Abstract
Artificial intelligence (AI) has gained significant traction in medical applications. This study focuses on knee joint diseases, specifically osteoarthritis (OA) and rheumatoid arthritis, which often lead to pathological gait patterns in patients due to pain and mobility issues. The proposed technique put forth in this research aims to classify gait patterns in kinematic data of osteoarthritic and asymptomatic (AS) knees. Our approach utilizes Phase Space Reconstruction (PSR), Intrinsic Time-Scale Decomposition (ITD), and neural networks to extract features. Knee kinematic data, including translations and rotations, are analyzed using ITD to obtain dominant proper rotation components (PRCs) capturing most of the energy from the signals. The phase space of PRCs is then reconstructed, revealing nonlinear gait dynamics. By employing three-dimensional PSR and Euclidean distance, we extract features that capture the distinctive dynamics of osteoarthritic and AS knee gait patterns. Utilizing neural networks, we model and classify the gait system dynamics. Experimental evaluation on 22 knee OA patients and 28 age-matched AS control individuals demonstrates the effectiveness of our method in distinguishing between the two groups’ gait patterns, achieving superior classification accuracies of 92\(\%\) and 96\(\%\), respectively. These results suggest that our approach holds promise for aiding the identification of knee OA in clinical practice, leading to improved quality outcomes. By enabling accurate identification of knee OA in clinical practice, the proposed method has the potential to contribute to improved patient outcomes, such as timely interventions, personalized treatment plans, and enhanced monitoring of disease progression. This, in turn, can lead to better management of knee OA and improved quality outcomes for patients.
Similar content being viewed by others
Availability of data and materials
The datasets used and/or analyzed during in current study are available from the corresponding author on reasonable requests.
References
Alkjaer T, Raffalt PC, Dalsgaard H, Simonsen EB, Petersen NC, Bliddal H, Henriksen M (2015) Gait variability and motor control in people with knee osteoarthritis. Gait Posture 42(4):479–484
Altman R, Asch E, Bloch D, Bole G, Borenstein D, Brandt K, Wolfe F (1986) Development of criteria for the classification and reporting of osteoarthritis: Classification of osteoarthritis of the knee. Arthritis Rheumatism 29(8):1039–1049
Ameli S, Naghdy F, Stirling D, Naghdy G, Aghmesheh M (2017) Objective clinical gait analysis using inertial sensors and six minute walking test. Pattern Recognit 63:246–257
An X, Jiang D, Chen J, Liu C (2012) Application of the intrinsic time-scale decomposition method to fault diagnosis of wind turbine bearing. J Vib Control 18(2):240–245
Arunkumar N, Ramkumar K, Venkatraman V, Abdulhay E, Fernandes SL, Kadry S, Segal S (2017) Classification of focal and non focal EEG using entropies. Pattern Recognit Lett 94:112–117
Azar AT, El-Said SA (2014) Performance analysis of support vector machines classifiers in breast cancer mammography recognition. Neural Comput Appl 24:1163–1177
Befrui N, Elsner J, Flesser A, Huvanandana J, Jarrousse O, Le TN, Weidert S (2018) Vibroarthrography for early detection of knee osteoarthritis using normalized frequency features. Med Biol Eng Comput 56(8):1499–1514
Blanco FJ, Ruiz-Romero C (2012) Osteoarthritis: metabolomic characterization of metabolic phenotypes in OA. Nat Rev Rheumatol 8(3):130–132
Boashash B, Azemi G, Khan NA (2015) Principles of time-frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detection. Pattern Recognition 48(3):616–627
Brooks S, Morgan M (2002) Accuracy of clinical diagnosis in knee arthroscopy. Ann R Coll Surg Engl 84(4):265
Cao P, Liu X, Yang J, Zhao D, Huang M, Zaiane O (2018) \(\ell \)2, 1-\(\ell \)1 regularized nonlinear multi-task representation learning based cognitive performance prediction of Alzheimer’s disease. Pattern Recognit 79:195–215
Chan S, Dittakan K, El Salhi S (2022) Osteoarthritis detection by applying quadtree analysis to human joint knee X-ray imagery. Int J Comput Appl 44(6):571–578
Chen B, He Z, Chen X, Cao H, Cai G, Zi Y (2011) A demodulating approach based on local mean decomposition and its applications in mechanical fault diagnosis. Meas Sci Technol 22(5):055704
Chen HC, Wu CH, Wang CK, Lin CJ, Sun YN (2014) A Joint-Constraint Model-Based System for Reconstructing Total Knee Motion. IEEE Trans Biomed Eng 61(1):171–181
Chen M, Fang Y, Zheng X (2014) Phase space reconstruction for improving the classification of single trial EEG. Biomed Signal Process Control 11:10–16
Debi R, Elbaz A, Mor A, Kahn G, Peskin B, Beer Y, Segal G (2017) Knee osteoarthritis, degenerative meniscal lesion and osteonecrosis of the knee: Can a simple gait test direct us to a better clinical diagnosis. Orthop Traumatol Surg Res 103(4):603–608
Duan J, Tench C, Gottlob I, Proudlock F, Bai L (2017) Automated segmentation of retinal layers from optical coherence tomography images using geodesic distance. Pattern Recognition 72:158–175
Esrafilian A, Karimi MT, Amiri P, Fatoye F (2013) Performance of subjects with knee osteoarthritis during walking: Differential parameters. Rheumatol Int 33(7):1753–1761
Farrell J (1998) Stability and approximator convergence in nonparametric nonlinear adaptive control. IEEE Trans Neural Netw 9(5):1008–1020
Feng Z, Lin X, Zuo MJ (2016) Joint amplitude and frequency demodulation analysis based on intrinsic time-scale decomposition for planetary gearbox fault diagnosis. Mech Syst Signal Process 72:223–240
Frei MG, Osorio I (2007) Intrinsic time-scale decomposition: time-frequency-energy analysis and real-time filtering of non-stationary signals. In Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences (Vol. 463, No. 2078, pp. 321-342). The Royal Society
Gustafson JA, Robinson ME, Fitzgerald GK, Tashman S, Farrokhi S (2015) Knee motion variability in patients with knee osteoarthritis: The effect of self-reported instability. Clin Biomech 30(5):475–480
Hada S, Ishijima M, Kaneko H, Kinoshita M, Liu L, Sadatsuki R, Shiozawa J (2017) Association of medial meniscal extrusion with medial tibial osteophyte distance detected by T2 mapping MRI in patients with early-stage knee osteoarthritis. Arthritis Res Ther 19(1):201
Halim HNA, Azaman A, Zulkapri I (2022) Cluster analysis of biomechanical gait data and pain score as a potential classification of severity in knee osteoarthritis. J Hum Centered Technol 1(2):33–43
Huang B, Kunoth A (2013) An optimization based empirical mode decomposition scheme. J Comput Appl Math 240:174–183
Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Liu HH (1998) The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. Royal Soc 454(1971):903–995
Iijima H, Shimoura K, Ono T, Aoyama T, Takahashi M (2019) Proximal gait adaptations in individuals with knee osteoarthritis: A systematic review and meta-analysis. J Biomech 87:127–141
Jia J, Goparaju B, Song J, Zhang R, Westover MB (2017) Automated identification of epileptic seizures in EEG signals based on phase space representation and statistical features in the CEEMD domain. Biomed Signal Process Control 38:148–157
Karg M, Seiberl W, Kreuzpointner F, Haas JP, Kulic D (2015) Clinical gait analysis: Comparing explicit state duration HMMs using a reference-based index. IEEE Trans Neural Syst Rehabil Eng 23(2):319–331
Kellgren JH, Lawrence JS (1957) Radiological assessment of osteo-arthrosis. Ann Rheum Dis 16(4):494
Kobsar D, Osis ST, Phinyomark A, Boyd JE, Ferber R (2016) Reliability of gait analysis using wearable sensors in patients with knee osteoarthritis. J Biomech 49(16):3977–3982
Kobsar D, Charlton JM, Hunt MA (2019) Individuals with knee osteoarthritis present increased gait pattern deviations as measured by a knee-specific gait deviation index. Gait Posture 72:82–88
Koktas NS, Yalabik N, Yavuzer G, Duin RPW (2010) A multi-classifier for grading knee osteoarthritis using gait analysis. Pattern Recognit Lett 31(9):898–904
Kotti M, Duffell LD, Faisal AA, McGregor AH (2017) Detecting knee osteoarthritis and its discriminating parameters using random forests. Med Eng Phys 43:19–29
Kour N, Gupta S, Arora S (2020) A survey of knee osteoarthritis assessment based on gait. Arch Comput Methods Eng 28:345–385
Kubkaddi S, Ravikumar KM (2017) Early detection of knee osteoarthritis using SVM classifier. Int J Eng Adv Technol 5(3):259–262
Kwon SB, Ro DH, Song MK, Han HS, Lee MC, Kim HC (2019) Identifying key gait features associated with the radiological grade of knee osteoarthritis. Osteoarthr Cartil 27(12):1755–1760
Kwon SB, Han HS, Lee MC, Kim HC, Ku Y (2020) Machine learning-based automatic classification of knee osteoarthritis severity using gait data and radiographic images. IEEE Access 8:120597–120603
Lee SH, Lim JS, Kim JK, Yang J, Lee Y (2014) Classification of normal and epileptic seizure EEG signals using wavelet transform, phase-space reconstruction, and Euclidean distance. Comput Methods Programs Biomed 116(1):10–25
Li Y, Xu M, Wei Y, Huang W (2015) Rotating machine fault diagnosis based on intrinsic characteristic-scale decomposition. Mech Mach Theory 94:9–27
Lundberg HJ, Foucher KC, Andriacchi TP, Wimmer MA (2012) Direct comparison of measured and calculated total knee replacement force envelopes during walking in the presence of normal and abnormal gait patterns. J Biomech 45(6):990–996
Martinez-Hernandez U, Dehghani-Sanij AA (2018) Adaptive Bayesian inference system for recognition of walking activities and prediction of gait events using wearable sensors. Neural Netw 102:107–119
McCarthy I, Hodgins D, Mor A, Elbaz A, Segal G (2013) Analysis of knee flexion characteristics and how they alter with the onset of knee osteoarthritis: A case control study. BMC Musculoskelet Disord 14(1):169
Merigó JM, Casanovas M (2011) Induced aggregation operators in the Euclidean distance and its application in financial decision making. Expert Syst Appl 38:7603–7608
Mezghani N, Husse S, Boivin K, Turcot K, Aissaoui R, Hagemeister N, De Guise J (2008) Automatic classification of asymptomatic and osteoarthritis knee gait patterns using kinematic data features and the nearest neighbor classifier. IEEE Trans Biomed Eng 55(3):1230–1232
Michael S (2005) Applied nonlinear time series analysis: applications in physics, physiology and finance (Vol. 52). World Scientific
Middleton A, Fritz SL, Lusardi M (2015) Walking speed: the functional vital sign. J Aging Phys Act 23(2):314–322
Mills K, Hunt MA, Ferber R (2013) Biomechanical deviations during level walking associated with knee osteoarthritis: a systematic review and meta-analysis. Arthritis Care Res 65(10):1643–1665
Orellana JN, Sixto AS, Torres BDLC, Cachadiña ES, Martín PF, de la Rosa FB (2018) Multiscale time irreversibility: Is it useful in the analysis of human gait? Biomed Signal Process Control 39:431–434
Ornetti P, Maillefert JF, Laroche D, Morisset C, Dougados M, Gossec L (2010) Gait analysis as a quantifiable outcome measure in hip or knee osteoarthritis: A systematic review. Jt Bone Spine 77(5):421–425
Park C, Looney D, Van Hulle MM, Mandic DP (2011) The complex local mean decomposition. Neurocomputing 74(6):867–875
Park HJ, Kim SS, Lee SY, Park NH, Park JY, Choi YJ, Jeon HJ (2013) A practical MRI grading system for osteoarthritis of the knee: association with Kellgren-Lawrence radiographic scores. European Journal of Radiology 82(1):112–117
Peixoto JG, de Souza Moreira B, Diz JBM, Timoteo EF, Kirkwood RN, Teixeira-Salmela LF (2019) Analysis of symmetry between lower limbs during gait of older women with bilateral knee osteoarthritis. Aging Clin Exp Res 31(1):67–73
Petersen ET, Rytter S, Koppens D, Dalsgaard J, Hansen TB, Larsen NE, Stilling M (2022) Patients with knee osteoarthritis can be divided into subgroups based on tibiofemoral joint kinematics of gait-an exploratory and dynamic radiostereometric study. Osteoarthr Cartil 30(2):249–259
Pfeiffer SJ, Nissman DB, Givens DL, Sorensen R, Drahzal J, Wikstrom EA, Pietrosimone B (2021) Associations between sagittal plane walking kinematics and femoral cartilage ultrasound echo-intensity in individuals with symptomatic radiographic knee osteoarthritis. Osteoarthr Cartil 29:S187–S188
Phinyomark A, Petri G, Ibanez-Marcelo E, Osis ST, Ferber R (2018) Analysis of big data in gait biomechanics: current trends and future directions. J Med Biol Eng 38(2):244–260
Prochazka A, Vysata O, Valis M, Tupa O, Schatz M, Marik V (2015) Use of the image and depth sensors of the Microsoft Kinect for the detection of gait disorders. Neural Comput. Appl 26(7):1621–1629
Riad R, Jennane R, Brahim A, Janvier T, Toumi H, Lespessailles E (2018) Texture analysis using complex wavelet decomposition for knee osteoarthritis detection: Data from the osteoarthritis initiative. Comput Electr Eng 68:181–191
Segal NA, Nevitt MC, Lynch JA, Niu J, Torner JC, Guermazi A (2015) Diagnostic performance of 3D standing CT imaging for detection of knee osteoarthritis features. Phys Sportsmed 43(3):213–220
Sharma S, Khari M (2021) Machine learning implementations in bioinformatics and its application. In Bioelectronics and Medical Devices. Apple Academic Press, p 187-205
Som A, Krishnamurthi N, Venkataraman V, Turaga P (2016) Attractor-shape descriptors for balance impairment assessment in Parkinson’s disease. In: IEEE Conference on Engineering in Medicine and Biology Society. p 3096-3100
Srivastava S, Khari M, Crespo RG, Chaudhary G, Arora P (eds) (2021) Concepts and real-time applications of deep learning. Springer International Publishing, Cham, Switzerland
Tadano S, Takeda R, Sasaki K, Fujisawa T, Tohyama H (2016) Gait characterization for osteoarthritis patients using wearable gait sensors (H-Gait systems). J Biomech 49(5):684–690
Tajbakhsh N, Suzuki K (2017) Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANNs vs. CNNs. Pattern Recognition 63:476–486
Takens F (1980) Detecting strange attractors in turbulence. In: Dynamical Systems and Turbulence, Warwick 1980. Springer, Berlin/Heidelberg, 1981, p 366-381
Tanimoto K, Takahashi M, Tokuda K, Sawada T, Anan M, Shinkoda K (2017) Lower limb kinematics during the swing phase in patients with knee osteoarthritis measured using an inertial sensor. Gait Posture 57:236–240
Tarnita D, Marghitu DB (2017) Nonlinear dynamics of normal and osteoarthritic human knee. Proc Rom Acad Math Phys Tech Sci Inf Sci 18(4):353–360
Tawy GF, Rowe P, Biant L (2018) Gait variability and motor control in patients with knee osteoarthritis as measured by the uncontrolled manifold technique. Gait Posture 59:272–277
Turcot K, Aissaoui R, Boivin K, Pelletier M, Hagemeister N, De Guise J (2008) New accelerometric method to discriminate between asymptomatic subjects and patients with medial knee osteoarthritis during 3-D gait. IEEE Trans Biomed Eng 55(4):1415–1422
van Egmond N, Stolwijk N, van Heerwaarden R, van Kampen A, Keijsers NL (2017) Gait analysis before and after corrective osteotomy in patients with knee osteoarthritis and a valgus deformity. Knee Surg Sports Traumatol Arthrosc 25(9):2904–2913
Venkataraman V, Turaga P (2016) Shape distributions of nonlinear dynamical systems for video-based inference. IEEE Trans Pattern Anal Mach Intell 38(12):2531–2543
Wang C, Hill DJ (2006) Learning from neural control. IEEE Trans Neural Netw 17(1):130–146
Wang C, Hill DJ (2007) Deterministic learning and rapid dynamical pattern recognition. IEEE Trans Neural Netw 18(3):617–630
Wang C, Hill DJ (2009) Deterministic Learning Theory for Identification. CRC Press, Boca Raton, Recognition and Control
Wang C, Chen T, Chen G, Hill DJ (2009) Deterministic learning of nonlinear dynamical systems. Int. J. Bifurc. Chaos 19(4):1307–1328
Wong DWC, Lam WK, Lee WCC (2020) Gait asymmetry and variability in older adults during long-distance walking: Implications for gait instability. Clin Biomech 72:37–43
Xing Z, Qu J, Chai Y, Tang Q, Zhou Y (2017) Gear fault diagnosis under variable conditions with intrinsic time-scale decomposition-singular value decomposition and support vector machine. J Mech Sci Technol 31(2):545–553
Xu B, Jacquir S, Laurent G, Bilbault JM, Binczak S (2013) Phase space reconstruction of an experimental model of cardiac field potential in normal and arrhythmic conditions. In: 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, p 3274-3277
Yang JH, Park JH, Jang SH, Cho J (2020) Novel method of classification in knee osteoarthritis: Machine learning application versus logistic regression model. Ann Rehabil Med 44(6):415
Yousef R, Gupta G, Yousef N, Khari M (2022) A holistic overview of deep learning approach in medical imaging. Multimed Syst 28(3):881–914
Zhang Y, Yao Z, Wang S, Huang W, Ma L, Huang H, Xia H (2015) Motion analysis of Chinese normal knees during gait based on a novel portable system. Gait Posture 41(3):763–768
Zhou D, Zhang S, Zhang H, Jiang L, Zhang J, Fang J (2017) A novel method of evaluating knee joint stability of patients with knee osteoarthritis: multiscale entropy analysis with a knee-aiming task. Sci Rep 7(1):354
Acknowledgements
This work was supported by the Natural Science Foundation of Fujian Province (Grant no. 2022J011146).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Ethical approval and consent to participate
Ethics approval for this study was obtained from the institutional ethics committees of Guangzhou General Hospital of Guangzhou Military Command. All patients and asymptomatic subjects were included based on their consent forms.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zeng, W., Ma, L. & Zhang, Y. Analysis and classification of gait patterns in osteoarthritic and asymptomatic knees using phase space reconstruction, intrinsic time-scale decomposition and neural networks. Multimed Tools Appl 83, 21107–21131 (2024). https://doi.org/10.1007/s11042-023-16322-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16322-9