Abstract
Joint torques of lower extremity are important clinical indicators of gait capability. This parameter can be quantified via hybrid neuromusculoskeletal modelling that combines electromyography-driven modelling and static optimisation. The simulations rely on kinematics and external force measurements, for example, ground reaction forces (GRF) and the corresponding centres of pressure (COP), which are conventionally acquired using force plates. This bulky equipment, however, hinders gait analysis in real-world environments. While this portability issue could potentially be solved by estimating the parameters through machine learning, the effect of the estimation errors on joint torque prediction with biomechanical models remains to be investigated. This study first estimated GRF and COP through feedforward artificial neural networks, and then leveraged them to predict lower-limb sagittal joint torques via (i) inverse dynamics and (ii) hybrid modelling. The approach was evaluated on five healthy subjects, individually. The predicted torques were validated with the measured torques, showing that hip was the most sensitive whereas ankle was the most resistive to the GRF/COP estimates for both models, with average metrics values being 0.70 < < 0.97 and 0.069 < RMSE < 0.15 (Nm/kg). This study demonstrated the feasibility of torque prediction based on personalised (neuro)musculoskeletal modelling using statistical ground reaction estimates, thus providing insights into potential real-world mobile joint torque quantification.
Highlights
Three-dimensional gait analysis aimed at quantifying joint and musculotendon kinetics is crucial for certain medical diagnosis, motor assessment and development of rehabilitative technologies [1,2,3]
The motivation behind this effort comes from a desire to allow subject-specific high-fidelity model-based gait analysis to take place outside the laboratory
We applied machine learning algorithms to estimate ground reaction forces (GRF) and centres of pressure (COP), which were used to compute the torques via inverse dynamics and hybrid neuromusculoskeletal modelling
Summary
Three-dimensional gait analysis aimed at quantifying joint and musculotendon kinetics is crucial for certain medical diagnosis, motor assessment and development of rehabilitative technologies [1,2,3]. Estimating joint moments through inverse dynamics modelling in gait anaylsis is regarded as the gold standard [4,5] Optimisation methods require definition of an objective function describing muscle recruitment strategies, which has remained a challenging endeavour To this end, electromyography (EMG) observations are introduced to drive the model and estimate these kinetic parameters [11,12,13,14,15]. In light of the limitations of both optimisation and EMG-driven methods, a hybrid model has been proposed to balance the uncertainties induced by the two approaches [23] This model compares the joint torques predicted by an EMG-driven model and inverse dynamics, and minimises the torque differences by minimally fine-tuning the EMG signals and generating the excitations that have not been recorded
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
