Sagittal Reaction Moments During Gait using Kinematic Inputs: A Deep Learning Approach
- 27 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 145-149
Abstract
Accurate estimation of joint reaction moments (JRMs) and ground reaction moments (GRMs) during gait is critical for diagnosing musculoskeletal disorders but remains constrained by lab-dependent methods requiring force plates or full-body kinematics. This study introduces a novel deep learning framework to predict sagittal plane JRMs and GRMs using only single-marker positional data (hip, knee, ankle), eliminating the need for complex instrumentation. Leveraging sequence-to-sequence models (GRU, LSTM, 1D-CNN) optimized via Bayesian hyperparameter tuning and Leave-One-Subject-Out (LOSO) cross-validation, we analyzed gait data from 80 asymptomatic adults. Models achieved RMSE values of $31.1-50.1 \text{Nmm} / \text{kg}$ across joints, with normalized RMSE (nRMSE) between $\mathbf{1 6} \boldsymbol{-} \mathbf{2 1 {\%}}$, comparable to prior studies using more extensive inputs. GRU excelled at ankle moment prediction $(31.1 \pm 25.8$ vs. $38.6 \pm 30.0$ Nmm/kg, left/right), while LSTM showed robustness for knee moments $(35.0 \pm 25.6$ vs. $37.2 \pm 30.1 \text{Nmm} / \text{kg})$. Asymmetries in hip RMSE $(48.7 \pm 25.7 \mathrm{L}$ vs. $42.4 \pm 23.4 \mathrm{R})$ highlighted joint-specific variability. The framework's minimal kinematic requirements reduce computational burden, offering a scalable alternative to traditional gait analysis. Despite strong performance in asymptomatic individuals, validation in pathological populations and integration with Markerless systems are needed for clinical translation. This work advances accessible, lab-free biomechanical assessment, demonstrating the potential of deep learning to bridge gaps between research and clinical practice.
Keywords
This publication has 14 references indexed in Scilit:
- Ground Reaction Forces and Moments in Stroke Survivors: Experimental versus AnyBody Model PredictionsAnnual International Conference of the IEEE Engineering in Medicine and Biology Society, 2024
- BlazePose-Seq2Seq: Leveraging Regular RGB Cameras for Robust Gait AssessmentIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024
- Gait analysis dataset of healthy volunteers and patients before and 6 months after total hip arthroplastyScientific Data, 2022
- Sagittal plane ankle kinetics are associated with dynamic hip range of motion and gait efficiency in women with hip osteoarthritisJournal of Orthopaedic Research, 2022
- Weakly-Supervised Learning of Human Dynamics2020
- Generating Individual Gait Kinetic Patterns Using Machine Learning2020
- Motion Generation of a Wearable Hip Exoskeleton Robot Using Machine Learning-Based Estimation of Ground Reaction Forces and Moments2019
- Joint Loading in the Sagittal Plane During Gait Is Associated With Hip Joint Abnormalities in Patients With Femoroacetabular ImpingementThe American Journal of Sports Medicine, 2016
- Estimation of ground reaction forces and ankle moment with multiple, low-cost sensorsJournal of NeuroEngineering and Rehabilitation, 2015
- Design of patient-specific gait modifications for knee osteoarthritis rehabilitationIEEE Transactions on Biomedical Engineering, 2007