Literature DB >> 33422707

A neural network to predict the knee adduction moment in patients with osteoarthritis using anatomical landmarks obtainable from 2D video analysis.

M A Boswell1, S D Uhlrich2, Ł Kidziński3, K Thomas4, J A Kolesar5, G E Gold6, G S Beaupre7, S L Delp8.   

Abstract

OBJECTIVE: The knee adduction moment (KAM) can inform treatment of medial knee osteoarthritis; however, measuring the KAM requires an expensive gait analysis laboratory. We evaluated the feasibility of predicting the peak KAM during natural and modified walking patterns using the positions of anatomical landmarks that could be identified from video analysis.
METHOD: Using inverse dynamics, we calculated the KAM for 86 individuals (64 with knee osteoarthritis, 22 without) walking naturally and with foot progression angle modifications. We trained a neural network to predict the peak KAM using the 3-dimensional positions of 13 anatomical landmarks measured with motion capture (3D neural network). We also trained models to predict the peak KAM using 2-dimensional subsets of the dataset to simulate 2-dimensional video analysis (frontal and sagittal plane neural networks). Model performance was evaluated on a held-out, 8-person test set that included steps from all trials.
RESULTS: The 3D neural network predicted the peak KAM for all test steps with r2( Murray et al., 2012) 2 = 0.78. This model predicted individuals' average peak KAM during natural walking with r2( Murray et al., 2012) 2 = 0.86 and classified which 15° foot progression angle modifications reduced the peak KAM with accuracy = 0.85. The frontal plane neural network predicted peak KAM with similar accuracy (r2( Murray et al., 2012) 2 = 0.85) to the 3D neural network, but the sagittal plane neural network did not (r2( Murray et al., 2012) 2 = 0.14).
CONCLUSION: Using the positions of anatomical landmarks from motion capture, a neural network accurately predicted the peak KAM during natural and modified walking. This study demonstrates the feasibility of measuring the peak KAM using positions obtainable from 2D video analysis.
Copyright © 2021 Osteoarthritis Research Society International. All rights reserved.

Entities:  

Keywords:  Gait; Knee adduction moment; Machine learning; Neural network; Osteoarthritis; Video motion analysis

Mesh:

Year:  2021        PMID: 33422707      PMCID: PMC7925428          DOI: 10.1016/j.joca.2020.12.017

Source DB:  PubMed          Journal:  Osteoarthritis Cartilage        ISSN: 1063-4584            Impact factor:   6.576


  40 in total

1.  Assessment of the functional method of hip joint center location subject to reduced range of hip motion.

Authors:  Stephen J Piazza; Ahmet Erdemir; Noriaki Okita; Peter R Cavanagh
Journal:  J Biomech       Date:  2004-03       Impact factor: 2.712

2.  Toe-in gait reduces the first peak knee adduction moment in patients with medial compartment knee osteoarthritis.

Authors:  Pete B Shull; Rebecca Shultz; Amy Silder; Jason L Dragoo; Thor F Besier; Mark R Cutkosky; Scott L Delp
Journal:  J Biomech       Date:  2012-11-10       Impact factor: 2.712

3.  Ambulatory measurement of the knee adduction moment in patients with osteoarthritis of the knee.

Authors:  Josien J C van den Noort; Martin van der Esch; Martijn P M Steultjens; Joost Dekker; Martin H M Schepers; Peter H Veltink; Jaap Harlaar
Journal:  J Biomech       Date:  2012-10-31       Impact factor: 2.712

4.  Real-Time Estimation of Knee Adduction Moment for Gait Retraining in Patients With Knee Osteoarthritis.

Authors:  Chao Wang; Peter P K Chan; Ben M F Lam; Sizhong Wang; Janet H Zhang; Zoe Y S Chan; Rosa H M Chan; Kevin K W Ho; Roy T H Cheung
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2020-03-05       Impact factor: 3.802

5.  Number of Persons With Symptomatic Knee Osteoarthritis in the US: Impact of Race and Ethnicity, Age, Sex, and Obesity.

Authors:  Bhushan R Deshpande; Jeffrey N Katz; Daniel H Solomon; Edward H Yelin; David J Hunter; Stephen P Messier; Lisa G Suter; Elena Losina
Journal:  Arthritis Care Res (Hoboken)       Date:  2016-11-03       Impact factor: 4.794

6.  Lateral trunk lean and medializing the knee as gait strategies for knee osteoarthritis.

Authors:  T A Gerbrands; M F Pisters; P J R Theeven; S Verschueren; B Vanwanseele
Journal:  Gait Posture       Date:  2016-11-08       Impact factor: 2.840

7.  Six-week gait retraining program reduces knee adduction moment, reduces pain, and improves function for individuals with medial compartment knee osteoarthritis.

Authors:  Pete B Shull; Amy Silder; Rebecca Shultz; Jason L Dragoo; Thor F Besier; Scott L Delp; Mark R Cutkosky
Journal:  J Orthop Res       Date:  2013-03-12       Impact factor: 3.494

8.  Knee adduction moment and medial contact force--facts about their correlation during gait.

Authors:  Ines Kutzner; Adam Trepczynski; Markus O Heller; Georg Bergmann
Journal:  PLoS One       Date:  2013-12-02       Impact factor: 3.240

9.  Evaluation of 3D Markerless Motion Capture Accuracy Using OpenPose With Multiple Video Cameras.

Authors:  Nobuyasu Nakano; Tetsuro Sakura; Kazuhiro Ueda; Leon Omura; Arata Kimura; Yoichi Iino; Senshi Fukashiro; Shinsuke Yoshioka
Journal:  Front Sports Act Living       Date:  2020-05-27
View more
  3 in total

1.  Predicting the Internal Knee Abduction Impulse During Walking Using Deep Learning.

Authors:  Issam Boukhennoufa; Zainab Altai; Xiaojun Zhai; Victor Utti; Klaus D McDonald-Maier; Bernard X W Liew
Journal:  Front Bioeng Biotechnol       Date:  2022-05-12

2.  Predicting knee adduction moment response to gait retraining with minimal clinical data.

Authors:  Nataliya Rokhmanova; Katherine J Kuchenbecker; Peter B Shull; Reed Ferber; Eni Halilaj
Journal:  PLoS Comput Biol       Date:  2022-05-16       Impact factor: 4.779

Review 3.  Applications of Pose Estimation in Human Health and Performance across the Lifespan.

Authors:  Jan Stenum; Kendra M Cherry-Allen; Connor O Pyles; Rachel D Reetzke; Michael F Vignos; Ryan T Roemmich
Journal:  Sensors (Basel)       Date:  2021-11-03       Impact factor: 3.576

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.