Regression equations for RT3 activity monitors to estimate energy expenditure in manual wheelchair users

Activity monitors (AMs) can assist persons with Spinal Cord Injury (SCI) who use manual wheelchairs to self-assess regular physical activity to move towards healthier lifestyles. In this study we evaluated the validity of an accelerometer-based RT3 AM in predicting energy expenditure (EE) of manual wheelchair users with SCI. Twenty-four subjects performed four types of physical activities including wheelchair propulsion, arm-ergometry exercise, deskwork, and resting in a laboratory setting. Subjects wore two RT3 AMs: an RT3 around the waist (RT3W) per the manufacturer's instruction and an RT3 on the upper arm (RT3A). Criterion EE was collected by a portable metabolic system. The absolute EE estimation error for the RT3W varied from 21.3%-55.2% for different activities. Two EE prediction equations (general and activity-specific) were developed from 19 randomly selected subjects and validated on the remaining 4 subjects for the RT3A, RT3W, and RT3 AMs combined. The results showed that the general and activity-specific regression equations for the RT3A performed better than the RT3W and similar to the RT3 AMs combined. The general EE equation for RT3A consisted of both the demographic variable weight and accelerometer variables showing it is sensitive to subject parameters and upper extremity movement. The activity-specific EE equations for RT3A showed demographic variable weight to be a significant predictor during resting and deskwork and accelerometer variables along with weight to be significant predictors during propulsion and arm-ergometry. The validation results from the activity-specific equations for the RT3A showed that the absolute EE estimation error varied from 12.2%-38.1%. Future work will recruit more subjects and refine the prediction equations for the RT3 AM to quantify physical activity in MWUs with SCI.