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

Deshpande, 2016, The number of persons with symptomatic knee osteoarthritis in the United States: impact of race/ethnicity, age, sex, and obesity, Arthritis Care Res, 68, 1743, 10.1002/acr.22897 Murray, 2012, Disability-adjusted life years (DALYs) for 291 diseases and injuries in 21 regions, 1990-2010: a systematic analysis for the Global Burden of Disease Study 2010, Lancet, 380, 2197, 10.1016/S0140-6736(12)61689-4 Wise, 2012, Patterns of compartment involvement in tibiofemoral osteoarthritis in men and women and in whites and African Americans, Arthritis Care Res, 64, 847, 10.1002/acr.21606 Mündermann, 2008, In vivo knee loading characteristics during activities of daily living as measured by an instrumented total knee replacement, J Orthop Res, 26, 1167, 10.1002/jor.20655 Kutzner, 2013, Knee adduction moment and medial contact force-facts about their correlation during gait, PloS One, 8, 8, 10.1371/journal.pone.0081036 Hurwitz, 2002, The knee adduction moment during gait in subjects with knee osteoarthritis is more closely correlated with static alignment than radiographic disease severity, toe out angle and pain, J Orthop Res, 20, 101, 10.1016/S0736-0266(01)00081-X Sharma, 1998, Knee adduction moment, serum hyaluronan level, and disease severity in medial tibiofemoral osteoarthritis, Arthritis Rheum, 41, 1233, 10.1002/1529-0131(199807)41:7<1233::AID-ART14>3.0.CO;2-L Foroughi, 2009, The association of external knee adduction moment with biomechanical variables in osteoarthritis: a systematic review, Knee, 16, 303, 10.1016/j.knee.2008.12.007 Miyazaki, 2002, Dynamic load at baseline can predict radiographic disease progression in medial compartment knee osteoarthritis, Ann Rheum Dis, 61, 617, 10.1136/ard.61.7.617 Mündermann, 2004, Potential strategies to reduce medial compartment loading in patients with knee osteoarthritis of varying severity: reduced walking speed, Arthritis Rheum, 50, 1172, 10.1002/art.20132 Mündermann, 2005, Secondary gait changes in patients with medial compartment knee osteoarthritis: increased load at the ankle, knee, and hip during walking, Arthritis Rheum, 52, 2835, 10.1002/art.21262 Amin, 2004, Knee adduction moment and development of chronic knee pain in elders, Arthritis Care Res, 51, 371, 10.1002/art.20396 Prodromos, 1985, A relationship between gait and clinical changes following high tibial osteotomy, J Bone Jt Surg, 67, 1188, 10.2106/00004623-198567080-00007 Simic, 2012, Trunk lean gait modification and knee joint load in people with medial knee osteoarthritis: the effect of varying trunk lean angles, Arthritis Care Res, 64, 1545, 10.1002/acr.21724 Mündermann, 2008, Implications of increased medio-lateral trunk sway for ambulatory mechanics, J Biomech, 41, 165, 10.1016/j.jbiomech.2007.07.001 Dunphy, 2016, Contralateral pelvic drop during gait increases knee adduction moments of asymptomatic individuals, Hum Mov Sci, 49, 27, 10.1016/j.humov.2016.05.008 Fregly, 2007, Design of patient-specific gait modifications for knee osteoarthritis rhabilitation, IEEE Trans Biomed Eng, 54, 1687, 10.1109/TBME.2007.891934 Gerbrands, 2017, Lateral trunk lean and medializing the knee as gait strategies for knee osteoarthritis, Gait Posture, 51, 247, 10.1016/j.gaitpost.2016.11.014 Shull, 2013, Six-week gait retraining program reduces knee adduction moment, reduces pain, and improves function for individuals with medial compartment knee osteoarthritis, J Orthop Res, 31, 1020, 10.1002/jor.22340 Hunt, 2014, Effects of a 10-week toe-out gait modification intervention in people with medial knee osteoarthritis: a pilot, feasibility study, Osteoarthritis Cartilage, 22, 904, 10.1016/j.joca.2014.04.007 Gerbrands, 2014, Individual selection of gait retraining strategies is essential to optimally reduce medial knee load during gait, Clin Biomech, 29, 828, 10.1016/j.clinbiomech.2014.05.005 Shull, 2015, Muscle force modification strategies are not consistent for gait retraining to reduce the knee adduction moment in individuals with knee osteoarthritis, J Biomech, 48, 3163, 10.1016/j.jbiomech.2015.07.006 Uhlrich, 2018, Subject-specific toe-in or toe-out gait modifications reduce the larger knee adduction moment peak more than a non-personalized approach, J Biomech, 66, 103, 10.1016/j.jbiomech.2017.11.003 van den Noort, 2013, Ambulatory measurement of the knee adduction moment in patients with osteoarthritis of the knee, J Biomech, 46, 43, 10.1016/j.jbiomech.2012.09.030 Cao, 2019, OpenPose : realtime multi-person 2D pose estimation using part affinity fields, IEEE Trans Pattern Anal Mach Intell, 1 Iskakov, 2019, Learnable triangulation of human pose, Proc IEEE Int Conf Comput Vis, 7717 Nakano, 2020, Evaluation of 3D markerless motion capture accuracy using OpenPose with multiple video cameras, Front Sport Act Living, 2, 1 Halilaj, 2018, Machine learning in human movement biomechanics: best practices, common pitfalls, and new opportunities, J Biomech, 81, 1, 10.1016/j.jbiomech.2018.09.009 Ł, 2020, Deep neural networks enable quantitative movement analysis using single-camera videos, Nat Commun, 11 Favre, 2012, A neural network model to predict knee adduction moment during walking based on ground reaction force and anthropometric measurements, J Biomech, 45, 692, 10.1016/j.jbiomech.2011.11.057 Ardestani, 2014, Human lower extremity joint moment prediction: a wavelet neural network approach, Expert Syst Appl, 41, 4422, 10.1016/j.eswa.2013.11.003 Stetter, 2020, A machine learning and wearable sensor based approach to estimate external knee flexion and adduction moments during various locomotion tasks, Front Bioeng Biotechnol, 8 Wang, 2020, Real-time estimation of knee adduction moment for gait retraining in patients with knee osteoarthritis, IEEE Trans Neural Syst Rehabil Eng, 28, 888, 10.1109/TNSRE.2020.2978537 Johnson, 2019, On-field player workload exposure and knee injury risk monitoring via deep learning, J Biomech, 93, 185, 10.1016/j.jbiomech.2019.07.002 Aljaaf, 2016, Evaluation of machine learning methods to predict knee loading from the movement of body segments, Proc Int Jt Conf Neural Networks, 2016-Octob, 5168 Piazza, 2004, Assessment of the functional method of hip joint center location subject to reduced range of hip motion, J Biomech, 37, 349, 10.1016/S0021-9290(03)00288-4 Tiulpin, 2018, Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach, Sci Rep, 8, 1, 10.1038/s41598-018-20132-7 Wang, 2016, Time series classification from scratch with deep neural networks: a strong baseline, arXiv, 1611, 6455 Kidziński, 2018 Glorot, 2010, Understanding the difficulty of training deep feedforward neural networks Xavier, 249 Kingma, 2015, Adam: a method for stochastic optimization, 1 Tibshirani, 1996, Regression shrinkage and selection via the lasso, J R Stat Soc Ser B, 58, 267 Friedman, 2010, Regularization paths for generalized linear models via coordinate descent, J Stat Software, 33, 1 2019 Nair, 2010, Rectified linear units improve Restricted Boltzmann machines Itti, 2000, A saliency-based search mechanism for overt and covert shifts of visual attention, Vis Res, 40, 1489, 10.1016/S0042-6989(99)00163-7 Kotikalapudi R, and Contributors. Keras-Vis. Published 2017. https://github.com/raghakot/keras-vis. Efron, 1993 Karatsidis, 2018 Shull, 2013, Toe-in gait reduces the first peak knee adduction moment in patients with medial compartment knee osteoarthritis, J Biomech, 46, 122, 10.1016/j.jbiomech.2012.10.019 Jenkyn, 2011, An analysis of the mechanisms for reducing the knee adduction moment during walking using a variable stiffness shoe in subjects with knee osteoarthritis, J Biomech, 44, 1271, 10.1016/j.jbiomech.2011.02.013 Ghorbani, 2019, Interpretation of neural networks is fragile, Proc Thirty-Third AAAI Conf Artif Intell., 33, 3681 Wang, 1990, The influence of walking mechanics and time on the results of proximal tibial osteotomy, J Bone Joint Surg Am, 72, 905, 10.2106/00004623-199072060-00017 Konrath, 2019, Estimation of the knee adduction moment and joint contact force during daily living activities using inertial motion capture, Sensors, 19, 10.3390/s19071681