Wheelchair Propulsion for Everyday Manual Wheelchair Users: Repetition Training and Machine Learning-based Monitoring

Author's School

Graduate School of Arts and Sciences

ORCID

https://orcid.org/0000-0002-4394-1519

Author's Department/Program

Rehabilitation and Participation Science

Language

English (en)

Date of Award

Winter 12-15-2019

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Chair and Committee

Kerri Morgan

Committee Members

Carolyn Baum, Joseph W. Klaesner, Michael Mueller, Alex Wong

Abstract

Upper limb pain and injuries are prevalent among manual wheelchair users and can restrict their participation and daily activities. Due to the high repetition and force in wheelchair propulsion, chronic wheelchair propulsion has been linked to the risk of upper limb pain and injury. Prevention of upper limb pain and injury is a high priority in wheelchair-related research. Decades of research in wheelchair propulsion biomechanics have led to clinical practice guidelines (CPG). Unfortunately, a decade after the publication of the CPG, CPG-recommended propulsion is still uncommon. Hence, for the first aim, a randomized controlled trial pilot study with two groups (i.e., training group and education group) and three assessments were conducted to test an overground, repetition-based wheelchair propulsion training program based on the CPG. The results indicated that, after the intervention, the training group had significantly improved CPG propulsion features such as a smaller minimum hand–axle distance and higher push effectiveness; a greater likelihood of propelling using CPG-recommended propulsions was found for the training group.On the other hand, due to limitations in technology, wheelchair propulsion research has not established direct evidence to link daily wheelchair propulsion patterns to the chance of upper limb injuries. Therefore, in Aim 2, a feasibility study of a wearable sensor and machine learning-based monitoring protocol was tested. The results suggest promising indoor propulsion detection using a linear support vector machine algorithm; an acceptable accuracy of outdoor propulsion detection. In Aim 3, acceptability and adherence of the wearable sensor monitoring protocol were explored using a 24-hour monitoring program. General acceptability was positive, and adherence to the 24-hour monitoring was high.Together, these results contribute knowledge to evidence-based approaches of teaching CPG-recommended propulsions and the ability to monitor the effects of propulsion daily. This will allow clinicians to effectively teach and correct manual wheelchair usage at an early stage and, in consequence, reduce the chance of upper limb pain and injuries. Ultimately, these results will enable participation and improve the well-being of manual wheelchair users.

DOI

https://doi.org/10.7936/9qgn-3y23

Share

COinS