ABSTRACT
The application of machine learning in gait biomechanics of knee osteoarthritis (OA) had been reported in many previous studies. Instead of using radiographic severity classification to grade OA, this study employed pain scores and gait features to characterize knee OA. Pain scores from Knee Injury and Osteoarthritis Outcome Score (KOOS) and Measure of Intermittent and Constant Osteoarthritis Pain (ICOAP) with correlated spatiotemporal, kinematic, and electromyography features were utilized as features. Using k-means clustering to cluster severity, the severity class were then trained and tested using Support Vector Machine classifier. The best performance classification model with an accuracy 85.2% for the training set and 91.2% for the testing set was the dataset of ICOAP constant pain with its correlated gait features, with medium Gaussian Kernel and three severity levels as clustered by K-means. The ranking of features for each dataset was also discovered using the ReliefF algorithm.
- Phinyomark, A., Petri, G., Ibáñez-Marcelo, E., Osis, S. T. and Ferber, R. Analysis of Big Data in Gait Biomechanics: Current Trends and Future Directions. Journal of Medical and Biological Engineering, 38, 2 (2018/04/01 2018), 244-260.Google ScholarCross Ref
- Laroche, D., Tolambiya, A., Morisset, C., Maillefert, J. F., French, R. M., Ornetti, P. and Thomas, E. A classification study of kinematic gait trajectories in hip osteoarthritis. Computers in Biology and Medicine, 55 (2014/12/01/ 2014), 42-48.Google ScholarDigital Library
- Nair, S. S., French, R. M., Laroche, D. and Thomas, E. The Application of Machine Learning Algorithms to the Analysis of Electromyographic Patterns From Arthritic Patients. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 18, 2 (2010), 174-184.Google ScholarCross Ref
- Wei, T. S., Liu, P. T., Chang, L. W. and Liu, S. Y. Gait asymmetry, ankle spasticity, and depression as independent predictors of falls in ambulatory stroke patients. Plos One, 12, 5 (May 2017).Google Scholar
- Roshdibenam, V., Jogerst, G. J., Butler, N. R. and Baek, S. Machine Learning Prediction of Fall Risk in Older Adults Using Timed Up and Go Test Kinematics. Sensors, 21, 10 (May 2021).Google ScholarCross Ref
- Ross, G. B., Dowling, B., Troje, N. F., Fischer, S. L. and Graham, R. B. Classifying Elite From Novice Athletes Using Simulated Wearable Sensor Data. Frontiers in Bioengineering and Biotechnology, 8 (2020-August-04 2020).Google Scholar
- Nelson, A. E. Osteoarthritis year in review 2017: clinical. Osteoarthritis and Cartilage, 26, 3 (2018/03/01/ 2018), 319-325.Google ScholarCross Ref
- Hunter, D. J. and Bierma-Zeinstra, S. Osteoarthritis. The Lancet, 393, 10182 (2019/04/27/ 2019), 1745-1759.Google Scholar
- Buckwalter, J. A. and Martin, J. A. Osteoarthritis. Advanced Drug Delivery Reviews, 58, 2 (2006/05/20/ 2006), 150-167.Google Scholar
- Kokkotis, C., Moustakidis, S., Papageorgiou, E., Giakas, G. and Tsaopoulos, D. E. Machine learning in knee osteoarthritis: A review. Osteoarthritis and Cartilage Open, 2, 3 (2020/09/01/ 2020), 100069.Google ScholarCross Ref
- Abid, M., Mezghani, N. and Mitiche, A. Knee Joint Biomechanical Gait Data Classification for Knee Pathology Assessment: A Literature Review. Applied Bionics and Biomechanics, 2019 (2019), 14.Google ScholarCross Ref
- Chakraborty, S., Tomsett, R., Raghavendra, R., Harborne, D., Alzantot, M., Cerutti, F., Srivastava, M., Preece, A., Julier, S., Rao, R. M., Kelley, T. D., Braines, D., Sensoy, M., Willis, C. J. and Gurram, P. Interpretability of deep learning models: A survey of results. City, 2017.Google Scholar
- Halilaj, E., Rajagopal, A., Fiterau, M., Hicks, J. L., Hastie, T. J. and Delp, S. L. Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities. Journal of Biomechanics, 81 (2018/11/16/ 2018), 1-11.Google ScholarCross Ref
- Levinger, P., Lai, D. T. H., Begg, R. K., Webster, K. E. and Feller, J. A. The application of support vector machines for detecting recovery from knee replacement surgery using spatio-temporal gait parameters. Gait & Posture, 29, 1 (2009/01/01/ 2009), 91-96.Google ScholarCross Ref
- Moustakidis, S. P., Theocharis, J. B. and Giakas, G. A fuzzy decision tree-based SVM classifier for assessing osteoarthritis severity using ground reaction force measurements. Medical Engineering & Physics, 32, 10 (2010/12/01/ 2010), 1145-1160.Google ScholarCross Ref
- Yoo, T. K., Kim, S. K., Choi, S. B., Kim, D. Y. and Kim, D. W. Interpretation of movement during stair ascent for predicting severity and prognosis of knee osteoarthritis in elderly women using support vector machine. City, 2013.Google Scholar
- Yang, J. H., Park, J. H., Jang, S. H. and Cho, J. Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model. Annals of Rehabilitation Medicine-Arm, 44, 6 (Dec 2020), 415-427.Google Scholar
- Elbaz, A., Mor, A., Segal, G., Debi, R., Shazar, N. and Herman, A. Novel classification of knee osteoarthritis severity based on spatiotemporal gait analysis. Osteoarthritis and Cartilage, 22, 3 (2014/03/01/ 2014), 457-463.Google ScholarCross Ref
- Leporace, G., Gonzalez, F., Metsavaht, L., Motta, M., Carpes, F. P., Chahla, J. and Luzo, M. Are there different gait profiles in patients with advanced knee osteoarthritis? A machine learning approach. Clinical Biomechanics, 88 (2021/08/01/ 2021), 105447.Google ScholarCross Ref
- Petersen, E. T., Rytter, S., Koppens, D., Dalsgaard, J., Hansen, T. B., Larsen, N. E., Andersen, M. S. and Stilling, M. Patients with knee osteoarthritis can be divided into subgroups based on tibiofemoral joint kinematics of gait – an exploratory and dynamic radiostereometric study. Osteoarthritis and Cartilage (2021/10/29/ 2021).Google Scholar
- Deveza, L. A., Melo, L., Yamato, T. P., Mills, K., Ravi, V. and Hunter, D. J. Knee osteoarthritis phenotypes and their relevance for outcomes: a systematic review. Osteoarthritis and Cartilage, 25, 12 (2017/12/01/ 2017), 1926-1941.Google ScholarCross Ref
- Heidari, B. Knee osteoarthritis prevalence, risk factors, pathogenesis and features: Part I. Caspian J Intern Med, 2, 2 (Spring 2011), 205-212.Google Scholar
- Bedson, J. and Croft, P. R. The discordance between clinical and radiographic knee osteoarthritis: A systematic search and summary of the literature. BMC Musculoskeletal Disorders, 9, 1 (2008/09/02 2008), 116.Google ScholarCross Ref
- Swagerty, D. L., Jr. and Hellinger, D. Radiographic assessment of osteoarthritis. Am Fam Physician, 64, 2 (Jul 15 2001), 279-286.Google Scholar
- Roemer, F. W., Eckstein, F., Hayashi, D. and Guermazi, A. The role of imaging in osteoarthritis. Best Practice & Research Clinical Rheumatology, 28, 1 (2014/02/01/ 2014), 31-60.Google ScholarCross Ref
- Nebel, M. B., Sims, E. L., Keefe, F. J., Kraus, V. B., Guilak, F., Caldwell, D. S., Pells, J. J., Queen, R. and Schmitt, D. The Relationship of Self-Reported Pain and Functional Impairment to Gait Mechanics in Overweight and Obese Persons With Knee Osteoarthritis. Archives of Physical Medicine and Rehabilitation, 90, 11 (2009), 1874-1879.Google Scholar
- Kito, N., Shinkoda, K., Yamasaki, T., Kanemura, N., Anan, M., Okanishi, N., Ozawa, J. and Moriyama, H. Contribution of knee adduction moment impulse to pain and disability in Japanese women with medial knee osteoarthritis. Clinical Biomechanics, 25, 9 (2010/11/01/ 2010), 914-919.Google ScholarCross Ref
- O'Connell, M., Farrokhi, S. and Fitzgerald, G. K. The role of knee joint moments and knee impairments on self-reported knee pain during gait in patients with knee osteoarthritis. Clinical Biomechanics, 31 (2016), 40-46.Google ScholarCross Ref
- Park, S.-K., Kobsar, D. and Ferber, R. Relationship between lower limb muscle strength, self-reported pain and function, and frontal plane gait kinematics in knee osteoarthritis. Clinical Biomechanics, 38 (2016/10/01/ 2016), 68-74.Google ScholarCross Ref
- Marriott, K. A., Birmingham, T. B., Leitch, K. M., Pinto, R. and Giffin, J. R. Strong independent associations between gait biomechanics and pain in patients with knee osteoarthritis. Journal of Biomechanics, 94 (2019/09/20/ 2019), 123-129.Google ScholarCross Ref
- Debi, R., Mor, A., Segal, G., Segal, O., Agar, G., Debbi, E., Halperin, N., Haim, A. and Elbaz, A. Correlation between single limb support phase and self-evaluation questionnaires in knee osteoarthritis populations. Disability and Rehabilitation, 33, 13-14 (2011/01/01 2011), 1103-1109.Google ScholarCross Ref
- Naili, J. E., Esbjörnsson, A.-C., Iversen, M. D., Schwartz, M. H., Hedström, M., Häger, C. K. and Broström, E. W. The impact of symptomatic knee osteoarthritis on overall gait pattern deviations and its association with performance-based measures and patient-reported outcomes. The Knee, 24, 3 (2017/06/01/ 2017), 536-546.Google ScholarCross Ref
- Hermens, H. J., Freriks, B., Disselhorst-Klug, C. and Rau, G. Development of recommendations for SEMG sensors and sensor placement procedures. Journal of Electromyography and Kinesiology, 10, 5 (2000/10/01/ 2000), 361-374.Google ScholarCross Ref
- Vicon Vicon Documentation: Lower body modeling with Plug-in Gait. Vicon Motion Systems, City.Google Scholar
- Jackson, J. E. A user's guide to principal components. John Wiley & Sons, 2005.Google Scholar
- Astephen, J. L. and Deluzio, K. J. A multivariate gait data analysis technique: Application to knee osteoarthritis. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, 218, 4 (2004/04/01 2004), 271-279.Google Scholar
- Şen Köktaş, N., Yalabik, N., Yavuzer, G. and Duin, R. P. W. A multi-classifier for grading knee osteoarthritis using gait analysis. Pattern Recognition Letters, 31, 9 (2010/07/01/ 2010), 898-904.Google ScholarDigital Library
- McBride, J., Zhang, S., Wortley, M., Paquette, M., Klipple, G., Byrd, E., Baumgartner, L. and Zhao, X. Neural network analysis of gait biomechanical data for classification of knee osteoarthritis. City, 2011.Google Scholar
- Kobsar, D., Osis, S. T., Hettinga, B. A. and Ferber, R. Gait Biomechanics and Patient-Reported Function as Predictors of Response to a Hip Strengthening Exercise Intervention in Patients with Knee Osteoarthritis. PLOS ONE, 10, 10 (2015), e0139923.Google Scholar
- Mezghani, M., Hagemeister, N., Ouakrim, Y., Cagnin, A., Fuentes, A. and Mezghani, N. 3D Kinematics and Decision Trees to Predict the Impact of a Physical Exercise Program on Knee Osteoarthritis Patients. Applied Sciences, 11, 2 (2021).Google ScholarCross Ref
- Roos, E. M. and Lohmander, L. S. The Knee injury and Osteoarthritis Outcome Score (KOOS): from joint injury to osteoarthritis. Health and Quality of Life Outcomes, 1 (11/03 06/30/received 11/03/accepted 2003), 64-64.Google Scholar
- Hawker, G. A., Stewart, L., French, M. R., Cibere, J., Jordan, J. M., March, L., Suarez-Almazor, M. and Gooberman-Hill, R. Understanding the pain experience in hip and knee osteoarthritis – an OARSI/OMERACT initiative. Osteoarthritis and Cartilage, 16, 4 (2008/04/01/ 2008), 415-422.Google ScholarCross Ref
- Neogi, T. The Epidemiology and Impact of Pain in Osteoarthritis. Osteoarthritis and cartilage / OARS, Osteoarthritis Research Society, 21, 9 (2013), 1145-1153.Google ScholarCross Ref
- Mills, K., Hunt, M. A. and Ferber, R. Biomechanical deviations during level walking associated with knee osteoarthritis: a systematic review and meta-analysis. Arthritis Care Res (Hoboken), 65, 10 (Oct 2013), 1643-1665.Google Scholar
- Astephen, J. L., Deluzio, K. J., Caldwell, G. E., Dunbar, M. J. and Hubley-Kozey, C. L. Gait and neuromuscular pattern changes are associated with differences in knee osteoarthritis severity levels. Journal of Biomechanics, 41, 4 (2008/01/01/ 2008), 868-876.Google ScholarCross Ref
- Heiden, T. L., Lloyd, D. G. and Ackland, T. R. Knee joint kinematics, kinetics and muscle co-contraction in knee osteoarthritis patient gait. Clinical Biomechanics, 24, 10 (2009/12/01/ 2009), 833-841.Google ScholarCross Ref
Index Terms
- Clustering-Based Support Vector Machine (SVM) for Symptomatic Knee Osteoarthritis Severity Classification
Recommendations
Knee Osteoarthritis Classification System Examination on Wearable Daily-Use IMU Layout
ISWC '22: Proceedings of the 2022 ACM International Symposium on Wearable ComputersThe diagnostic approach for knee osteoarthritis that draws on kinematic characteristics provides a solution other than imaging medicine. However, the gait-based kinematic analysis still requires a motion capture suit as a prerequisite to ensure a ...
Knee osteoarthritis severity level classification using whole knee cartilage damage Index and ANN
CHASE '18: Proceedings of the 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering TechnologiesIn this study, we extended our previous work on analyzing the relationship between cartilage thickness and osteoarthritis (OA) severity grade change. Cartilage thickness is measured by the Cartilage Damage Index (CDI) which includes 60 points marked on ...
A rough margin based support vector machine
By introducing the rough set theory into the support vector machine (SVM), a rough margin based SVM (RMSVM) is proposed to deal with the overfitting problem due to outliers. Similar to the classical SVM, the RMSVM searches for the separating hyper-plane ...
Comments