Iranian Journal of Biomedical Engineering (IJBME)
نشریه علمی مهندسی پزشکی زیستی

IMU-based Estimation of the Knee Contact Force using Artificial Neural Networks

Document Type : Full Research Paper

Authors

Alireza Rezaie Zangene 1
Ramila Abedi Azar 2
Hamidreza Naserpour 3
Seyyed Hamed Hosseini Nasab 4

1 M.Sc. Department of Biomechanics and Sports Injuries, Faculty of Physical Education and Sport Sciences, Kharazmi University, Tehran, Iran / National Brain Mapping Laboratory, Tehran, Iran

2 Ph.D. Student, Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran

3 Instructor, Department of Biomechanics and Sports Injuries, Faculty of Physical Education and Sport Sciences, Kharazmi University, Tehran, Iran

4 Researcher, Laboratory for Movement Biomechanics, ETH Zürich, Zürich, Switzerland

https://doi.org/10.22041/ijbme.2023.1998736.1834
Abstract
Knee joint contact force (KCF) plays a significant role in the occurrence and progression of knee osteoarthritis (KOA) disease. KCF can be used in monitoring rehabilitation progress after knee arthroplasty surgery and the design of prostheses. Currently, measuring KCF is dependent on the data extracted from gait laboratories. The combination of artificial neural networks (ANNs) and wearable technology can overcome the limitations imposed by lab-based analysis in measuring KCF. Therefore, the present study aimed to investigate the potential of a fully-connected neural network (FCNN) in predicting the KCF via three inertial measurement unit (IMU) sensors attached to the pelvis, thigh, and shank segments. Ten healthy male volunteers participated in this study. The 3D marker trajectories and ground reaction forces (GRF) were captured at 200 Hz and 1000 Hz sampling frequencies during level-ground walking. Using a generic OpenSim model, the KCF was estimated through static optimization. The resultant KCF estimated by the musculoskeletal model was then used as the target of the neural network, while linear acceleration and 3D angular velocity data captured by three IMUs were considered as the network inputs. The network performance was investigated at intra- and inter-subject levels. Based on our findings, the proposed network of this study enables the prediction of KCF with 89% and 79% accuracy (based on the Pearson correlation coefficient) at the intra- and inter-subject levels, respectively. The results of this study promise the possibility of using IMU sensors in predicting KCF outside the lab and during daily activities.

Keywords

Inertial Measurement Unit
Knee Contact Force
Knee Osteoarthritis
Continuous Estimation
Artificial Neural Networks
Musculoskeletal Modeling
OpenSim

Subjects

  1. A. Louw, J. Manilall, and K. A. Grimmer, “Epidemiology of knee injuries among adolescents: a systematic review,” Br. J. Sports Med., vol. 42, no. 1, pp. 2–10, 2008, doi: 10.1136/BJSM.2007.035360.
  2. E. Taunton, M. B. Ryan, D. B. Clement, D. C. McKenzie, D. R. Lloyd-Smith, and B. D. Zumbo, “A retrospective case-control analysis of 2002 running injuries,” Br. J. Sports Med., vol. 36, no. 2, pp. 95–101, 2002, doi: 10.1136/BJSM.36.2.95.
  3. Naserpour, E. Shirzad, M. Khaleghi Tazji, and A. Letafatkar, “The comparison of selected kinetic factors during a cross-cutting maneuver in soccer players with athletics groin pain and healthy ones: Implications for injury prevention,” Journal of Exercise Science and Medicine, 12(2).
  4. D. D’Lima, B. J. Fregly, S. Patil, N. Steklov, and C. W. Colwell Jr, “Knee joint forces: prediction, measurement, and significance,” Proc. Inst. Mech. Eng. H, vol. 226, no. 2, pp. 95–102, 2012, doi: 10.1177/0954411911433372.
  5. J. Baliunas et al., “Increased knee joint loads during walking are present in subjects with knee osteoarthritis,” Osteoarthritis Cartilage, vol. 10, no. 7, pp. 573–579, 2002, doi: 10.1053/JOCA.2002.0797.
  6. Weiss and C. Whatman, “Biomechanics Associated with Patellofemoral Pain and ACL Injuries in Sports,” Sport. Med., vol. 45, no. 9, pp. 1325–1337, 2015, doi: 10.1007/S40279-015-0353-4.
  7. C. Lawrence et al., “Estimates of the prevalence of arthritis and other rheumatic conditions in the United States. Part II,” Arthritis Rheum., vol. 58, no. 1, pp. 26–35, 2008, doi: 10.1002/ART.23176.
  8. J. Wallace et al., “Knee osteoarthritis has doubled in prevalence since the mid-20th century,” Proc. Natl. Acad. Sci. U. S. A., vol. 114, no. 35, pp. 9332–9336, 2017, doi: 10.1073/PNAS.1703856114.
  9. Kobsar et al., “Wearable inertial sensors for gait analysis in adults with osteoarthritis-A scoping review,” Sensors (Basel), vol. 20, no. 24, p. 7143, 2020, doi: 10.3390/S20247143.
  10. Blagojevic, C. Jinks, A. Jeffery, and K. P. Jordan, “Risk factors for onset of osteoarthritis of the knee in older adults: a systematic review and meta-analysis,” Osteoarthritis Cartilage, vol. 18, no. 1, pp. 24–33, 2010, doi: 10.1016/j.joca.2009.08.010.
  11. Richards and J. S. Higginson, “Knee contact force in subjects with symmetrical OA grades: differences between OA severities,” J. Biomech., vol. 43, no. 13, pp. 2595–2600, 2010, doi: 10.1016/j.jbiomech.2010.05.006.
  12. J. Fregly, J. A. Reinbolt, K. L. Rooney, K. H. Mitchell, and T. L. Chmielewski, “Design of patient-specific gait modifications for knee osteoarthritis rehabilitation,” IEEE Trans. Biomed. Eng., vol. 54, no. 9, pp. 1687–1695, 2007, doi: 10.1109/TBME.2007.891934.
  13. M. Zingde and J. Slamin, “Biomechanics of the knee joint, as they relate to arthroplasty,” Orthop. Trauma, vol. 31, no. 1, pp. 1–7, 2017, doi: 10.1016/j.mporth.2016.10.001.
  14. D. D’Lima, N. Steklov, S. Patil, and C. W. Colwell, “The Mark Coventry award: In vivo knee forces during recreation and exercise after knee arthroplasty,” Clin. Orthop. Relat. Res., vol. 466, no. 11, pp. 2605–2611, 2008, doi: 10.1007/S11999-008-0345-X.
  15. D. Komistek, T. R. Kane, M. Mahfouz, J. A. Ochoa, and D. A. Dennis, “Knee mechanics: a review of past and present techniques to determine in vivo loads,” J. Biomech., vol. 38, no. 2, pp. 215–228, 2005, doi: 10.1016/j.jbiomech.2004.02.041.
  16. L. Delp et al., “OpenSim: open-source software to create and analyze dynamic simulations of movement,” IEEE Trans. Biomed. Eng., vol. 54, no. 11, pp. 1940–1950, 2007, doi: 10.1109/TBME.2007.901024.
  17. Damsgaard, J. Rasmussen, S. T. Christensen, E. Surma, and M. de Zee, “Analysis of musculoskeletal systems in the AnyBody Modeling System,” Simul. Model. Pract. Theory, vol. 14, no. 8, pp. 1100–1111, 2006, doi: 10.1016/J.SIMPAT.2006.09.001.
  18. Curreli, F. Di Puccio, G. Davico, L. Modenese, and M. Viceconti, “Using Musculoskeletal Models to Estimate in vivo Total Knee Replacement Kinematics and Loads: Effect of Differences Between Models,” Front. Bioeng. Biotechnol., vol. 9, p. 611, 2021, doi: 10.3389/FBIOE.2021.703508.
  19. R. Zangene and A. Abbasi, "Continuous Estimation of Knee Joint Angle during Squat from sEMG using Artificial Neural Networks," 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME), pp. 75-78, 2020, doi: 10.1109/ICBME51989.2020.9319429.
  20. Mundt et al., “Estimation of Gait Mechanics Based on Simulated and Measured IMU Data Using an Artificial Neural Network,” Front. Bioeng. Biotechnol., vol. 8, p. 41, 2020, doi: 10.3389/FBIOE.2020.00041.
  21. Cerfoglio, M. Galli, M. Tarabini, F. Bertozzi, C. Sforza, and M. Zago, “Machine learning-based estimation of Ground Reaction Forces and knee joint kinetics from inertial sensors while performing a Vertical Drop Jump,” Sensors (Basel), vol. 21, no. 22, p. 7709, 2021, doi: 10.3390/S21227709.
  22. M. Ardestani et al., “Feed forward artificial neural network to predict contact force at medial knee joint: Application to gait modification,” Neurocomputing, vol. 139, pp. 114–129, 2014, doi: 10.1016/j.neucom.2014.02.054.
  23. Giarmatzis, E. I. Zacharaki, and K. Moustakas, “Real-time prediction of joint forces by motion capture and machine learning,” Sensors (Basel), vol. 20, no. 23, p. 6933, 2020, doi: 10.3390/S20236933.
  24. S. Burton 2nd, C. A. Myers, and P. J. Rullkoetter, “Machine learning for rapid estimation of lower extremity muscle and joint loading during activities of daily living,” J. Biomech., vol. 123, no. 110439, p. 110439, 2021, doi: 10.1016/j.jbiomech.2021.110439.
  25. Lebel, P. Boissy, M. Hamel, and C. Duval, “Inertial measures of motion for clinical biomechanics: comparative assessment of accuracy under controlled conditions - effect of velocity,” PLoS One, vol. 8, no. 11, p. e79945, 2013, doi: 10.1371/JOURNAL.PONE.0079945.
  26. Gao, G. Liu, F. Liang, and W. H. Liao, “IMU-Based Locomotion Mode Identification for Transtibial Prostheses, Orthoses, and Exoskeletons,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 6, pp. 1334–1343, 2020, doi: 10.1109/TNSRE.2020.2987155.
  27. D. Pollard, B. C. Heiderscheit, R. E. A. van Emmerik, and J. Hamill, “Gender differences in lower extremity coupling variability during an unanticipated cutting maneuver,” J. Appl. Biomech., vol. 21, no. 2, pp. 143–152, 2005, doi: 10.1123/jab.21.2.143.
  28. G. E. Robertson, G. E. Caldwell, J. Hamill, G. Kamen, and S. N. Whittlesey, Research Methods in Biomechanics, 2nd ed. Champaign, IL: Human Kinetics, 2013.
  29. E. Milner and M. R. Paquette, “A kinematic method to detect foot contact during running for all foot strike patterns,” J. Biomech., vol. 48, no. 12, pp. 3502–3505, 2015, doi: 10.1016/j.jbiomech.2015.07.036.
  30. L. Delp, J. P. Loan, M. G. Hoy, F. E. Zajac, E. L. Topp, and J. M. Rosen, “An Interactive Graphics-Based Model of the Lower Extremity to Study Orthopaedic Surgical Procedures,” IEEE Trans. Biomed. Eng., vol. 37, no. 8, pp. 757–767, 1990, doi: 10.1109/10.102791.
  31. C. Anderson and M. G. Pandy, “Static and dynamic optimization solutions for gait are practically equivalent,” J. Biomech., vol. 34, no. 2, pp. 153–161, 2001, doi: 10.1016/s0021-9290(00)00155-x .
  32. Pedregosa et al., "Scikit-learn: Machine learning in Python", J. Mach. Learn. Res., vol. 12, pp. 2825-2830, Feb. 2011.
  33. J. Dreyer et al., “European Society of Biomechanics S.M. Perren Award 2022: Standardized tibio-femoral implant loads and kinematics,” J. Biomech., vol. 141, p. 111171, 2022, doi: 10.1016/J.JBIOMECH.2022.111171.
  34. R. Zangene, A. Abbasi, and K. Nazarpour, “Estimation of lower limb kinematics during squat task in different loading using sEMG activity and deep recurrent neural networks,” Sensors (Basel), vol. 21, no. 23, p. 7773, 2021, doi: 10.3390/S21237773.
  35. De Brabandere, J. Emmerzaal, A. Timmermans, I. Jonkers, B. Vanwanseele, and J. Davis, “A machine learning approach to estimate hip and knee joint loading using a mobile phone-embedded IMU,” Front. Bioeng. Biotechnol., vol. 8, p. 320, 2020, doi: 10.3389/FBIOE.2020.00320.
Iranian Journal of Biomedical Engineering (IJBME)
Volume 16, Issue 4
Winter 2023
Pages 335-344

  • Receive Date 25 March 2023
  • Revise Date 21 June 2023
  • Accept Date 30 July 2023

Home

Contact Us