Factors influencing neuromuscular responses to gait training with a robotic ankle exoskeleton in cerebral palsy

ABSTRACT

A current limitation in the development of robotic gait training interventions is understanding the factors that predict responses to treatment. The purpose of this study was to explore the application of an interpretable machine learning method, Bayesian Additive Regression Trees (BART), to identify factors influencing neuromuscular responses to a resistive ankle exoskeleton in individuals with cerebral palsy (CP). Eight individuals with CP (GMFCS levels I – III, ages 12–18 years) walked with a resistive ankle exoskeleton over seven visits while we measured soleus activation. A BART model was developed using a predictor set of kinematic, device, study, and participant metrics that were hypothesized to influence soleus activation. The model (R² = 0.94) found that kinematics had the largest influence on soleus activation, but the magnitude of exoskeleton resistance, amount of gait training practice with the device, and participant-level parameters also had substantial effects. To optimize neuromuscular engagement during exoskeleton training in individuals with CP, our analysis highlights the importance of monitoring the user’s kinematic response, in particular, peak stance phase hip flexion and ankle dorsiflexion. We demonstrate the utility of machine learning techniques for enhancing our understanding of robotic gait training outcomes, seeking to improve the efficacy of future interventions.

KEYWORDS:

• Bayesian additive regression tree
• cerebral palsy
• device engagement
• exoskeleton
• neurorehabilitation

Acknowledgments

The authors would like to thank Michael Schwartz for his assistance with data analysis methodology, as well as Greg Orekhov, Leah Liebelt, and Samuel Maxwell for their assistance with device manufacturing. The authors would also like to thank the participants and their families for their involvement in the study.

Disclosure statement

ZFL is a co-founder with shareholder interest of a university start-up company seeking to commercialize the device used in this study. He also holds intellectual property inventorship rights. The other authors have no conflicts of interest to declare.

Author contributions

All authors conceived and contributed to the design of the study. B.C. and A.S. performed the study and data collection, and prepared figures. B.C., A.S., K.S., and Z.L. analyzed the data and wrote the manuscript. All authors revised the manuscript.

Consent to publish

All authors have contributed to this study and are in agreement with the content of the manuscript.

Declarations and ethics statements

The protocol used in this study was approved by the Northern Arizona University Institutional Review Board (# 986,744), and all participants or guardians provided written consent to participate.

Data availability statement

The data collected and analyzed in this study are available from the corresponding author upon reasonable request.

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/10400435.2022.2121324

Additional information

Funding

This research was supported in part by the National Science Foundation under award number [2045966], the Eunice Kennedy Shriver National Institute of Child Health & Human Development of the National Institutes of Health under award number [F30HD103318], the National Institute of Neurological Disorders and Stroke under award number [R01NS091056], and the NSF Graduate Research Fellowship Program, DGE under award number [1762114]. The content is solely the responsibility of the authors and does not necessarily represent the official views of any of the aforementioned organizations.