All devices are not created equal: Simultaneous data collection of three triaxial accelerometers sampling at different frequencies

Abstract

The surge of wearable device technology has enabled out-of-the-lab collection of running gait data for commercial, clinical, and coaching applications. However, low sampling frequencies interfere with measuring peak acceleration magnitudes accurately, and the ability to track relative changes during a prolonged run with lower sampling devices is unknown. The purposes of this study were to compare peak resultant acceleration measured simultaneously at different sampling frequencies and evaluate if different sampling frequencies could track similar relative changes in peak acceleration over a 20-min treadmill run. Seventeen participants ran on a treadmill at a self-selected, “easy” pace for 20-min (mean ± SD = 2.6 ± 0.4 m s−1). Three research-grade, triaxial accelerometers (“HiRes” = 1200 Hz, “MedRes” = 462 Hz, and “LoRes” = 100 Hz) were secured to each of three anatomical locations (tibia, low-back, forehead). Mean peak resultant accelerations from each device during minutes 3 to 18 were compared within each location (linear mixed model, α = 0.050). No significant device by timepoint interaction was observed ( p > 0.999). A significant main effect of sampling frequency at all three locations (HiRes > MedRes > LoRes; p < 0.001) confirmed the underestimation of low sampling frequencies on peak resultant acceleration. However, the significant main effect of time indicated that peak resultant acceleration changed similarly over time between sampling frequencies at the tibia ( p = 0.010) and head ( p = 0.002), but not the low-back ( p = 0.318). Downsampling HiRes to 400 and 100 Hz reduced the underestimation of the resultant peaks within the MedRes and LoRes signals by <7.7% across anatomical locations. This study confirms sampling frequency of wearable devices significantly affects peak resultant acceleration and demonstrates these effects are greater for signals captured at lower sampling frequencies and caudal locations. Despite these effects, this study cautiously supports the use of ≥100 Hz sampling frequencies for within-individual peak resultant acceleration tracking during “easy” prolonged runs for research, clinical, and coaching applications.