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

We currently lack a theoretical framework capable of characterizing heterogeneous responses to exoskeleton interventions. Predicting an individual's response to an exoskeleton and understanding what data are needed to characterize responses has been a persistent challenge. In this study, 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) gait, (ii) ( ) gait, and (iii) the ( , response) between them. If an (Nominal+Discrepancy) model captured exoskeleton responses, its predictions should account for comparable amounts of variance in gait data as the model. Discrepancy modeling successfully quantified individuals' exoskeleton responses without requiring knowledge about physiological structure or motor control: a model of gait augmented with a model of response accounted for significantly more variance in gait (median for kinematics (0.928 - 0.963) and electromyography (0.665 - 0.788), ( < 0.042)) than the model (median for kinematics (0.863 - 0.939) and electromyography (0.516 - 0.664)). However, additional measurement modalities and/or improved resolution are needed to characterize gait, as the discrepancy may not comprehensively capture response due to unexplained variance in gait (median 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.