Objectives: We aimed to quantify the agreement between self-report, standard cut-point accelerometer, and machine learning accelerometer estimates of physical activity (PA), and exam- ine how agreement changes over time among older adults in an intervention setting. Methods: Data were from a randomized weight loss trial that encouraged increased PA among 333 postmenopausal breast cancer survivors. PA was estimated using accelerometry and a validated questionnaire at baseline and 6-months. Accelerometer data were processed using standard cut-points and a validated machine learning algorithm. Agreement of PA at each time-point and change was assessed using mixed effects regression models and concordance correlation. Results: At baseline, self-report and machine learning provided similar PA estimates (mean dif- ference = 11.5 min/day) unlike self-report and standard cut-points (mean difference = 36.3 min/ day). Cut-point and machine learning methods assessed PA change over time more similarly than other comparisons. Specifically, the mean difference of PA change for the cut-point versus machine learning methods was 5.1 min/day for intervention group and 2.9 in controls, whereas it was ≥ 24.7 min/day for other comparisons. Conclusions: Intervention researchers are facing the issue of self-report measures introducing bias and accelerometer cut-points being insensi- tive. Machine learning approaches may bridge this gap.
RCT Entities:
Objectives: We aimed to quantify the agreement between self-report, standard cut-point accelerometer, and machine learning accelerometer estimates of physical activity (PA), and exam- ine how agreement changes over time among older adults in an intervention setting. Methods: Data were from a randomized weight loss trial that encouraged increased PA among 333 postmenopausal breast cancer survivors. PA was estimated using accelerometry and a validated questionnaire at baseline and 6-months. Accelerometer data were processed using standard cut-points and a validated machine learning algorithm. Agreement of PA at each time-point and change was assessed using mixed effects regression models and concordance correlation. Results: At baseline, self-report and machine learning provided similar PA estimates (mean dif- ference = 11.5 min/day) unlike self-report and standard cut-points (mean difference = 36.3 min/ day). Cut-point and machine learning methods assessed PA change over time more similarly than other comparisons. Specifically, the mean difference of PA change for the cut-point versus machine learning methods was 5.1 min/day for intervention group and 2.9 in controls, whereas it was ≥ 24.7 min/day for other comparisons. Conclusions: Intervention researchers are facing the issue of self-report measures introducing bias and accelerometer cut-points being insensi- tive. Machine learning approaches may bridge this gap.
Authors: Martina E Schmidt; Joachim Wiskemann; Petra Armbrust; Andreas Schneeweiss; Cornelia M Ulrich; Karen Steindorf Journal: Int J Cancer Date: 2014-12-16 Impact factor: 7.396
Authors: Kerry S Courneya; Roanne J Segal; Donald C McKenzie; Huiru Dong; Karen Gelmon; Christine M Friedenreich; Yutaka Yasui; Robert D Reid; Jennifer J Crawford; John R Mackey Journal: Med Sci Sports Exerc Date: 2014-09 Impact factor: 5.411
Authors: Kerry S Courneya; Roanne J Segal; John R Mackey; Karen Gelmon; Christine M Friedenreich; Yutaka Yasui; Robert D Reid; Diana Jespersen; Diane Cook; Carolyn Proulx; Linda Trinh; Lianne B Dolan; Evyanne Wooding; Cynthia C Forbes; Donald C McKenzie Journal: Breast Cancer Res Treat Date: 2014-02-20 Impact factor: 4.872
Authors: Stéphanie A Prince; Kristi B Adamo; Meghan E Hamel; Jill Hardt; Sarah Connor Gorber; Mark Tremblay Journal: Int J Behav Nutr Phys Act Date: 2008-11-06 Impact factor: 6.457