Toward community-based wheelchair evaluation with machine learning methods

Abstract

Introduction Upper extremity pain among manual wheelchair users induces functional decline and reduces quality of life. Research has identified chronic overuse due to wheelchair propulsion as one of the factors associated with upper limb injuries. Lack of a feasible tool to track wheelchair propulsion in the community precludes testing validity of wheelchair propulsion performed in the laboratory. Recent studies have shown that wheelchair propulsion can be tracked through machine learning methods and wearable accelerometers. Better results were found in subject-specific machine learning method. To further develop this technique, we conducted a pilot study examining the feasibility of measuring wheelchair propulsion patterns. Methods Two participants, an experienced manual wheelchair user and an able-bodied individual, wore two accelerometers on their arms. The manual wheelchair user performed wheelchair propulsion patterns on a wheelchair roller system and overground. The able-bodied participant performed common daily activities such as cooking, cleaning, and eating. Results The support vector machine built from the wrist and arm acceleration of wheelchair propulsion pattern recorded on the wheelchair roller system predicted the wheelchair propulsion patterns performed overground with 99.7% accuracy. The support vector machine built from additional rotation data recorded overground predicted wheelchair propulsion patterns (F1 = 0.968). Conclusions These results further demonstrate the possibility of tracking wheelchair propulsion in the community.

Real-Life Wheelchair Mobility Metrics from IMUs

“…Therefore, the disadvantage of IMUs is that propulsion variables are not measured directly on the wheel but must be deduced from the (raw) IMU signals. To use IMUs for tracking physical activity and wheelchair propulsion, methodologies have been developed for use in both daily life [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ] and sports settings [ 37 , 38 , 39 , 40 , 41 , 42 ]. Regarding wheelchair propulsion in daily life, most of the literature is published on methods for quantifying a manual wheelchair user’s energy expenditure or activity levels during physical activity [ 27 , 30 , 31 , 34 ].…”

“…However, methods for quantifying wheelchair propulsion itself, and thus quantifying the wheelchair user’s exposure to one of the risk factors for shoulder problems, are scarce. Nevertheless, in general, one or two variables of propulsion quantification are addressed in previous publications, (such as speed [ 26 , 29 , 36 ], distance covered [ 26 , 29 , 33 , 35 , 36 ], number of pushes [ 20 , 24 , 25 , 28 , 32 ], duration of movement [ 23 , 36 ], direction of movement [ 23 ] or propulsion style [ 21 , 22 ]); a methodology combining several of the relevant variables is still missing.…”