Physical Activity as a Risk Factor in the Progression of Osteoarthritis: A Machine Learning Perspective
Knee osteoarthritis (KOA) comes with a variety of symptoms’ intensity, frequency and pattern. Most of the current methods in KOA diagnosis are very expensive commonly measuring changes in joint morphology and function. So, it is very important to diagnose KOA early, which can be achieved with early identification of significant risk factors in clinical data. Our objective in this paper is to investigate the predictive capacity of physical activity measures as risk factors in the progression of KOA. In order to achieve this, a machine learning approach is proposed here for KOA prediction using features extracted from an accelerometer bracelet. Various ML models were explored for their suitability in implementing the learning task on different combinations of feature subsets. Results up to 74.5% were achieved indicating that physical activity measured by accelerometers may constitute an important risk factor for KOA progression prediction especially if it is combined with complementary data sources.
KeywordsKnee osteoarthritis prediction Machine learning Wearable activity data Physical function Knee joint
This work has received funding from the European Community’s H2020 Programme, under grant agreement Nr. 777159 (OACTIVE).
- 2.Chen, C., Breiman, L.: Using Random Forest to Learn Imbalanced Data. University of California, Berkeley (2004)Google Scholar
- 3.Christodoulou, E., Moustakidis, S., Papandrianos, N., Tsaopoulos, D., Papageorgiou, E.: Exploring deep learning capabilities in knee osteoarthritis case study for classification. In: 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), pp. 1–6. IEEE (2019)Google Scholar
- 6.Freedson, P., Melanson, E., Sirard, J.: Calibration of the computer science and applications, inc. accelerometer. Med. Sci. Sports Exercise 30(5), 777–781 (1998). https://doi.org/10.1097/00005768-199805000-00021
- 7.Lazzarini, N., et al.: A machine learning approach for the identification of new biomarkers for knee osteoarthritis development in overweight and obese women. Osteoarthritis Cartilage 25 (2017). https://doi.org/10.1016/j.joca.2017.09.001
- 9.Moustakidis, S., Christodoulou, E., Papageorgiou, E., Kokkotis, C., Papandrianos, N., Tsaopoulos, D.: Application of machine intelligence for osteoarthritis classification: a classical implementation and a quantum perspective. Quantum Mach. Intell. 1–14 (2019)Google Scholar
- 11.Phinyomark, A., Osis, S., Hettinga, B., Kobsar, D., Ferber, R.: Gender differences in gait kinematics for patients with knee osteoarthritis. BMC Musculoskeletal Disorders 17 (2016). https://doi.org/10.1186/s12891-016-1013-z
- 14.Swartz, A.M., Strath, S.J., BASSETT, D.R., O’BRIEN, W.L., King, G.A., Ainsworth, B.E.: Estimation of energy expenditure using CSA accelerometers at hip and wrist sites. Med. Sci. Sports Exercise 32(9), S450–S456 (2000)Google Scholar
- 16.Vendittoli, P.A., Ouakrim, Y., Fuentes, A., Mitiche, A., Hagemeister, N., de Guise, J.: Mechanical biomarkers of medial compartment knee osteoarthritis diagnosis and severity grading: discovery phase. J. Biomech. 52 (2016). https://doi.org/10.1016/j.jbiomech.2016.12.022
- 17.Yoo, T., Kim, D.W., Choi, S., Oh, E., Park, J.S.: Simple scoring system and artificial neural network for knee osteoarthritis risk prediction: a cross-sectional study. PloS One 11, e0148724 (2016). https://doi.org/10.1371/journal.pone.0148724