Prediction of Lower Limb Joint Angles and Moments During Gait Using Artificial Neural Networks

Overview

Journal Med Biol Eng Comput

Publisher Springer

Specialties Biomedical Engineering
Medical Informatics

Date 2019 Dec 12

PMID 31823114

Citations 29

Authors

Marion Mundt

Wolf Thomsen

Tom Witter

Arnd Koeppe

Sina David

Franz Bamer

Wolfgang Potthast

Bernd Markert

Affiliations

Soon will be listed here.

Abstract

In recent years, gait analysis outside the laboratory attracts more and more attention in clinical applications as well as in life sciences. Wearable sensors such as inertial sensors show high potential in these applications. Unfortunately, they can only measure kinematic motions patterns indirectly and the outcome is currently jeopardized by measurement discrepancies compared with the gold standard of optical motion tracking. The aim of this study was to overcome the limitation of measurement discrepancies and the missing information on kinetic motion parameters using a machine learning application based on artificial neural networks. For this purpose, inertial sensor data-linear acceleration and angular rate-was simulated from a database of optical motion tracking data and used as input for a feedforward and long short-term memory neural network to predict the joint angles and moments of the lower limbs during gait. Both networks achieved mean correlation coefficients higher than 0.80 in the minor motion planes, and correlation coefficients higher than 0.98 in the sagittal plane. These results encourage further applications of artificial intelligence to support gait analysis. Graphical Abstract The graphical abstract displays the processing of the data: IMU data is used as input to a feedforward and a long short-term memory neural network to predict the joint kinematics and kinetics of the lower limbs during gait.

Citing Articles

Comparing sparse inertial sensor setups for sagittal-plane walking and running reconstructions.

Dorschky E, Nitschke M, Mayer M, Weygers I, Gassner H, Seel T Front Bioeng Biotechnol. 2025; 13:1507162.

PMID: 40046809 PMC: 11879983. DOI: 10.3389/fbioe.2025.1507162.

Predicting noncontact injuries of professional football players using machine learning.

Freitas D, Mostafa S, Caldeira R, Santos F, Ferme E, Gouveia E PLoS One. 2025; 20(1):e0315481.

PMID: 39746031 PMC: 11694968. DOI: 10.1371/journal.pone.0315481.

Estimation of Lower Limb Joint Angles Using sEMG Signals and RGB-D Camera.

Du G, Ding Z, Guo H, Song M, Jiang F Bioengineering (Basel). 2024; 11(10).

PMID: 39451402 PMC: 11504533. DOI: 10.3390/bioengineering11101026.

Multibody Model with Foot-Deformation Approach for Estimating Ground Reaction Forces and Moments and Joint Torques during Level Walking through Optical Motion Capture without Optimization Techniques.

Haraguchi N, Hase K Sensors (Basel). 2024; 24(9).

PMID: 38732898 PMC: 11086093. DOI: 10.3390/s24092792.

Estimation of Kinetics Using IMUs to Monitor and Aid in Clinical Decision-Making during ACL Rehabilitation: A Systematic Review.

Krishnakumar S, van Beijnum B, Baten C, Veltink P, Buurke J Sensors (Basel). 2024; 24(7).

PMID: 38610374 PMC: 11014074. DOI: 10.3390/s24072163.

References

Goulermas J, Findlow A, Nester C, Liatsis P, Zeng X, Kenney L . An instance-based algorithm with auxiliary similarity information for the estimation of gait kinematics from wearable sensors. IEEE Trans Neural Netw. 2008; 19(9):1574-82. DOI: 10.1109/TNN.2008.2000808. View

Argent R, Drummond S, Remus A, OReilly M, Caulfield B . Evaluating the use of machine learning in the assessment of joint angle using a single inertial sensor. J Rehabil Assist Technol Eng. 2019; 6:2055668319868544. PMC: 6700879. DOI: 10.1177/2055668319868544. View

Wu G, Siegler S, Allard P, Kirtley C, Leardini A, Rosenbaum D . ISB recommendation on definitions of joint coordinate system of various joints for the reporting of human joint motion--part I: ankle, hip, and spine. International Society of Biomechanics. J Biomech. 2002; 35(4):543-8. DOI: 10.1016/s0021-9290(01)00222-6. View

Vienne A, Barrois R, Buffat S, Ricard D, Vidal P . Inertial Sensors to Assess Gait Quality in Patients with Neurological Disorders: A Systematic Review of Technical and Analytical Challenges. Front Psychol. 2017; 8:817. PMC: 5435996. DOI: 10.3389/fpsyg.2017.00817. View

Hochreiter S, Schmidhuber J . Long short-term memory. Neural Comput. 1997; 9(8):1735-80. DOI: 10.1162/neco.1997.9.8.1735. View

Robert-Lachaine X, Mecheri H, Larue C, Plamondon A . Validation of inertial measurement units with an optoelectronic system for whole-body motion analysis. Med Biol Eng Comput. 2016; 55(4):609-619. DOI: 10.1007/s11517-016-1537-2. View

Hu B, Dixon P, Jacobs J, Dennerlein J, Schiffman J . Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking. J Biomech. 2018; 71:37-42. DOI: 10.1016/j.jbiomech.2018.01.005. View

Caldas R, Mundt M, Potthast W, de Lima Neto F, Markert B . A systematic review of gait analysis methods based on inertial sensors and adaptive algorithms. Gait Posture. 2017; 57:204-210. DOI: 10.1016/j.gaitpost.2017.06.019. View

Gers F, Schmidhuber J, Cummins F . Learning to forget: continual prediction with LSTM. Neural Comput. 2000; 12(10):2451-71. DOI: 10.1162/089976600300015015. View

10.

Nuesch C, Roos E, Pagenstert G, Mundermann A . Measuring joint kinematics of treadmill walking and running: Comparison between an inertial sensor based system and a camera-based system. J Biomech. 2017; 57:32-38. DOI: 10.1016/j.jbiomech.2017.03.015. View

11.

Komnik I, Weiss S, Fantini Pagani C, Potthast W . Motion analysis of patients after knee arthroplasty during activities of daily living--a systematic review. Gait Posture. 2015; 41(2):370-7. DOI: 10.1016/j.gaitpost.2015.01.019. View

12.

Mundt M, Thomsen W, David S, Dupre T, Bamer F, Potthast W . Assessment of the measurement accuracy of inertial sensors during different tasks of daily living. J Biomech. 2018; 84:81-86. DOI: 10.1016/j.jbiomech.2018.12.023. View

13.

Brunner T, Lauffenburger J, Changey S, Basset M . Magnetometer-augmented IMU simulator: in-depth elaboration. Sensors (Basel). 2015; 15(3):5293-310. PMC: 4435162. DOI: 10.3390/s150305293. View

14.

Komnik I, Peters M, Funken J, David S, Weiss S, Potthast W . Non-Sagittal Knee Joint Kinematics and Kinetics during Gait on Level and Sloped Grounds with Unicompartmental and Total Knee Arthroplasty Patients. PLoS One. 2016; 11(12):e0168566. PMC: 5176302. DOI: 10.1371/journal.pone.0168566. View

15.

Seel T, Raisch J, Schauer T . IMU-based joint angle measurement for gait analysis. Sensors (Basel). 2014; 14(4):6891-909. PMC: 4029684. DOI: 10.3390/s140406891. View

16.

Findlow A, Goulermas J, Nester C, Howard D, Kenney L . Predicting lower limb joint kinematics using wearable motion sensors. Gait Posture. 2007; 28(1):120-6. DOI: 10.1016/j.gaitpost.2007.11.001. View

17.

Robert-Lachaine X, Mecheri H, Larue C, Plamondon A . Accuracy and repeatability of single-pose calibration of inertial measurement units for whole-body motion analysis. Gait Posture. 2017; 54:80-86. DOI: 10.1016/j.gaitpost.2017.02.029. View

18.

Kay R, Dennis S, Rethlefsen S, REYNOLDS R, Skaggs D, Tolo V . The effect of preoperative gait analysis on orthopaedic decision making. Clin Orthop Relat Res. 2000; (372):217-22. DOI: 10.1097/00003086-200003000-00023. View

19.

Struzik A, Juras G, Pietraszewski B, Rokita A . Effect of drop jump technique on the reactive strength index. J Hum Kinet. 2017; 52:157-164. PMC: 5260527. DOI: 10.1515/hukin-2016-0003. View

20.

Goulermas J, Howard D, Nester C, Jones R, Ren L . Regression techniques for the prediction of lower limb kinematics. J Biomech Eng. 2006; 127(6):1020-4. DOI: 10.1115/1.2049328. View