INTRODUCTION: Methods to estimate physical activity (PA) and sedentary behavior (SB) from wearable monitors need to be validated in free-living settings. PURPOSE: The purpose of this study was to develop and validate two novel machine-learning methods (Sojourn-1 Axis [soj-1x] and Sojourn-3 Axis [soj-3x]) in a free-living setting. METHODS: Participants were directly observed in their natural environment for 10 consecutive hours on three separate occasions. Physical activity and SB estimated from soj-1x, soj-3x, and a neural network previously calibrated in the laboratory (lab-nnet) were compared with direct observation. RESULTS: Compared with lab-nnet, soj-1x and soj-3x improved estimates of MET-hours (lab-nnet: % bias [95% confidence interval] = 33.1 [25.9 to 40.4], root-mean-square error [RMSE] = 5.4 [4.6-6.2]; soj-1x: % bias = 1.9 [-2.0 to 5.9], RMSE = 1.0 [0.6 to 1.3]; soj-3x: % bias = 3.4 [0.0 to 6.7], RMSE = 1.0 [0.6 to 1.5]) and minutes in different intensity categories {lab-nnet: % bias = -8.2 (sedentary), -8.2 (light), and 72.8 (moderate-to-vigorous PA [MVPA]); soj-1x: % bias = 8.8 (sedentary), -18.5 (light), and -1.0 (MVPA); soj-3x: % bias = 0.5 (sedentary), -0.8 (light), and -1.0 (MVPA)}. Soj-1x and soj-3x also produced accurate estimates of guideline minutes and breaks from sedentary time. CONCLUSIONS: Compared with the lab-nnet algorithm, soj-1x and soj-3x improved the accuracy and precision in estimating free-living MET-hours, sedentary time, and time spent in light-intensity activity and MVPA. In addition, soj-3x is superior to soj-1x in differentiating SB from light-intensity activity.
INTRODUCTION: Methods to estimate physical activity (PA) and sedentary behavior (SB) from wearable monitors need to be validated in free-living settings. PURPOSE: The purpose of this study was to develop and validate two novel machine-learning methods (Sojourn-1 Axis [soj-1x] and Sojourn-3 Axis [soj-3x]) in a free-living setting. METHODS:Participants were directly observed in their natural environment for 10 consecutive hours on three separate occasions. Physical activity and SB estimated from soj-1x, soj-3x, and a neural network previously calibrated in the laboratory (lab-nnet) were compared with direct observation. RESULTS: Compared with lab-nnet, soj-1x and soj-3x improved estimates of MET-hours (lab-nnet: % bias [95% confidence interval] = 33.1 [25.9 to 40.4], root-mean-square error [RMSE] = 5.4 [4.6-6.2]; soj-1x: % bias = 1.9 [-2.0 to 5.9], RMSE = 1.0 [0.6 to 1.3]; soj-3x: % bias = 3.4 [0.0 to 6.7], RMSE = 1.0 [0.6 to 1.5]) and minutes in different intensity categories {lab-nnet: % bias = -8.2 (sedentary), -8.2 (light), and 72.8 (moderate-to-vigorous PA [MVPA]); soj-1x: % bias = 8.8 (sedentary), -18.5 (light), and -1.0 (MVPA); soj-3x: % bias = 0.5 (sedentary), -0.8 (light), and -1.0 (MVPA)}. Soj-1x and soj-3x also produced accurate estimates of guideline minutes and breaks from sedentary time. CONCLUSIONS: Compared with the lab-nnet algorithm, soj-1x and soj-3x improved the accuracy and precision in estimating free-living MET-hours, sedentary time, and time spent in light-intensity activity and MVPA. In addition, soj-3x is superior to soj-1x in differentiating SB from light-intensity activity.
Authors: Anthony G Brooks; Robert T Withers; Christopher J Gore; Andrew J Vogler; John Plummer; John Cormack Journal: Eur J Appl Physiol Date: 2003-12-18 Impact factor: 3.078
Authors: Barbara E Ainsworth; William L Haskell; Stephen D Herrmann; Nathanael Meckes; David R Bassett; Catrine Tudor-Locke; Jennifer L Greer; Jesse Vezina; Melicia C Whitt-Glover; Arthur S Leon Journal: Med Sci Sports Exerc Date: 2011-08 Impact factor: 5.411
Authors: Sarah Kozey-Keadle; Amanda Libertine; Kate Lyden; John Staudenmayer; Patty S Freedson Journal: Med Sci Sports Exerc Date: 2011-08 Impact factor: 5.411
Authors: Marta Karas; Jiawei Bai; Marcin Strączkiewicz; Jaroslaw Harezlak; Nancy W Glynn; Tamara Harris; Vadim Zipunnikov; Ciprian Crainiceanu; Jacek K Urbanek Journal: Stat Biosci Date: 2019-01-12
Authors: Steven P Hooker; Brent Hutto; Wenfei Zhu; Steven N Blair; Natalie Colabianchi; John E Vena; David Rhodes; Virginia J Howard Journal: J Sci Med Sport Date: 2015-04-17 Impact factor: 4.319
Authors: Ryan J Dougherty; Stephanie A Schultz; Taylor K Kirby; Elizabeth A Boots; Jennifer M Oh; Dorothy Edwards; Catherine L Gallagher; Cynthia M Carlsson; Barbara B Bendlin; Sanjay Asthana; Mark A Sager; Bruce P Hermann; Bradley T Christian; Sterling C Johnson; Dane B Cook; Ozioma C Okonkwo Journal: J Alzheimers Dis Date: 2017 Impact factor: 4.472
Authors: Erika Rees-Punia; Charles E Matthews; Ellen M Evans; Sarah K Keadle; Rebecca L Anderson; Jennifer L Gay; Michael D Schmidt; Susan M Gapstur; Alpa V Patel Journal: Med Sci Sports Exerc Date: 2019-01 Impact factor: 5.411
Authors: Ryan J Dougherty; Jacob B Lindheimer; Aaron J Stegner; Stephanie Van Riper; Ozioma C Okonkwo; Dane B Cook Journal: J Alzheimers Dis Date: 2018 Impact factor: 4.472
Authors: Ryan J Dougherty; Elizabeth A Boots; Jacob B Lindheimer; Aaron J Stegner; Stephanie Van Riper; Dorothy F Edwards; Catherine L Gallagher; Cynthia M Carlsson; Howard A Rowley; Barbara B Bendlin; Sanjay Asthana; Bruce P Hermann; Mark A Sager; Sterling C Johnson; Ozioma C Okonkwo; Dane B Cook Journal: Brain Imaging Behav Date: 2020-08 Impact factor: 3.978
Authors: Somdat Mahabir; Walter C Willett; Christine M Friedenreich; Gabriel Y Lai; Carol J Boushey; Charles E Matthews; Rashmi Sinha; Graham A Colditz; Joseph A Rothwell; Jill Reedy; Alpa V Patel; Michael F Leitzmann; Gary E Fraser; Sharon Ross; Stephen D Hursting; Christian C Abnet; Lawrence H Kushi; Philip R Taylor; Ross L Prentice Journal: Cancer Epidemiol Biomarkers Prev Date: 2017-12-18 Impact factor: 4.254
Authors: Kate Lyden; Tracy Swibas; Victoria Catenacci; Ruixin Guo; Neil Szuminsky; Edward L Melanson Journal: Med Sci Sports Exerc Date: 2014-11 Impact factor: 5.411