Real-Life Wheelchair Mobility Metrics from IMUs

Abstract

Daily wheelchair ambulation is seen as a risk factor for shoulder problems, which are prevalent in manual wheelchair users. To examine the long-term effect of shoulder load from daily wheelchair ambulation on shoulder problems, quantification is required in real-life settings. In this study, we describe and validate a comprehensive and unobtrusive methodology to derive clinically relevant wheelchair mobility metrics (WCMMs) from inertial measurement systems (IMUs) placed on the wheelchair frame and wheel in real-life settings. The set of WCMMs includes distance covered by the wheelchair, linear velocity of the wheelchair, number and duration of pushes, number and magnitude of turns and inclination of the wheelchair when on a slope. Data are collected from ten able-bodied participants, trained in wheelchair-related activities, who followed a 40 min course over the campus. The IMU-derived WCMMs are validated against accepted reference methods such as Smartwheel and video analysis. Intraclass correlation (ICC) is applied to test the reliability of the IMU method. IMU-derived push duration appeared to be less comparable with Smartwheel estimates, as it measures the effect of all energy applied to the wheelchair (including thorax and upper extremity movements), whereas the Smartwheel only measures forces and torques applied by the hand at the rim. All other WCMMs can be reliably estimated from real-life IMU data, with small errors and high ICCs, which opens the way to further examine real-life behavior in wheelchair ambulation with respect to shoulder loading. Moreover, WCMMs can be applied to other applications, including health tracking for individual interest or in therapy settings.

Keywords: IMU; activities of daily living; shoulder; spinal cord injury; wearable sensors; wheelchair propulsion.

Figure 1

Equipment used. A standard active wheelchair with a Smartwheel on the right side, a Shimmer IMU attached to the wheel in such a way it did not hinder propulsion and another IMU attached to one of the horizontal bars of the wheelchair frame (not visible here).

Figure 2

Distance covered as derived from Smartwheel data (blue) and from an IMU mounted on the wheel (green). Typical example from one participant. The blue line is hardly visible as the lines overlap, indicating equal performance over the complete trajectory.

Figure 3

Linear velocity as derived from Smartwheel data (blue) and from an IMU mounted on the wheel (green). The graph represents a typical example from one participant.

Figure 4

Typical example of the push detection for one participant using about two minutes of data. The top graph depicts the pushes detected from propulsive torque as measured with a Smartwheel; the lower graph depicts the results from push detection on angular velocity from an IMU attached to the wheelchair wheel. The number of pushes indicated in the titles of the graphs are for the full duration of the measurement, in this case around 40 min. A green circle indicates the start and a red circle the end of a push.

Figure 5

The normalized histograms show the overlap of push duration derived from the Smartwheel (SW, blue) and (A) IMU angular velocity (green) or (B) IMU angular acceleration (green) for one participant. Dark green areas visualize the overlap of the blue and green bars.

Figure 6

Normalized histograms for the magnitude of turns as derived from the data from the frame IMU (blue) and the wheel IMU (green) according to Equation (3). The percentage overlap (visualized in dark green) is calculated according to Equation (4); it is 95% for this specific participant.

Figure 7

The graph depicts the different push styles that were observed in an extended analysis, indicating the need for clear definitions of pushes and braking actions. AV is angular velocity, which is positive when driving forward and negative when driving backward. The blue vertical lines indicate propulsive torque when driving forward (313 pushes), the dashed green lines indicate propulsive torque when driving backward and then forward during a push (26 pushes, making a turn on the spot, then driving forward) or when driving backward (red dotted lines, 2 pushes, in fact braking when driving backward); blue lines at negative angular velocity indicate negative torque when driving backward (11, propelling backward), the dashed green lines indicate negative torque when driving forward and backward during a push (12 times), the red dotted lines indicate negative torque while driving forward (75 times, in fact braking when driving forward).