Evaluation of activity monitors to estimate energy expenditure in manual wheelchair users

In an effort to make activity monitors usable by manual wheelchair users with spinal cord injury (SCI), our study examines the validity of SenseWearreg Armband (SenseWear) and RT3 in assessing energy expenditure (EE) during wheelchair related activities. This paper presents the data obtained from six subjects (n=6) with SCI performing three activities, including wheelchair propulsion, armergometer exercise and deskwork. The analysis presented here compares the EE estimated from the SenseWear and the RT3 with respect to the EE measured from a portable metabolic cart. It was found that the SenseWear overestimated EE for resting (+5.78%), wheelchair propulsion (+88.20%, +46.20%, and +138.21% for the three trials at different intensities, respectively), arm-ergometer exercise (+55.05%, +26.91%, and +39.17% for the three trials at different intensities, respectively) and deskwork (+13.11%). The results also indicate that RT3 underestimated EE for resting (-3.06%), wheelchair propulsion (-24.23%, -19.42%, and -9.98% for the three trials at different intensities, respectively), arm-ergometer exercise (-49.06%, -53.69% and -52.08 for the three trials at different intensities, respectively) and measured EE relatively accurate for deskwork. Good and moderate Intraclass correlations were found between EE measured by metabolic cart and EE estimated by SenseWear (0.787, p<0.0001) and RT3 (0.705, p<0.0001). Weka, machine learning software, was used to select attributes and model EE equations for the SenseWear and the RT3. Excellent and good Intraclass correlations were found between the EE measured by the metabolic cart and the estimated EE based on the models for SenseWear (0.944, p<0.0001) and RT3 (0.821, p<0.0001). Future work will test more subjects to refine the model and provide manual wheelchair users with a valid tool to gauge their daily physical activity and EE.