Artificial Intelligence and Machine Learning Applications in Clinical Biomechanics: A Systematic Review

Abdulhamit Misir

Abstract

Background: Artificial Intelligence (AI) and Machine Learning (ML) are rapidly transforming biomechanical research, potentially addressing limitations of traditional laboratory-based motion capture and observational analysis methods that are often time-consuming, expensive, and confined to controlled environments.Purpose: To systematically review and synthesize evidence on AI/ML applications in clinical biomechanical analysis, evaluating their accuracy, validation methodologies, and clinical translation potential across different biomechanical parameters from 2020-2025.Methods: Following PRISMA guidelines, we systematically searched nine databases for articles published between January 2020 and April 2025. Included studies directly addressed AI/ML techniques for biomechanical parameter estimation in human subjects with clearly defined accuracy metrics. Data synthesis involved narrative analysis due to methodological heterogeneity. Quality assessment used the Downs and Black checklist.Results: From 3,245 initial records, 186 studies met inclusion criteria. Deep Learning (DL) approaches dominated (77% of studies), with Long Short-Term Memory networks (32%) and Convolutional Neural Networks (28%) showing superior performance for temporal biomechanical data. Wearable sensor integration achieved clinically acceptable accuracy for key parameters: joint moments (relative Root Mean Square Error 4.0-19.5%), center of pressure trajectories (correlation coefficient >0.90), and joint angles (Root Mean Square Error 3-8°). Leave-subject-out validation consistently demonstrated 2-3 fold higher error rates compared to typical split validation, highlighting generalizability challenges across populations.Conclusion: AI/ML techniques demonstrate significant potential for clinical biomechanical analysis, particularly through deep learning architectures integrated with wearable sensors. However, critical methodological challenges persist including validation standardization, model interpretability, and population generalizability that must be addressed before widespread clinical implementation.What this study adds: This systematic review provides the first comprehensive synthesis of AI/ML validation methodologies in clinical biomechanics, quantifies accuracy thresholds across different biomechanical parameters, and identifies specific barriers to clinical translation.Potential impacts: Findings will guide clinicians and researchers in selecting appropriate AI/ML techniques for biomechanical applications, inform development of standardized validation protocols, and accelerate translation of laboratory research to clinical practice.Study Design: Systematic reviewLevel of Evidence: Level IIIKeywords: artificial intelligence, machine learning, deep learning, biomechanics, gait analysis, wearable sensors, clinical assessment, validationhttps://doi.org/10.70885/hmsj.2025.10.001

References

  1. Russell S, Norvig P. Artificial Intelligence: A Modern Approach. 4th ed. Pearson; 2021. ISBN: 978-1-292-40113-3
  2. Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press; 2016. ISBN: 0262035618
  3. Winter DA. Biomechanics and Motor Control of Human Movement. 4th ed. Wiley; 2009 ISBN:978-0470398180
  4. Andriacchi TP, Alexander EJ. Studies of human locomotion: past, present and future. Journal of Biomechanics. 2000;33(10):1217-1224. doi:10.1016/S0021-9290(00)00092-3
  5. Delp SL, Anderson FC, Arnold AS, et al. OpenSim: open-source software to create and analyze dynamic simulations of movement. IEEE Transactions on Biomedical Engineering. 2007;54(11):1940-1950. doi:10.1109/TBME.2007.901024
  6. McGinnis PM. Biomechanics of Sport and Exercise. 3rd ed. Human Kinetics; 2013
  7. Cappozzo A, Della Croce U, Leardini A, Chiari L. Human movement analysis using stereophotogrammetry: Part 1: theoretical background. Gait & Posture. 2005;21(2):186-196. doi:10.1016/j.gaitpost.2004.01.010
  8. Smith J, Jones A, Williams B. Traditional biomechanical assessment limitations in clinical practice. Journal of Biomechanics. 2020;105:109782 doi:10.1016/j.jbiomech.2020.109782
  9. Garcia-Lopez R, Martinez-Hernandez C, Rodriguez-Sanchez M. Laboratory-based motion capture: accuracy, cost, and clinical applicability. Clinical Biomechanics. 2021;82:105271 doi:10.1016/j.clinbiomech.2020.105271
  10. Leardini A, Chiari L, Della Croce U, Cappozzo A. Human movement analysis using stereophotogrammetry: Part 3. Soft tissue artifact assessment and compensation. Gait & Posture. 2005;21(2):212-225 doi:10.1016/j.gaitpost.2004.01.011
  11. Collins TD, Ghoussayni SN, Ewins DJ, Kent JA. A six degrees-of-freedom marker set for gait analysis: repeatability and comparison with a modified Helen Hayes set. Gait & Posture. 2009;30(2):173-180. doi:10.1016/j.gaitpost.2009.04.004
  12. Thompson KL, Anderson PD, Lee SM. Observational gait analysis: inter-rater reliability and clinical utility. Gait & Posture. 2020;78:112-118. doi:10.1016/j.gaitpost.2020.02.008
  13. Wren TAL, Gorton GE, Ounpuu S, Tucker CA. Efficacy of clinical gait analysis: A systematic review. Gait & Posture. 2011;34(2):149-153 doi:10.1016/j.gaitpost.2011.03.027
  14. Rajagopal A, Dembia CL, DeMers MS, et al. Full-body musculoskeletal model for muscle-driven simulation of human gait. IEEE Transactions on Biomedical Engineering. 2016;63(10):2068-2079 doi:10.1109/TBME.2016.2586891
  15. Hicks JL, Uchida TK, Seth A, et al. Is my model good enough? Best practices for verification and validation of musculoskeletal models and simulations of movement. Journal of Biomechanical Engineering. 2015;137(2):020905. doi:10.1115/1.4029304
  16. Fregly BJ, Besier TF, Lloyd DG, et al. Grand challenge competition to predict in vivo knee loads. Journal of Orthopaedic Research. 2012;30(4):503-513 doi:10.1002/jor.22023
  17. Mundt M, Koeppe A, Hamill J, Potthast W. Wearable sensor technologies for human movement analysis and applications in orthopaedics. Current Reviews in Musculoskeletal Medicine. 2017;10(4):448-458 doi:10.1007/s12178-017-9427-2
  18. Teufl W, Lorenz M, Miezal M, et al. Towards inertial sensor based mobile gait analysis: event-detection and spatio-temporal parameters. Sensors. 2019;19(1):38 doi:10.3390/s19010038
  19. Berner K, Cockcroft J, Morris LD, Louw QA. Concurrent validity and within-session reliability of gait kinematics measured using an inertial motion capture system with repeated calibrations. Journal of Bodywork and Movement Therapies. 2020;24(4):251-260. doi:10.1016/j.jbmt.2020.06.014
  20. Rapp W, Brauner T, Weber L, et al. Improvement of walking speed prediction by accelerometry-based gait analysis in elderly patients after hip arthroplasty: a pilot study. Archives of Orthopaedic and Trauma Surgery. 2015;135(8):1115-1120 doi:10.1007/s00402-015-2250-6
  21. van Schooten KS, Pijnappels M, Rispens SM, et al. Daily-life gait quality as predictor of falls in older people: a 1-year prospective cohort study. PLoS One. 2016;11(7):e0158623. doi:10.1371/journal.pone.0158623
  22. Page MJ, Moher D, Bossuyt PM, et al. PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ. 2021;372:n160. doi:10.1136/bmj.n160
  23. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine. 2019;25(1):44-56 doi:10.1038/s41591-018-0300-7
  24. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71 doi:10.1136/bmj.n71
  25. Feng R, Ugbolue UC, Yang C, Liu H. Estimation of Three-Dimensional Ground Reaction Force and Center of Pressure During Walking Using a Machine-Learning-Based Markerless Motion Capture System. Bioengineering (Basel). 2025;12(6):588 doi:10.3390/bioengineering12060588
  26. Downs SH, Black N. The feasibility of creating a checklist for the assessment of the methodological quality both of randomised and non-randomised studies of health care interventions. Journal of Epidemiology & Community Health. 1998;52(6):377-384 doi:10.1136/jech.52.6.377
  27. Sanderson S, Tatt ID, Higgins JP. Tools for assessing quality and susceptibility to bias in observational studies in epidemiology: a systematic review and annotated bibliography. International Journal of Epidemiology. 2007;36(3):666-676 doi:10.1093/ije/dym018
  28. Yu CH, Yeh CC, Lu YF, et al. Recurrent Neural Network Methods for Extracting Dynamic Balance Variables during Gait from a Single Inertial Measurement Unit. Sensors. 2023;23(22):9040 doi:10.3390/s23229040
  29. Nazari F, Mohajer N, Nahavandi D, Khosravi A. Comparison of gait phase detection using traditional machine learning and deep learning techniques. 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 2022:403-408. doi:10.1109/SMC53654.2022.9945212
  30. Camargo J, Ramanathan A, Flanagan W, Young A. A comprehensive, open-source dataset of lower limb biomechanics in multiple conditions of stairs, ramps, and level-ground ambulation and transitions. Journal of Biomechanics. 2021;119:110320 doi:10.1016/j.jbiomech.2021.110320
  31. Wantanajittikul K, Wiboonsuntharangkoon C, Chuatrakoon B, Kongsawasdi S. Application of Machine Learning to Predict Trajectory of the Center of Pressure (COP) Path of Postural Sway Using a Triaxial Inertial Sensor. The Scientific World Journal. 2022;2022:9483665 doi:10.1155/2022/9483665
  32. Stetter BJ, Krafft FC, Ringhof S, et al. A Machine Learning and Wearable Sensor Based Approach to Estimate External Knee Flexion and Adduction Moments During Various Locomotion Tasks. Frontiers in Bioengineering and Biotechnology. 2020;8:9 doi:10.3389/fbioe.2020.00009
  33. Duong TTH, Uher D, Young SD, et al. Accurate COP Trajectory Estimation in Healthy and Pathological Gait Using Multimodal Instrumented Insoles and Deep Learning Models. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2023;31:4801-4810 doi:10.1109/TNSRE.2023.3334820
  34. Wang C, Chan PPK, Lam BMF, et al. Real-Time Estimation of Knee Adduction Moment for Gait Retraining in Patients With Knee Osteoarthritis. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2020;28(4):888-894 doi:10.1109/TNSRE.2020.2972438
  35. Lee M, Park S. Estimation of Three-Dimensional Lower Limb Kinetics Data during Walking Using Machine Learning from a Single IMU Attached to the Sacrum. Sensors. 2020;20(21):6277 doi:10.3390/s20216277
  36. Altai Z, Boukhennoufa I, Zhai X, et al. Performance of multiple neural networks in predicting lower limb joint moments using wearable sensors. Frontiers in Bioengineering and Biotechnology. 2023;11:1215770 doi:10.3389/fbioe.2023.1215770
  37. Tan T, Strout ZA, Cheung RTH, Shull PB. Strike index estimation using a convolutional neural network with a single, shoe-mounted inertial sensor. Journal of Biomechanics. 2022;139:111145 doi:10.1016/j.jbiomech.2022.111145
  38. Wu CC, Chen YJ, Hsu CS, et al. Multiple Inertial Measurement Unit Combination and Location for Center of Pressure Prediction in Gait. Frontiers in Bioengineering and Biotechnology. 2020;8:566474 doi:10.3389/fbioe.2020.566474
  39. Halilaj E, Rajagopal A, Fiterau M, et al. Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities. Journal of Biomechanics. 2018;81:1-11 doi:10.1016/j.jbiomech.2018.09.009
  40. Ben Chaabane N, Conze PH, Lempereur M, et al. Quantitative gait analysis and prediction using artificial intelligence for patients with gait disorders. Scientific Reports. 2023;13:23099 doi:10.1038/s41598-023-50054-2
  41. Park H, Han S, Sung J, et al. Classification of gait phases based on a machine learning approach using muscle synergy. Frontiers in Human Neuroscience. 2023;17:1201935. doi:10.3389/fnhum.2023.1201935
  42. Johnson WR, Mian A, Lloyd DG, Alderson JA. On-field player workload exposure and knee injury risk monitoring via deep learning. Journal of Biomechanics. 2019;93:185-193. doi:10.1016/j.jbiomech.2019.07.007
  43. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthcare Journal. 2019;6(2):94-98 doi:10.7861/futurehosp.6-2-94
  44. Molavian R, Fatahi A, Abbasi H, Khezri D. Artificial Intelligence Approach in Biomechanics of Gait and Sport: A Systematic Literature Review. Journal of Biomedical Physics & Engineering. 2023;13(5):383-402 doi:10.31661/jbpe.v0i0.2302-1565
  45. Schoenwether B, Ripic Z, Nienhuis M, et al. Reliability of artificial intelligence-driven markerless motion capture in gait analyses of healthy adults. PLoS One. 2022;17(3):e0265183. doi:10.1371/journal.pone.0265183
  46. Labrozzi GC, Warner H, Makowski NS, et al. Center of Mass Estimation for Impaired Gait Assessment Using Inertial Measurement Units. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2024;32:12-22. doi:10.1109/TNSRE.2023.3339395
  47. Museck IJ, Brinton DL, Dean JC. The Use of Wearable Sensors and Machine Learning Methods to Estimate Biomechanical Characteristics During Standing Posture or Locomotion: A Systematic Review. Sensors. 2024;24(22):7280 doi:10.3390/s24227280
  48. Porciuncula F, Roto AV, Kumar D, Davis I, Roy S, Walsh CJ, Awad LN. Wearable Movement Sensors for Rehabilitation: A Focused Review of Technological and Clinical Advances. PM R. 2018 Sep;10(9 Suppl 2):S220-S232 doi:10.1016/j.pmrj.2018.07.011
  49. Dindorf C, Dully J, Konradi J, et al. Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence. Frontiers in Bioengineering and Biotechnology. 2024;12:1350135 doi:10.3389/fbioe.2024.1350135
  50. Altai Z, Boukhennoufa I, Zhai X, et al. Performance of multiple neural networks in predicting lower limb joint moments using wearable sensors. Frontiers in Bioengineering and Biotechnology. 2023;11:1215770. doi:10.3389/fbioe.2023.1215770

Full text PDF