{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T18:28:27Z","timestamp":1788546507878,"version":"build-2803163510"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate prediction of knee biomechanics during total knee replacement (TKR) surgery is crucial for optimal outcomes. This study investigates the application of machine learning (ML) techniques for real-time prediction of knee joint mechanics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A validated finite element (FE) model of the lower limb was used to generate a dataset of knee joint kinematics, kinetics, and contact mechanics. The models were trained on joint alignment data, ligament information, and external boundary conditions. Several predictive algorithms were explored, including linear regression (LRM), multilayer perceptron (MLP), bi-directional long short-term memory (biLSTM), convolutional neural network (CNN), and transformer-based approaches. The performance of these models was evaluated using average normalized root mean squared error (nRMSE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The biLSTM model achieved the highest accuracy, with a significantly lower nRMSE compared to other models. Compared to traditional FE or rigid body dynamics models, these predictive models offered significantly faster prediction speeds, enabling near-instantaneous insights into the TKR system\u2019s performance. The small size of the predictive models makes them suitable for deployment on edge devices potentially used in operating rooms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings suggest that real-time biomechanical prediction using biLSTM models has the potential to provide valuable feedback for surgeons during TKR surgery. Applications of this work could be applied to provide pre-operative guidance on optimal target implant alignment or given the real-time prediction ability of these models, could also be used intra-operatively after integration of patient-specific intra-op kinematic and soft-tissue information.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbioe.2024.1461768","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:45:56Z","timestamp":1736923556000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Evaluation of machine learning techniques for real-time prediction of implanted lower limb mechanics"],"prefix":"10.3389","volume":"12","author":[{"given":"Chase","family":"Maag","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clare K.","family":"Fitzpatrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul J.","family":"Rullkoetter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"041004","DOI":"10.1115\/1.4051834","article-title":"Apparatus for in vivo knee laxity assessment using high-speed stereo radiography","volume":"15","author":"Andreassen","year":"2021","journal-title":"J. Med. Device."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1016\/j.jbiomech.2009.06.028","article-title":"Verification of predicted specimen-specific natural and implanted patellofemoral kinematics during simulated deep knee bend","volume":"42","author":"Baldwin","year":"2009","journal-title":"J. Biomech."},{"key":"B3","doi-asserted-by":"publisher","first-page":"011007","DOI":"10.1115\/1.4063950","article-title":"Simultaneous evaluation of tibiofemoral and patellofemoral mechanics in total knee arthroplasty: a combined experimental and computational approach","volume":"146","author":"Behnam","year":"2024","journal-title":"J. Biomech. Eng."},{"key":"B4","doi-asserted-by":"publisher","first-page":"e86035","DOI":"10.1371\/journal.pone.0086035","article-title":"Standardized loads acting in knee implants","volume":"9","author":"Bergmann","year":"2014","journal-title":"PLoS One"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5792\/ksrr.2016.28.1.1","article-title":"Patient satisfaction after total knee arthroplasty","volume":"28","author":"Choi","year":"2016","journal-title":"Knee Surg. Relat. Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1115\/1.1516196","article-title":"The effect of vastus medialis forces on patello-femoral contact: a model-based study","volume":"124","author":"Dhaher","year":"2002","journal-title":"J. Biomech. Eng."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e24.00023","DOI":"10.5435\/JAAOSGlobal-D-24-00023","article-title":"Individualizing a total knee arthroplasty with three-dimensional planning","volume":"8","author":"Dossett","year":"2024","journal-title":"JAAOS Glob. Res. Rev."},{"key":"B8","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1016\/j.jbiomech.2009.10.039","article-title":"Computational assessment of the influence of vastus medialis obliquus function on patellofemoral pressures: model evaluation","volume":"43","author":"Elias","year":"2010","journal-title":"J. Biomech."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y","article-title":"InceptionTime: finding AlexNet for time series classification","author":"Fawaz","year":"2019"},{"key":"B10","first-page":"142","article-title":"Z-score normalization, hubness, and few-shot learning","author":"Fei","year":"2021"},{"key":"B11","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1080\/10255842.2012.684242","article-title":"Evaluating knee replacement mechanics during ADL with PID-controlled dynamic finite element analysis","volume":"17","author":"Fitzpatrick","year":"","journal-title":"Comput. Methods Biomech. Biomed. Engin."},{"key":"B12","doi-asserted-by":"publisher","first-page":"2092","DOI":"10.1016\/j.jbiomech.2012.05.035","article-title":"The role of patient, surgical, and implant design variation in total knee replacement performance","volume":"45","author":"Fitzpatrick","year":"2012","journal-title":"J. Biomech."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2398","DOI":"10.1016\/j.jbiomech.2014.04.024","article-title":"Developing simulations to reproduce in vivo fluoroscopy kinematics in total knee replacement patients","volume":"47","author":"Fitzpatrick","year":"","journal-title":"J. Biomech."},{"key":"B14","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.jbiomech.2011.09.009","article-title":"Development of a statistical model of knee kinetics for applications in pre-clinical testing","volume":"45","author":"Galloway","year":"2012","journal-title":"J. Biomech."},{"key":"B15","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jbiomech.2019.03.010","article-title":"Development of a statistical shape-function model of the implanted knee for real-time prediction of joint mechanics","volume":"88","author":"Gibbons","year":"2019","journal-title":"J. Biomech."},{"key":"B16","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1115\/1.3138397","article-title":"A joint coordinate system for the clinical description of three-dimensional motions: application to the knee","volume":"105","author":"Grood","year":"1983","journal-title":"J. Biomech. Eng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"081010","DOI":"10.1115\/1.4001678","article-title":"Verification of predicted knee replacement kinematics during simulated gait in the Kansas knee simulator","volume":"132","author":"Halloran","year":"2010","journal-title":"J. Biomech. Eng."},{"key":"B18","doi-asserted-by":"publisher","first-page":"0810041","DOI":"10.1115\/1.4033882","article-title":"A combined experimental and computational approach to subject-specific analysis of knee joint laxity","volume":"138","author":"Harris","year":"2016","journal-title":"J. Biomech. Eng."},{"key":"B19","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.knee.2022.11.010","article-title":"Computer-based analysis of different component positions and insert thicknesses on tibio-femoral and patello-femoral joint dynamics after cruciate-retaining total knee replacement","volume":"40","author":"Kebbach","year":"2023","journal-title":"Knee"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1016\/j.jbiomech.2008.09.032","article-title":"The effect of femoral component malrotation on patellar biomechanics","volume":"41","author":"Kessler","year":"2008","journal-title":"J. Biomech."},{"key":"B21","unstructured":"Adam: a method for stochastic optimization\n          \n          \n            \n              Kingma\n              D. P.\n            \n            \n              Ba\n              J.\n            \n          \n          \n          2014"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1016\/j.jbiomech.2006.07.027","article-title":"Comparison of long-term numerical and experimental total knee replacement wear during simulated gait loading","volume":"40","author":"Knight","year":"2007","journal-title":"J. Biomech."},{"key":"B23","doi-asserted-by":"publisher","first-page":"648356","DOI":"10.3389\/fbioe.2021.648356","article-title":"Total knee replacement: subject-specific modeling, finite element analysis, and evaluation of dynamic activities","volume":"9","author":"Loi","year":"2021","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"503","DOI":"10.3390\/bioengineering11050503","article-title":"Computational lower limb simulator boundary conditions to reproduce measured TKA loading in a cohort of telemetric implant patients","volume":"11","author":"Maag","year":"2024","journal-title":"Bioengineering"},{"key":"B25","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1115\/1.1846070","article-title":"Simulating dynamic activities using a five-Axis knee simulator","volume":"127","author":"Maletsky","year":"2005","journal-title":"J. Biomech. Eng."},{"key":"B26","doi-asserted-by":"publisher","first-page":"3253","DOI":"10.1007\/s11517-023-02890-3","article-title":"Estimation of lower limb joint moments based on the inverse dynamics approach: a comparison of machine learning algorithms for rapid estimation","volume":"61","author":"Mansour","year":"2023","journal-title":"Med. Biol. Eng. Comput."},{"key":"B27","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.knee.2005.03.004","article-title":"Biomechanics of the knee joint in flexion under various quadriceps forces","volume":"12","author":"Mesfar","year":"2005","journal-title":"Knee"},{"key":"B28","unstructured":"Tsai - a state-of-the-art deep learning library for time series and sequential data\n          \n          \n            \n              Oguiza\n              I.\n            \n          \n          \n          2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1007\/s10237-023-01726-1","article-title":"Subject-specific tribo-contact conditions in total knee replacements: a simulation framework across scales","volume":"22","author":"Rothammer","year":"2023","journal-title":"Biomech. Model. Mechanobiol."},{"key":"B30","unstructured":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition\n          \n          \n            \n              Sak\n              H.\n            \n            \n              Senior\n              A.\n            \n            \n              Beaufays\n              F.\n            \n          \n          \n          2014"},{"key":"B36","doi-asserted-by":"crossref","unstructured":"Automatic optimization of deep learning training through feature-aware-based dataset splitting\n          \n          106\n          \n            \n              Shahrabadi\n              S.\n            \n            \n              Ad\u00e3o\n              T.\n            \n            \n              Peres\n              E.\n            \n            \n              Morais\n              R.\n            \n            \n              Magalh\u00e3es\n              L. G.\n            \n            \n              Alves\n              V.\n            \n          \n          10.3390\/a17030106\n          Algorithms\n          17\n          2024","DOI":"10.3390\/a17030106"},{"key":"B31","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1002\/jor.21344","article-title":"Biomechanical effects of total knee arthroplasty component malrotation: a computational simulation","volume":"29","author":"Thompson","year":"2011","journal-title":"J. Orthop. Res."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1016\/j.jbiomech.2011.02.009","article-title":"Design optimization of a total knee replacement for improved constraint and flexion kinematics","volume":"44","author":"Willing","year":"2011","journal-title":"J. Biomech."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2172","DOI":"10.1002\/jor.24392","article-title":"Condylar-stabilized TKR may not fully compensate for PCL-deficiency: an in vitro cadaver study","volume":"37","author":"Willing","year":"2019","journal-title":"J. Orthop. Res."},{"key":"B34","first-page":"2114","article-title":"A transformer-based framework for multivariate time series representation learning","author":"Zerveas","year":"2021"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2024.1461768\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:46:00Z","timestamp":1736923560000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2024.1461768\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":35,"alternative-id":["10.3389\/fbioe.2024.1461768"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2024.1461768","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"article-number":"1461768"}}