{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:11:40Z","timestamp":1790802700188,"version":"4.1.0"},"reference-count":32,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Aesculap AG and Deutsche Forschungsgemeinschaft","award":["SFB\/CRC1444"],"award-info":[{"award-number":["SFB\/CRC1444"]}]},{"name":"Aesculap AG and Deutsche Forschungsgemeinschaft","award":["TR 1657\/1-1"],"award-info":[{"award-number":["TR 1657\/1-1"]}]},{"name":"Aesculap AG and Deutsche Forschungsgemeinschaft","award":["DA 1786\/9-1"],"award-info":[{"award-number":["DA 1786\/9-1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>This study explores the feasibility of estimating tibiofemoral joint contact forces using deep learning models trained on in vivo biomechanical data. Leveraging the comprehensive CAMS-Knee datasets, we developed and evaluated two machine learning network architectures, a bidirectional Long Short-Term-Memory Network with a Multilayer Perceptron (biLSTM-MLP) and a Temporal Convolutional Network (TCN) model, to predict medial and lateral knee contact forces (KCFs) across various activities of daily living. Using a leave-one-subject-out validation approach, the biLSTM-MLP model achieved root mean square errors (RMSEs) as low as 0.16 body weight (BW) and Pearson correlation coefficients up to 0.98 for the total KCF (Ftot) during walking. Although the prediction of individual force components showed slightly lower accuracy, the model consistently demonstrated high predictive accuracy and strong temporal coherence. In contrast to the biLSTM-MLP model, the TCN model showed more variable performance across force components and activities. Leave-one-feature-out analyses underscored the dominant role of lower-limb kinematics and ground reaction forces in driving model accuracy, while EMG features contributed only marginally to the overall predictive performance. Collectively, these findings highlight deep learning as a scalable and reliable alternative to traditional musculoskeletal simulations for personalized knee load estimation, establishing a foundation for future research on larger and more heterogeneous populations.<\/jats:p>","DOI":"10.3390\/bioengineering13020173","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T09:48:08Z","timestamp":1770025688000},"page":"173","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine Learning-Based Estimation of Knee Joint Mechanics from Kinematic and Neuromuscular Inputs: A Proof-of-Concept Using the CAMS-Knee Datasets"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3302-7148","authenticated-orcid":false,"given":"Yara N.","family":"Derungs","sequence":"first","affiliation":[{"name":"Laboratory for Movement Biomechanics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Bertsch","sequence":"additional","affiliation":[{"name":"Laboratory for Movement Biomechanics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kushal","family":"Malla","sequence":"additional","affiliation":[{"name":"Laboratory for Movement Biomechanics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2995-4556","authenticated-orcid":false,"given":"Allan","family":"Maas","sequence":"additional","affiliation":[{"name":"Research & Development, Aesculap AG, Am Aesculap Platz, 78532 Tuttlingen, Germany"},{"name":"Department of Orthopaedic and Trauma Surgery, Musculoskeletal University Center Munich (MUM), Campus Grosshadern, LMU Munich, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1068-7497","authenticated-orcid":false,"given":"Thomas M.","family":"Grupp","sequence":"additional","affiliation":[{"name":"Research & Development, Aesculap AG, Am Aesculap Platz, 78532 Tuttlingen, Germany"},{"name":"Department of Orthopaedic and Trauma Surgery, Musculoskeletal University Center Munich (MUM), Campus Grosshadern, LMU Munich, 81377 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Trepczynski","sequence":"additional","affiliation":[{"name":"Julius Wolff Institute, Berlin Institute of Health at Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, 13353 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8471-7284","authenticated-orcid":false,"given":"Philipp","family":"Damm","sequence":"additional","affiliation":[{"name":"Julius Wolff Institute, Berlin Institute of Health at Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin, 13353 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3518-3316","authenticated-orcid":false,"given":"Seyyed Hamed Hosseini","family":"Nasab","sequence":"additional","affiliation":[{"name":"Laboratory for Movement Biomechanics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.jbiomech.2017.09.022","article-title":"A comprehensive assessment of the musculoskeletal system: The CAMS-Knee data set","volume":"65","author":"Taylor","year":"2017","journal-title":"J. Biomech."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"081004","DOI":"10.1115\/1.4064550","article-title":"Predicting Knee Joint Contact Forces During Normal Walking Using Kinematic Inputs With a Long-Short Term Neural Network","volume":"146","author":"Bennett","year":"2024","journal-title":"J. Biomech. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Valente, G., Grenno, G., Fabbro, G.D., Zaffagnini, S., and Taddei, F. (2023). Medial and lateral knee contact forces during walking, stair ascent and stair descent are more affected by contact locations than tibiofemoral alignment in knee osteoarthritis patients with varus malalignment. Front. Bioeng. Biotechnol., 11.","DOI":"10.3389\/fbioe.2023.1254661"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.gaitpost.2018.12.030","article-title":"Effect of lateral wedged insoles on the knee internal contact forces in medial knee osteoarthritis","volume":"68","author":"Mannisi","year":"2019","journal-title":"Gait Posture"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"S4","DOI":"10.1016\/j.jbiomech.2007.02.014","article-title":"Design, calibration and pre-clinical testing of an instrumented tibial tray","volume":"40","author":"Heinlein","year":"2007","journal-title":"J. Biomech."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Guo, N., Smith, C.R., Sch\u00fctz, P., Trepczynski, A., Moewis, P., Damm, P., Maas, A., Grupp, T.M., Taylor, W.R., and Nasab, S.H.H. (2024). Posterior tibial slope influences joint mechanics and soft tissue loading after total knee arthroplasty. Front. Bioeng. Biotechnol., 12.","DOI":"10.3389\/fbioe.2024.1352794"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"20240588","DOI":"10.1098\/rsif.2024.0588","article-title":"On the consequences of intra-operative release versus over-tensioning of the posterior cruciate ligament in total knee arthroplasty","volume":"21","author":"Nasab","year":"2024","journal-title":"J. R. Soc. Interface"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"110439","DOI":"10.1016\/j.jbiomech.2021.110439","article-title":"Machine learning for rapid estimation of lower extremity muscle and joint loading during activities of daily living","volume":"123","author":"Burton","year":"2021","journal-title":"J. Biomech."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Jung, Y., Phan, C.B., and Koo, S. (2016). Intra-Articular Knee Contact Force Estimation During Walking Using Force-Reaction Elements and Subject-Specific Joint Model. J. Biomech. Eng., 138.","DOI":"10.1115\/1.4032414"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"108016","DOI":"10.1016\/j.compbiomed.2024.108016","article-title":"Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors","volume":"170","author":"Xiang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TNSRE.2022.3156786","article-title":"Lower-Limb Joint Torque Prediction Using LSTM Neural Networks and Transfer Learning","volume":"30","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Mundt, M., Johnson, W.R., Potthast, W., Markert, B., Mian, A., and Alderson, J. (2021). A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units. Sensors, 21.","DOI":"10.3390\/s21134535"},{"key":"ref_13","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/TMRB.2022.3144025","article-title":"Subject-Independent, Biological Hip Moment Estimation During Multimodal Overground Ambulation Using Deep Learning","volume":"4","author":"Molinaro","year":"2022","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3988","DOI":"10.1109\/LRA.2024.3374189","article-title":"A Deep Learning Framework for End-to-End Control of Powered Prostheses","volume":"9","author":"Nuesslein","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"111851","DOI":"10.1016\/j.jbiomech.2023.111851","article-title":"Knee kinematics are primarily determined by implant alignment but knee kinetics are mainly influenced by muscle coordination strategy","volume":"161","author":"Dreyer","year":"2023","journal-title":"J. Biomech."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1016\/j.jbiomech.2011.01.014","article-title":"The effect of valgus braces on medial compartment load of the knee joint\u2014In vivo load measurements in three subjects","volume":"44","author":"Kutzner","year":"2011","journal-title":"J. Biomech."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Mundt, M., Born, Z., Goldacre, M., and Alderson, J. (2022). Estimating Ground Reaction Forces from Two-Dimensional Pose Data: A Biomechanics-Based Comparison of AlphaPose, BlazePose, and OpenPose. Sensors, 23.","DOI":"10.3390\/s23010078"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Nasab, S.H.H., Smith, C., Sch\u00fctz, P., Postolka, B., Ferguson, S., Taylor, W.R., and List, R. (2020). Elongation Patterns of the Posterior Cruciate Ligament after Total Knee Arthroplasty. J. Clin. Med., 9.","DOI":"10.3390\/jcm9072078"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1007\/s11517-023-03011-w","article-title":"Prediction of medial knee contact force using multisource fusion recurrent neural network and transfer learning","volume":"62","author":"Zou","year":"2024","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liew, B.X.W., R\u00fcgamer, D., Mei, Q., Altai, Z., Zhu, X., Zhai, X., and Cortes, N. (2023). Smooth and accurate predictions of joint contact force time-series in gait using over parameterised deep neural networks. Front. Bioeng. Biotechnol., 11.","DOI":"10.3389\/fbioe.2023.1208711"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"11004","DOI":"10.1038\/s41598-024-60387-x","article-title":"Employing machine learning for enhanced abdominal fat prediction in cavitation post-treatment","volume":"14","author":"Hady","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_23","unstructured":"Strike.money (2025, June 19). Time Series Analysis in Technical Trading. Available online: https:\/\/www.strike.money\/technical-analysis\/time-series-analysis."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, G., Shourijeh, M.S., Ao, D., Patten, C., and Fregly, B.J. (2021). How Well Do Commonly Used Co-contraction Indices Approximate Lower Limb Joint Stiffness Trends During Gait for Individuals Post-stroke?. Front. Bioeng. Biotechnol., 8.","DOI":"10.3389\/fbioe.2020.588908"},{"key":"ref_25","first-page":"35","article-title":"Current Evidence of Gait Modification with Real-time Biofeedback to Alter Kinetic, Temporospatial, and Function-Related Outcomes: A Review","volume":"5","author":"Eddo","year":"2017","journal-title":"Int. J. Kinesiol. Sport. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s11517-014-1233-z","article-title":"Real-time visual feedback for gait retraining: Toward application in knee osteoarthritis","volume":"53","author":"Steenbrink","year":"2015","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1109\/TNSRE.2020.3003559","article-title":"The Uncontrolled Manifold Theory Could Explain Part of the Inter-Trial Variability of Knee Contact Force During Level Walking","volume":"28","author":"Mazza","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"do Nascimento, T.C.F., Gerv\u00e1sio, F.M., Pignolo, A., Bueno, G.A.S., do Carmo, A.A., Ribeiro, D.M., D\u2019Amelio, M., and dos Santos Mendes, F.A. (2021). Assessment of the Kinematic Adaptations in Parkinson\u2019s Disease Using the Gait Profile Score: Influences of Trunk Posture, a Pilot Study. Brain Sci., 11.","DOI":"10.3390\/brainsci11121605"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Xu, P., Yu, H., Wang, X., and Song, R. (2022). Characterizing stroke-induced changes in the variability of lower limb kinematics using multifractal detrended fluctuation analysis. Front. Neurol., 13.","DOI":"10.3389\/fneur.2022.893999"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Moon, H.S., Liao, Y.C., Li, C., Lee, B., and Oulasvirta, A. (2024). Real-time 3D Target Inference via Biomechanical Simulation. Proceedings of the CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA, 11\u201316 May 2025, ACM.","DOI":"10.1145\/3613904.3642131"},{"key":"ref_31","first-page":"1582361","article-title":"Synergy of physics-based reasoning and machine learning in biomedical applications: Towards unlimited deep learning with limited data","volume":"4","author":"Gavrishchaka","year":"2019","journal-title":"Adv. Phys. X"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"199903","DOI":"10.1109\/ACCESS.2025.3635541","article-title":"The Impact of Feature Scaling in Machine Learning: Effects on Regression and Classification Tasks","volume":"13","author":"Pinheiro","year":"2025","journal-title":"IEEE Access"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/2\/173\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T12:30:07Z","timestamp":1770035407000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/2\/173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["bioengineering13020173"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13020173","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,31]]}}}