Ground Reaction Forces and Joint Moments Predict Metabolic Cost in Physical Performance: Harnessing the Power of Artificial Neural Networks
Source abstract
Abstract
Understanding metabolic cost through biomechanical data, including ground reaction forces (GRFs) and joint moments, is vital for health, sports, and rehabilitation. The long stabilization time (2–5 min) of indirect calorimetry poses challenges in prolonged tests. This study investigated using artificial neural networks (ANNs) to predict metabolic costs from the GRF and joint moment time series. Data from 20 participants collected over 270 walking trials, including the GRF and joint moments, formed a detailed dataset. Two ANN models were crafted, netGRF for the GRF and netMoment for joint moments, and both underwent training, validation, and testing to validate their predictive accuracy for metabolic cost. NetGRF (six hidden layers, two input delays) showed significant correlations: 0.963 (training), 0.927 (validation), 0.883 (testing), p < 0.001. NetMoment (three hidden layers, one input delay) had correlations of 0.920 (training), 0.956 (validation), 0.874 (testing), p < 0.001. The models’ low mean squared errors reflect their precision. Using Partial Dependence Plots, we demonstrated how gait cycle phases affect metabolic cost predictions, pinpointing key phases. Our findings show that the GRF and joint moments data can accurately predict metabolic costs via ANN models, with netGRF being notably consistent. This emphasizes ANNs’ role in biomechanics as a crucial method for estimating metabolic costs, impacting sports science, rehabilitation, assistive technology development, and fostering personalized advancements.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sports Performance and Training · Lower Extremity Biomechanics and Pathologies · Muscle activation and electromyography studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Biomechanics and Center for Research in Human Movement Variability, University of Nebraska at Omaha, Omaha, NE 68182, USA
Institute for Rehabilitation Science and Engineering, Madonna Rehabilitation Hospitals, Lincoln, NE 68506, USA
Department of Neurology, Oregon Health & Science University, Portland, OR 97239, USA
Department of Surgery, University of Nebraska Medical Center, Omaha, NE 68105, USA
Department of Surgery and Research Service, Nebraska-Western Iowa Veterans Affairs Medical Center, Omaha, NE 68105, USA
Funding
National Institutes of Health · U.S. Department of Veterans Affairs Rehabilitation Research and Development Service
References (34)
Show source-provided references
1. A Simple Model of Mechanical Effects to Estimate Metabolic Cost of Human Walking10.1038/s41598-018-29429-z ↗
2. Estimating Instantaneous Energetic Cost during Non-Steady-State Gait10.1152/japplphysiol.00445.2014 ↗
3. Zhu, Y., Xia, D., and Zhang, H. (2023). Using Wearable Sensors to Estimate Vertical Ground Reaction Force Based on a Transformer. Appl. Sci., 13.10.3390/app13042136 ↗
4. Karatsidis, A., Bellusci, G., Schepers, H., de Zee, M., Andersen, M., and Veltink, P. (2016). Estimation of Ground Reaction Forces and Moments During Gait Using Only Inertial Motion Capture. Sensors, 17.10.3390/s17010075 ↗
5. Mohammadzadeh Gonabadi, A., Antonellis, P., and Malcolm, P. (2020). Differences between Joint-Space and Musculoskeletal Estimations of Metabolic Rate Time Profiles. PLoS Comput. Biol., 16.10.1371/journal.pcbi.1008280 ↗
6. Arones, M.M., Shourijeh, M.S., Patten, C., and Fregly, B.J. (2020). Musculoskeletal Model Personalization Affects Metabolic Cost Estimates for Walking. Front. Bioeng. Biotechnol., 8.10.3389/fbioe.2020.588925 ↗
7. Joo, H., Kim, D.R.D., Kim, J.H., and Roberts, D. (2015). A Joint-Space Numerical Model of Metabolic Energy Expenditure for Human Multibody Dynamic System. Int. J. Numer. Methods Biomed. Eng., 31.10.1002/cnm.2721 ↗
8. Stance and Swing Phase Costs in Human Walking10.1098/rsif.2010.0084 ↗
9. A Model of Human Muscle Energy Expenditure10.1080/1025584031000091678 ↗
10. Metabolic Perceptrons for Neural Computing in Biological Systems10.1038/s41467-019-11889-0 ↗
11. Forecasting the Cost of Water Using a Neural Network Method in the Municipality of Isfahan
12. Comparison of Forecasting the Cost of Water Using Statistical and Neural Network Methods: Case Study of Isfahan Municipality
13. Mohammadzadeh, G., Arash, F., Farahnaz, P., Iraklis, I., and Myers, S.A. (Gait Posture, 2024). Predicting Lower Body Joint Moments and Electromyography Signals Using Ground Reaction Forces During Walking and Running: An Artificial Neural Network Approach, Gait Posture, under revision.
14. Koelewijn, A.D., Heinrich, D., and van den Bogert, A.J. (2019). Metabolic Cost Calculations of Gait Using Musculoskeletal Energy Models, a Comparison Study. PLoS ONE, 14.10.1101/588590 ↗
15. Mandrikova, O., Polozov, Y., Zhukova, N., and Shichkina, Y. (2022). Approximation and Analysis of Natural Data Based on NARX Neural Networks Involving Wavelet Filtering. Mathematics, 10.10.3390/math10224345 ↗
16. (2016, October 01). Design Time Series NARX Feedback Neural Networks. Available online: https://www.mathworks.com/help/deeplearning/ug/design-time-series-narx-feedback-neural-networks.html.
17. Machine Learning in Human Movement Biomechanics: Best Practices, Common Pitfalls, and New Opportunities10.1016/j.jbiomech.2018.09.009 ↗
18. Li, X., Liu, X., Deng, X., and Fan, Y. (2022). Interplay between Artificial Intelligence and Biomechanics Modeling in the Cardiovascular Disease Prediction. Biomedicines, 10.10.3390/biomedicines10092157 ↗
19. Editorial: Artificial Intelligence to Enhance Biomechanical Modelling10.3389/fspor.2023.1188035 ↗
20. Diagnosis of Disease Affecting Gait with a Body Acceleration-Based Model Using Reflected Marker Data for Training and a Wearable Accelerometer for Implementation10.1038/s41598-023-50727-8 ↗
21. Modular Footwear That Partially Offsets Downhill or Uphill Grades Minimizes the Metabolic Cost of Human Walking10.1098/rsos.191527 ↗
22. Mohammadzadeh Gonabadi, A., Antonellis, P., Dzewaltowski, A.C., Myers, S.A., Pipinos, I.I., and Malcolm, P. (2024). Design and Evaluation of a Bilateral Semi-Rigid Exoskeleton to Assist Hip Motion. Biomimetics, 9.10.3390/biomimetics9040211 ↗
23. Derivation of Formulae Used to Calculate Energy Expenditure in Man
24. Oriented Principal Component Analysis for Large Margin Classifiers10.1016/S0893-6080(01)00106-X ↗
25. A Novel Nested Loop Optimization Problem Based on Deep Neural Networks and Feasible Operation Regions Definition for Simultaneous Material Screening and Process Optimization10.1016/j.cherd.2022.02.013 ↗
26. Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning, Springer.10.1007/978-0-387-84858-7 ↗
27. Greedy Function Approximation: A Gradient Boosting Machine10.1214/aos/1013203451 ↗
28. Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation10.1080/10618600.2014.907095 ↗
29. Bishop, C.M., and Nasrabadi, N.M. (2006). Pattern Recognition and Machine Learning, Springer.
30. Powers, D.M.W. (2020). Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. arXiv.
31. A Survey of Cross-Validation Procedures for Model Selection10.1214/09-SS054 ↗
32. Mechanical Work for Step-to-Step Transitions Is a Major Determinant of the Metabolic Cost of Human Walking10.1242/jeb.205.23.3717 ↗
33. Understanding Muscle Energetics in Locomotion: New Modeling and Experimental Approaches10.1097/JES.0b013e31820d7bc5 ↗
34. Partitioning the Energetics of Walking and Running: Swinging the Limbs Is Expensive10.1126/science.1090704 ↗