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

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 di...

Full description

Saved in:
Bibliographic Details
Published in:Journal of biomechanics 2023-08, Vol.157, p.111695-111695, Article 111695
Main Authors: Ebers, Megan R., Rosenberg, Michael C., Kutz, J. Nathan, Steele, Katherine M.
Format: Article
Language:English
Subjects:
Ankle
Ankle exoskeleton
Discrepancy modeling
Electromyography
Exoskeleton
Exoskeletons
Gait
Kinematics
Machine learning
Modelling
Motor task performance
Neural networks
Prediction
Rehabilitation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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
ISSN:0021-9290
1873-2380
DOI:10.1016/j.jbiomech.2023.111695