y, Cai S. Fractal analysis of knee-joint vibroarthrographic signals via power spectral analysis. Biomedical Signal Processing and Control. 2013 Jan; 8(1): 23–9.
• 27. Karpiński R, Krakowski P, Jonak J, Machrowska A, Maciejewski M, Nogalski A. Diagnostics of Articular Cartilage Damage Based on Generated Acoustic Signals Using ANN—Part I: Femoral-Tibial Joint. Sensors. 2022 Mar 10; 22(6): 2176.
• 28. Karpiński R, Krakowski P, Jonak J, Machrowska A, Maciejewski M, Nogalski A. Diagnostics of Articular Cartilage Damage Based on Generated Acoustic Signals Using ANN—Part II: Patellofemoral Joint. Sensors. 2022 May 15; 22(10): 3765.
• 29. Karpiński R. Knee joint osteoarthritis diagnosis based on selected acoustic signal discriminants using machine learning. Applied Computer Science. 2022; 18(2): 71–85.
• 30. Jonak J, Karpinski R, Machrowska A, Krakowski P, Maciejewski M. A preliminary study on the use of EEMD-RQA algorithms in the detection of degenerative changes in knee joints. IOP Conf Ser: Mater Sci Eng. 2019 Dec 1; 710(1): 012037.
• 31. Contact microphone CM-01B, Technical Data Sheet. 2015; 3.
• 32. Karpiński R, Krakowski P, Jonak J, Machrowska A, Maciejewski M. Comparison of selected clas- sification methods based on machine learning as a diagnostic tool for knee joint cartilage damage Comput Sci. 2023 Dec 31; 19(4): 136–50.
• 33. Karpiński R, Krakowski P, Jonak J, Machrowska A, Maciejewski M, Nogalski A. Estimation of differences in selected indices of vibroacoustic signals between healthy and osteoarthritic patellofemoral joints as a potential non-invasive diagnostic tool. J Phys: Conf Ser. 2021 Dec 1; 2130(1): 012009.
• 34. Karpiński R, Krakowski P, Jonak J, Machrowska A, Maciejewski M, Nogalski A. Analysis of differences in vibroacoustic signals between healthy and osteoarthritic knees using EMD algorithm and statistical analysis. J Phys: Conf Ser. 2021 Dec 1; 2130(1): 012010.
• 35. Karpiński R, Machrowska A, Maciejewski M. Application of acoustic signal processing methods in detecting differences between open and closed kinematic chain movement for the knee joint. Applied Computer Science. 2019 Mar 31; 15(1): 36–48.
• 36. Machrowska A, Karpiński R, Krakowski P, Jonak J. Diagnostic factors for opened and closed kinematic chain of vibroarthrography signals. Applied Computer Science [Internet]. 2019 [cited 2020 Dec 20]; 15(3). Available from: http://yadda. icm.edu.pl/baztech/element/bwmeta1.element. baztech-9da426cc-646e-4a3e-8797-d4f57c125596
• 37. Ellenbecker TS, Davies GJ. Closed kinetic chain exercise: a comprehensive guide to multiple joint exercise. Human Kinetics; 2001.
• 38. Litak G, Syta A, Gajewski J, Jonak J. Detecting and identifying non-stationary courses in the ripping head power consumption by recurrence plots. Meccanica. 2010 Aug; 45(4): 603–8.
• 39. Syta A, Czarnigowski J, Jakliński P. Detection of cylinder misfire in an aircraft engine using linear and non-linear signal analysis. Measurement. 2021 Apr; 174: 108982.
• 40. Koszewnik A, Ambroziak L, Ołdziej D, Dzienis P, Ambrożkiewicz B, Syta A, et al. Nonlinear recur- rence analysis of piezo sensor placement for unmanned aerial vehicle motor failure diagnosis. Sci Rep. 2024 Apr 9; 14(1): 8289.
• 41. Takens F. Detecting strange attractors in turbulence. In: Rand D, Young LS, editors. Dynamical Systems and Turbulence, Warwick 1980 [Internet]. Berlin, Heidelberg: Springer Berlin Heidelberg; 1981 [cited 2024 May 7]. 366–81. (Lecture Notes in Mathematics; 898). Available from: http://link.springer. com/10.1007/BFb0091924
• 42. Chen Y, Yang H. Multiscale recurrence analysis of long-term nonlinear and nonstationary time series. Chaos, Solitons & Fractals. 2012 Jul; 45(7): 978–87.
• 43. Hui Y. Multiscale Recurrence Quantification Analysis of Spatial Cardiac Vectorcardiogram Signals. IEEE Trans Biomed Eng. 2011 Feb; 58(2): 339–47.
• 44. Machrowska A, Karpiński R, Jonak J, Szabelski J, Krakowski P. Numerical prediction of the component-ratio-dependent compressive strength of bone cement. Applied Computer Science. 2020 Sep 30; 16(3): 87–101.
• 45. Machrowska A, Szabelski J, Karpiński R, Krakowski P, Jonak J, Jonak K. Use of deep learning networks and statistical modeling to predict changes in me- chanical parameters of contaminated bone cements. Materials. 2020 Nov 28; 13(23): 5419.
• 46. Gardner MW, Dorling SR. Artificial neural networks (the multilayer perceptron) – a review of ap- plications in the atmospheric sciences. Atmospheric environment. 1998; 32(14–15): 2627–36.
• 47. Falkowicz K, Kulisz M. Prediction of buckling behaviour of composite plate element using artificial neural networks. Adv Sci Technol Res J. 2024 Feb 1; 18(1): 231–43.
• 48. Elanayar SVT., Shin YC. Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems. IEEE Trans Neural Netw. 1994 Jul; 5(4): 594–603.
• 49. Montazer GA, Giveki D, Karami M, Rastegar H. Radial basis function neural networks: A review. Computer Reviews Journal. 2018; 1(1): 52–74.
• 50. Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 2020 Dec; 21(1): 6.
• 51. Goutte C, Gaussier E. A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. In: Losada DE, Fernández-Luna JM, editors. Advances in Information Retrieval [Internet]. Berlin, Heidelberg: Springer Berlin Heidel- berg; 2005 [cited 2024 May 2]. 345–59. (Hutchison D, Kanade T, Kittler J, Kleinberg JM, Mattern F, Mitchell JC, et al., editors. Lecture Notes in Computer Science; 3408). Available from: http://link. springer.com/10.1007/978-3-540-31865-1_25.
• 52. Madeleine P, Andersen RE, Larsen JB, Arendt-Nielsen L, Samani A. Wireless multichannel vibroarthrographic recordings for the assessment of knee osteoarthritis during three activities of daily living. Clinical Biomechanics. 2020 Feb; 72: 16–23.
• 53. Nalband S, Sundar A, Prince AA, Agarwal A. Feature selection and classification methodology for the detection of knee-joint disorders. Computer Methods and Programs in Biomedicine. 2016 Apr; 127: 94–104.
• 54. Nalband S, Prince A, Agrawal A. Entropy‐based feature extraction and classification of vibroarthographic signal using complete ensemble empirical mode decomposition with adaptive noise. IET Science, Measurement & Technology. 2018 May; 12(3): 350–9.
• 55. Wu Y, Chen P, Luo X, Huang H, Liao L, Yao Y, et al. Quantification of knee vibroarthrographic sigal irregularity associated with patellofemoral joint cartilage pathology based on entropy and envelope amplitude measures. Computer Methods and Programs in Biomedicine. 2016 Jul; 130: 1–12.
• 56. Mascarenhas E, Nalband S, Fredo ARJ, Prince AA. Analysis and Classification of Vibroarthrographic Signals using Tuneable ‘Q’ Wavelet Transform. In: 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN) [Internet]. Noida, India: IEEE; 2020 [cited 2022 Apr 1]. 65–70. Available from: https://ieeexplore.ieee.org/ document/9071335/
• 57. Sharma M, Acharya UR. Analysis of knee-joint vibroarthographic signals using bandwidth-duration localized three-channel filter bank. Computers & Electrical Engineering. 2018 Nov; 72: 191–202.
• 58. Nalband S, Valliappan CA, Prince RGAA, Agrawal A. Feature extraction and classification of knee joint disorders using Hilbert Huang transform. In: 2017 14th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) [Internet]. Phuket: IEEE; 2017 [cited 2022 Apr 1]. 266–9. Available from: http://ieeexplore.ieee.org/ document/8096224/
• 59. Wu Y, Cai S, Yang S, Zheng F, Xiang N. Classification of Knee Joint Vibration Signals Using Bivar osterior Probability Decision Criterion. Entropy. 2013 Apr 17; 15(12): 1375–87.
• 60. Cai S, Yang S, Zheng F, Lu M, Wu Y, Krishnan S. Knee Joint Vibration Signal Analysis with Matching Pursuit Decomposition and Dynamic Weighted Classifier Fusion. Computational and Mathematical Methods in Medicine. 2013; 2013: 1–11.
• 61. Mu T, Nandi AK, Rangayyan RM. Screening of knee-joint vibroarthrographic signals using the strict 2-surface proximal classifier and genetic algorithm. Computers in Biology and Medicine. 2008 Oct; 38(10): 1103–11.
• 62. Zheng Y, Wang Y, Liu J, Jiang H, Yue Q. Knee joint vibration signal classification algorithm based on machine learning. Neural Comput & Applic. 2021 Feb; 33(3): 985–95.
• 63. Kim KS, Seo JH, Kang JU, Song CG. An enhanced algorithm for knee joint sound classification using feature extraction based on time-frequency analysis. Computer Methods and Programs in Biomedicine. 2009 May; 94(2): 198–206.
• 64. Balajee A, Murugan R, Venkatesh K. Security-enhanced machine learning model for diagnosis of knee joint disorders using vibroarthrographic signals. Soft Comput. 2023 Jun; 27(11): 7543–53.
• 65. Rangayyan RM, Wu Y. Analysis of Vibroarthrographic Signals with Features Related to Signal Variability and Radial-Basis Functions. Ann Biomed Eng. 2009 Jan; 37(1): 156–63.
• 66. Semiz B, Hersek S, Whittingslow DC, Ponder LA, Prahalad S, Inan OT. Using Knee Acoustical Emissions for Sensing Joint Health in Patients With Juvenile Idiopathic Arthritis: A Pilot Study. IEEE Sensors J. 2018 Nov 15; 18(22): 9128–36.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).