Purpose: This study was conducted to devise a new individual calibration method to enhance MTI accelerometer estimation of free-living level walking speed.
Method: Five female and five male middle-aged adults walked 400 m at 3.5, 4.5, and 5.5 km x h(-1), and 800 m at 6.5 km x h(-1) on an outdoor track, following a continuous protocol. Lap speed was controlled by a global positioning system (GPS) monitor. MTI counts-to-speed calibration equations were derived for each trial, for each subject for four such trials with each of four MTI, for each subject for the average MTI, and for the pooled data. Standard errors of the estimate (SEE) with and without individual calibration were compared. To assess accuracy of prediction of free-living walking speed, subjects also completed a self-paced, "brisk" 3-km walk wearing one of the four MTI, and differences between actual and predicted walking speed with and without individual calibration were examined.
Results: Correlations between MTI counts and walking speed were 0.90 without individual calibration, 0.98 with individual calibration for the average MTI, and 0.99 with individual calibration for a specific MTI. The SEE (mean +/- SD) was 0.58 +/- 0.30 km x h(-1) without individual calibration, 0.19 +/- 0.09 km x h(-1) with individual calibration for the average MTI monitor, and 0.16 +/- 0.08 km x h(-1) with individual calibration for a specific MTI monitor. The difference between actual and predicted walking speed on the "brisk" 3-km walk was 0.06 +/- 0.25 km x h(-1) using individual calibration and 0.28 +/- 0.63 km x h(-1) without individual calibration (for specific accelerometers).
Conclusion: MTI accuracy in predicting walking speed without individual calibration might be sufficient for population-based studies but not for intervention trials. This individual calibration method will substantially increase precision of walking speed predicted from MTI counts.