Random Forest enhancement using improved Artificial Fish Swarm for the medial knee contact force prediction

Knee contact force (KCF) is an important factor to evaluate the knee joint function for the patients with knee joint impairment. However, the KCF measurement based on the instrumented prosthetic implants or inverse dynamics analysis is limited due to the invasive, expensive price and time consumption. In this work, we propose a KCF prediction method by integrating the Artificial Fish Swarm and the Random Forest algorithm. First, we train a Random Forest to learn the nonlinear relation between gait parameters (input) and contact pressures (output) based on a dataset of three patients instrumented with knee replacement. Then, we use the improved artificial fish group algorithm to optimize the main parameters of the Random Forest based KCF prediction model. The extensive experiments verify that our method can predict the medial knee contact force both before and after the intervention of gait patterns, and the performance outperforms the classical multi-body dynamics analysis and artificial neural network model.

[1]  Adel Nadjaran Toosi,et al.  Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applications , 2012, Artificial Intelligence Review.

[2]  Sumit Kumar,et al.  Medical image encryption using fractional discrete cosine transform with chaotic function , 2019, Medical & Biological Engineering & Computing.

[3]  Surangsee Dechjarern,et al.  Above-knee prosthesis design based on fatigue life using finite element method and design of experiment. , 2017, Medical engineering & physics.

[4]  Yu Liu,et al.  Lower extremity joint torque predicted by using artificial neural network during vertical jump. , 2009, Journal of biomechanics.

[5]  B. A. Shepherd,et al.  An Appraisal of a Decision Tree Approach to Image Classification , 1983, IJCAI.

[6]  Karim Abdel-Malek,et al.  Neural network for dynamic human motion prediction , 2016, Expert Syst. Appl..

[7]  G. Bergmann,et al.  Loading of the knee joint during activities of daily living measured in vivo in five subjects. , 2010, Journal of biomechanics.

[8]  D. D’Lima,et al.  An implantable telemetry device to measure intra-articular tibial forces. , 2005, Journal of biomechanics.

[9]  M. Torry,et al.  Effects of walking poles on lower extremity gait mechanics. , 2001, Medicine and science in sports and exercise.

[10]  Ziyun Ding,et al.  In Vivo Knee Contact Force Prediction Using Patient-Specific Musculoskeletal Geometry in a Segment-Based Computational Model. , 2016, Journal of biomechanical engineering.

[11]  Ales Procházka,et al.  Bayesian classification and analysis of gait disorders using image and depth sensors of Microsoft Kinect , 2015, Digit. Signal Process..

[12]  J Harlaar,et al.  Relationship between knee joint contact forces and external knee joint moments in patients with medial knee osteoarthritis: effects of gait modifications. , 2018, Osteoarthritis and cartilage.

[13]  Fei Liu,et al.  In vivo patellofemoral forces in high flexion total knee arthroplasty. , 2008, Journal of biomechanics.

[14]  Sangbaek Park,et al.  Finite element analysis of knee and ankle joint during gait based on motion analysis. , 2019, Medical engineering & physics.

[15]  Jaap H van Dieën,et al.  Methodological aspects of SEMG recordings for force estimation--a tutorial and review. , 2010, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[16]  Yumin Chen,et al.  Finding rough set reducts with fish swarm algorithm , 2015, Knowl. Based Syst..

[17]  Apostolos Georgakis,et al.  Fatigue analysis of the surface EMG signal in isometric constant force contractions using the averaged instantaneous frequency , 2003, IEEE Transactions on Biomedical Engineering.

[18]  Satoshi Hamai,et al.  Effect of Tibial Posterior Slope on Knee Kinematics, Quadriceps Force, and Patellofemoral Contact Force After Posterior-Stabilized Total Knee Arthroplasty. , 2015, The Journal of arthroplasty.

[19]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[20]  H.E.J. Veeger,et al.  Can shoulder joint reaction forces be estimated by neural networks? , 2016, Journal of biomechanics.

[21]  Ming Zhang,et al.  Redistribution of knee stress using laterally wedged insole intervention: Finite element analysis of knee-ankle-foot complex. , 2013, Clinical biomechanics.

[22]  Jing Zhang,et al.  A real-time topography of maximum contact pressure distribution at medial tibiofemoral knee implant during gait: Application to knee rehabilitation , 2015, Neurocomputing.

[23]  M S Andersen,et al.  Knee internal contact force in a varus malaligned phenotype in knee osteoarthritis (KOA). , 2017, Osteoarthritis and cartilage.

[24]  Benjamin J Fregly,et al.  Multibody dynamic simulation of knee contact mechanics. , 2004, Medical engineering & physics.

[25]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[26]  Walter Herzog,et al.  Model-based estimation of muscle forces exerted during movements. , 2007, Clinical biomechanics.

[27]  Timothy E Hewett,et al.  Finite element model of the knee for investigation of injury mechanisms: development and validation. , 2014, Journal of biomechanical engineering.

[28]  Benjamin J Fregly,et al.  Changes in in vivo knee contact forces through gait modification , 2013, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[29]  Zhongmin Jin,et al.  Concurrent prediction of ground reaction forces and moments and tibiofemoral contact forces during walking using musculoskeletal modelling. , 2017, Medical engineering & physics.

[30]  Tien-Tuan Dao,et al.  From deep learning to transfer learning for the prediction of skeletal muscle forces , 2018, Medical & Biological Engineering & Computing.

[31]  Gary R. Weckman,et al.  Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast , 2017, Applied Intelligence.

[32]  K. Kaczmarczyk,et al.  Gait classification in post-stroke patients using artificial neural networks. , 2009, Gait & posture.

[33]  Marcus G Pandy,et al.  Grand challenge competition to predict in vivo knee loads , 2012, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[34]  Zhe Du,et al.  Fish swarm window selection algorithm based on cell microscopic automatic focus , 2017, Cluster Computing.

[35]  Rebecca L. Krupenevich,et al.  Knee adduction moment peak and impulse do not change during the first six months of walking with a prosthesis. , 2018, Gait & posture.

[36]  Ling Wang,et al.  Evaluation of a subject-specific musculoskeletal modelling framework for load prediction in total knee arthroplasty. , 2016, Medical engineering & physics.

[37]  Mohammad Kia,et al.  Evaluation of a musculoskeletal model with prosthetic knee through six experimental gait trials. , 2014, Medical engineering & physics.

[38]  B. Koopman,et al.  A subject-specific musculoskeletal modeling framework to predict in vivo mechanics of total knee arthroplasty. , 2015, Journal of biomechanical engineering.

[39]  B. Fregly,et al.  Correlation between the knee adduction torque and medial contact force for a variety of gait patterns , 2007, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[40]  Zhongmin Jin,et al.  Gait modification and optimization using neural network-genetic algorithm approach: Application to knee rehabilitation , 2014, Expert Syst. Appl..

[41]  G. Bergmann,et al.  Hip contact forces and gait patterns from routine activities. , 2001, Journal of biomechanics.

[42]  Seungbum Koo,et al.  Intra-Articular Knee Contact Force Estimation During Walking Using Force-Reaction Elements and Subject-Specific Joint Model. , 2016, Journal of biomechanical engineering.

[43]  G. Bergmann,et al.  Standardized Loads Acting in Hip Implants , 2014, PloS one.

[44]  Ling Wang,et al.  Feed forward artificial neural network to predict contact force at medial knee joint: Application to gait modification , 2014, Neurocomputing.

[45]  Xuan Zhang,et al.  Human lower extremity joint moment prediction: A wavelet neural network approach , 2014, Expert Syst. Appl..

[46]  J. L. Astephen,et al.  Biomechanical changes at the hip, knee, and ankle joints during gait are associated with knee osteoarthritis severity , 2008, Journal of orthopaedic research : official publication of the Orthopaedic Research Society.

[47]  Zhiwei Ni,et al.  Improved discrete artificial fish swarm algorithm combined with margin distance minimization for ensemble pruning , 2019, Comput. Ind. Eng..

[48]  Yali Amit,et al.  Shape Quantization and Recognition with Randomized Trees , 1997, Neural Computation.

[49]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[50]  Jeffrey A. Reinbolt,et al.  From the Selectedworks of Jeffrey A. Reinbolt Design of Patient-specific Gait Modifications for Knee Osteoarthritis Rehabilitation Design of Patient-specific Gait Modifications for Knee Osteoarthritis Rehabilitation , 2022 .