Abstract
Osteoarthritis is the most common form of arthritis in the knee that comes with a variation in symptoms’ intensity, frequency and pattern. Knee OA (KOA) is often diagnosed using invasive and expensive methods that can measure changes in joint morphology and function. Early and accurate identification of significant risk factors in clinical data is of vital importance in diagnosing KOA. A machine intelligence approach is proposed here to enable automated, non-invasive identification of risk factors from self-reported clinical data about joint symptoms, disability, function and general health. The proposed methodology was applied to recognize participants with symptomatic KOA or being at high risk of developing KOA in at least one knee. Different machine learning and deep learning algorithms were tested and compared in terms of multiple criteria e.g. accuracy, per class accuracy and execution time. Deep learning was proved to be the most effective in terms of accuracy with classification accuracies up to 86.95%, evaluated on data from the osteoarthritis initiative study. Insights about ten different feature subsets and their effect on classification accuracy are provided. The proposed methodology was also demonstrated in subgroups defined by gender and age. The results suggest that machine intelligence and especially deep learning may facilitate clinical evaluation, monitoring and even prediction of knee osteoarthritis. Apart from the classical implementation of the proposed methodology, a quantum perspective is also discussed highlighting the future application of quantum computers in OA diagnosis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ackerman IN, Kemp JL, Crossley KM, Culvenor AG, Hinman RS (2017) Hip and Knee Osteoarthritis Affects Younger People, Too. J Orthop Sports Phys Ther 47(2):67–79
Atkeson CG, Moore AW, Schaal S (1997) Locally Weighted Learning. Artif Intell Rev 11(1):11–73
Belson WA (1959) "Matching and Prediction on the Principle of Biological Classification." Journal of the Royal Statistical Society. Series C (Applied Statistics) 8(2):65–75
Beynon MJ, Jones L, Holt CA (2006) Classification of osteoarthritic and normal knee function using three-dimensional motion analysis and the Dempster-Shafer theory of evidence. IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans 36(1):173–186
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Cicuttini FM, Spector TD (1996) Genetics of osteoarthritis. Ann Rheum Dis 55(9):665–667
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
de Dieu Uwisengeyimana J, Ibrikci T (2017) Diagnosing Knee Osteoarthritis Using Artificial Neural Networks and Deep Learning. Biomedical Statistics and Informatics 2(3):95
Deluzio KJ, Astephen JL (2007) Biomechanical features of gait waveform data associated with knee osteoarthritis: An application of principal component analysis. Gait Posture 25:86–93
Dieppe P (1993) Management of osteoarthritis of the hip and knee joints. Curr Opin Rheumatol 5(4):487–493
Duda RO, Hart PE, Stork DG (2012) Pattern classification, John Wiley & Sons
Eckstein F, Wirth W, Nevitt MC (2012) Recent advances in osteoarthritis imaging--the osteoarthritis initiative. Nat Rev Rheumatol 8(10):622–630
Farhi E, Neven H (2018) Classification with quantum neural networks on near term processors. Preprint at https://arxiv.org/abs/1802.06002
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139
Havlíček V, Córcoles A, Temme K, Harrow A, Kandala A, Chow J, Gambetta J (2019) Supervised learning with quantum-enhanced feature spaces. Nature 567(7747):209–212. https://doi.org/10.1038/s41586-019-0980-2
Jones L, Holt CA, Beynon MJ (2008) Reduction, classification and ranking of motion analysis data: an application to osteoarthritic and normal knee function data. Comput Methods Biomech Biomed Engin 11(1):31–40
Keller J, Gray M, Givens J (1985) A fuzzy K-nearest neighbor algorithm. IEEE Transactions On Systems, Man, And Cybernetics, SMC-15(4), 580–585. doi: https://doi.org/10.1109/tsmc.1985.6313426
Kotti M, Duffell L, Faisal A, McGregor A (2013) Towards automatically assessing osteoarthritis severity by regression trees & SVMs
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
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
LeCun Y, Chopra S, Hadsell R, Ranzato M, Huang F (2006) A tutorial on energy-based learning. Predicting structured data 1(0)
Martin DF (1994) Pathomechanics of knee osteoarthritis. Med Sci Sports Exerc 26(12):1429–1434
McBride J, Zhang S, Wortley M, Paquette M, Klipple G, Byrd E, Baumgartner L, Zhao X (2011) Neural network analysis of gait biomechanical data for classification of knee osteoarthritis. Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine, BSEC 2011
McClean J, Boixo S, Smelyanskiy V, Babbush R, Neven H (2018) Barren plateaus in quantum neural network training landscapes. Nat Commun 9(1). https://doi.org/10.1038/s41467-018-07090-4
Mezghani N, Boiven K, Turcot K, Aissaoui R, Hagmeister N, De Guise JA (2008a) Hierarchical analysis and classification of asymptomatic and knee osteoarthritis gait patterns using a wavelet representation of kinetic data and the nearest neighbor classifier. Journal of Mechanics in Medicine and Biology 8(1):45–54
Mezghani N, Husse S, Boivin K, Turcot K, Aissaoui R, Hagemeister N, de Guise JA (2008b) 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
Moustakidis SP, Theocharis JB, Giakas G (2010) A fuzzy decision tree-based SVM classifier for assessing osteoarthritis severity using ground reaction force measurements. Med Eng Phys 32(10):1145–1160
Peat G, McCarney R, Croft P (2001) Knee pain and osteoarthritis in older adults: a review of community burden and current use of primary health care. Ann Rheum Dis 60(2):91–97
Scholkopf B (1997) Support vector learning. Ph. D. thesis, Technische Universitat Berlin
Şen Köktaş N, Yalabik N, Yavuzer G (2006) Ensemble classifiers for medical diagnosis of knee osteoarthritis using gait data. Proceedings - 5th International Conference on Machine Learning and Applications, ICMLA 2006
Şen Köktaş N, Yalabik N, Yavuzer G, Duin RPW (2010) A multi-classifier for grading knee osteoarthritis using gait analysis. Pattern Recogn Lett 31(9):898–904
Valdes AM, Arden NK, Vaughn FL, Doherty SA, Leaverton PE, Zhang W, Muir KR, Rampersaud E, Dennison EM, Edwards MH, Jameson KA, Javaid MK, Spector TD, Cooper C, Maciewicz RA, Doherty M (2011) Role of the Nav1.7 R1150W amino acid change in susceptibility to symptomatic knee osteoarthritis and multiple regional pain. Arthritis Care Res 63(3):440–444
Witten IH, Frank E, Hall MA, Pal CJ (2016) Data Mining: Practical machine learning tools and techniques, Morgan Kaufmann
Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701
Zhai J, Zhai M, Kang X (2014) Condensed fuzzy nearest neighbor methods based on fuzzy rough set technique. Intelligent Data Analysis 18(3):429–447. https://doi.org/10.3233/ida-140649
Acknowledgments
Part of this work has received funding from the European Community’s H2020 Programme, under grant agreement Nr. 777159 (OACTIVE).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
ESM 1
(PDF 657 kb)
Appendix
Appendix
1.1 Hyperparameter selection over the validation sets (average) for different classification methods on the 3-class problem
Average validation performance of various DNN architectures
Average validation performance for Adaboost with respect to the number of weak learners and the maximum number of splits (DT as weak learner)
Average validation performance for Random Forest with respect to the number of weak learners and the maximum number of splits (DT as weak learner)
Average validation performance for SVM with respect to the kernel scale and the C parameters
Average validation performance for KNN, Fuzzy KNN, Fuzzy NPC and CFKNN with respect to k parameter
Rights and permissions
About this article
Cite this article
Moustakidis, S., Christodoulou, E., Papageorgiou, E. et al. Application of machine intelligence for osteoarthritis classification: a classical implementation and a quantum perspective. Quantum Mach. Intell. 1, 73–86 (2019). https://doi.org/10.1007/s42484-019-00008-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42484-019-00008-3