The ActiGraph has a high ability to measure physical activity; however, it lacks an accurate posture classification to measure sedentary behavior. The aim of the present study was to develop an ActiGraph (waist-worn, 30 Hz) posture classification to detect prolonged sitting bouts, and to compare the classification to proprietary ActiGraph data. The activPAL, a highly valid posture classification device, served as reference criterion. Both sensors were worn by 38 office workers over a median duration of 9 days. An automated feature selection extracted the relevant signal information for a minute-based posture classification. The machine learning algorithm with optimal feature number to predict the time in prolonged sitting bouts (≥5 and ≥10 minutes) was searched and compared to the activPAL using Bland-Altman statistics. The comparison included optimized and frequently used cut-points (100 and 150 counts per minute (cpm), with and without low-frequency-extension (LFE) filtering). The new algorithm predicted the time in prolonged sitting bouts most accurate (bias ≤ 7 minutes/d). Of all proprietary ActiGraph methods, only 150 cpm without LFE predicted the time in prolonged sitting bouts non-significantly different from the activPAL (bias ≤ 18 minutes/d). However, the frequently used 100 cpm with LFE accurately predicted total sitting time (bias ≤ 7 minutes/d). To study the health effects of ActiGraph measured prolonged sitting, we recommend using the new algorithm. In case a cut-point is used, we recommend 150 cpm without LFE to measure prolonged sitting and 100 cpm with LFE to measure total sitting time. However, both cpm cut-points are not recommended for a detailed bout analysis.
Keywords: activPAL; automated feature selection; bout analysis; machine learning; posture prediction; sedentary behavior.
© 2019 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.