A machine learning approach to quantify individual gait responses to ankle exoskeletons

Megan R Ebers; Michael C Rosenberg; J Nathan Kutz; Katherine M Steele

doi:10.1016/j.jbiomech.2023.111695

A machine learning approach to quantify individual gait responses to ankle exoskeletons

J Biomech. 2023 Aug:157:111695. doi: 10.1016/j.jbiomech.2023.111695. Epub 2023 Jun 24.

Authors

Megan R Ebers¹, Michael C Rosenberg², J Nathan Kutz³, Katherine M Steele⁴

Affiliations

¹ Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA. Electronic address: mebers@uw.edu.
² Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, 30322, USA.
³ Department of Applied Mathematics, University of Washington, Seattle, WA, 98195, USA.
⁴ Department of Mechanical Engineering, University of Washington, Seattle, WA, 98195, USA.

PMID: 37406604
DOI: 10.1016/j.jbiomech.2023.111695

Abstract

Predicting an individual's response to an exoskeleton and understanding what data are needed to characterize responses remains challenging. Specifically, we lack a theoretical framework capable of quantifying heterogeneous responses to exoskeleton interventions. We leverage a neural network-based discrepancy modeling framework to quantify complex changes in gait in response to passive ankle exoskeletons in nondisabled adults. Discrepancy modeling aims to resolve dynamical inconsistencies between model predictions and real-world measurements. Neural networks identified models of (i) Nominal gait, (ii) Exoskeleton (Exo) gait, and (iii) the Discrepancy (i.e., response) between them. If an Augmented (Nominal+Discrepancy) model captured exoskeleton responses, its predictions should account for comparable amounts of variance in Exo gait data as the Exo model. Discrepancy modeling successfully quantified individuals' exoskeleton responses without requiring knowledge about physiological structure or motor control: a model of Nominal gait augmented with a Discrepancy model of response accounted for significantly more variance in Exo gait (median R² for kinematics (0.928-0.963) and electromyography (0.665-0.788), (p<0.042)) than the Nominal model (median R² for kinematics (0.863-0.939) and electromyography (0.516-0.664)). However, additional measurement modalities and/or improved resolution are needed to characterize Exo gait, as the discrepancy may not comprehensively capture response due to unexplained variance in Exo gait (median R² for kinematics (0.954-0.977) and electromyography (0.724-0.815)). These techniques can be used to accelerate the discovery of individual-specific mechanisms driving exoskeleton responses, thus enabling personalized rehabilitation.

Keywords: Ankle exoskeleton; Discrepancy modeling; Gait; Machine learning; Prediction.