Abstract
ABSTRACTPurposeThis study aimed to improve estimates of sitting time from hip-worn accelerometers used in large cohort studies by using machine learning methods developed on free-living activPAL data.MethodsThirty breast cancer survivors concurrently wore a hip-worn accelerometer and a thigh-worn activPAL for 7 d. A random forest classifier, trained on the activPAL data, was used to detect sitting, standing, and sit–stand transitions in 5-s windows in the hip-worn accelerometer. The classifier estimates were compared with the standard accelerometer cut point, and significant differences across different bout lengths were investigated using mixed-effect models.ResultsOverall, the algorithm predicted the postures with moderate accuracy (stepping, 77%; standing, 63%; sitting, 67%; sit-to-stand, 52%; and stand-to-sit, 51%). Daily level analyses indicated that errors in transition estimates were only occurring during sitting bouts of 2 min or less. The standard cut point was significantly different from the activPAL across all bout lengths, overestimating short bouts and underestimating long bouts.ConclusionsThis is among the first algorithms for sitting and standing for hip-worn accelerometer data to be trained from entirely free-living activPAL data. The new algorithm detected prolonged sitting, which has been shown to be the most detrimental to health. Further validation and training in larger cohorts is warranted.
Highlights
There has been increasing interest in the relationship between sedentary behavior and health [1]
Use of the activPAL as the ‘‘ground truth’’ for algorithm development in detecting postural transitions is beneficial because it is valid for this purpose, and it can be worn for multiple days and hours representing typical free-living behavior and does not depend on a human observer for postural coding
As indicated by activPAL ground truth, the average (SD) time spent sitting per day was 499 [83] min, and the average (SD) time spent standing per day was 248 [74] min
Summary
There has been increasing interest in the relationship between sedentary behavior and health [1]. New computation algorithms for hip-worn accelerometers that show promise in improving estimates of physical activity could perhaps minimize the error seen in the existing cut-point approach to sedentary behavior [12]. Use of the activPAL as the ‘‘ground truth’’ for algorithm development in detecting postural transitions is beneficial because it is valid for this purpose, and it can be worn for multiple days and hours representing typical free-living behavior and does not depend on a human observer for postural coding. Most algorithms that include sitting classifiers are not trained to detect postural transitions and algorithms or cut points that have been developed from laboratory studies do not include free-living behaviors such as sitting in a vehicle [18,19]. Because longer bouts of sitting may be worse for health, we compared estimates of the number of and minutes in sedentary bouts across different sitting bout lengths with the existing 100-counts per minute cut point
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
