This investigation developed models to estimate aspects of physical activity and sedentary behavior from three-axis high-frequency wrist-worn accelerometer data. The models were developed and tested on 20 participants (n = 10 males, n = 10 females, mean age = 24.1, mean body mass index = 23.9), who wore an ActiGraph GT3X+ accelerometer on their dominant wrist and an ActiGraph GT3X on the hip while performing a variety of scripted activities. Energy expenditure was concurrently measured by a portable indirect calorimetry system. Those calibration data were then used to develop and assess both machine-learning and simpler models with fewer unknown parameters (linear regression and decision trees) to estimate metabolic equivalent scores (METs) and to classify activity intensity, sedentary time, and locomotion time. The wrist models, applied to 15-s windows, estimated METs [random forest: root mean squared error (rSME) = 1.21 METs, hip: rMSE = 1.67 METs] and activity intensity (random forest: 75% correct, hip: 60% correct) better than a previously developed model that used counts per minute measured at the hip. In a separate set of comparisons, the simpler decision trees classified activity intensity (random forest: 75% correct, tree: 74% correct), sedentary time (random forest: 96% correct, decision tree: 97% correct), and locomotion time (random forest: 99% correct, decision tree: 96% correct) nearly as well or better than the machine-learning approaches. Preliminary investigation of the models' performance on two free-living people suggests that they may work well outside of controlled conditions.

Purpose To compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Methods Thirty-five older adults (21F and 14M ; 70.8 ± 4.9 y) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (dominant hip, wrist, and ankle). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore the GT3X+ in free-living settings and were directly observed for 2-3 hours. Time- and frequency- domain features from acceleration signals of each monitor were used to train Random Forest (RF) and Support Vector Machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on lab data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20 s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Results Overall classification accuracy rates for the algorithms developed from lab data were between 49% (wrist) to 55% (ankle) for the SVMLab algorithms, and 49% (wrist) to 54% (ankle) for RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Conclusion Our algorithms developed on free-living accelerometer data were more accurate in classifying activity type in free-living older adults than our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine-learning algorithms in older adults.

Purpose This pilot study examined if the combination of exercise training and reducing sedentary time (ST) results in greater changes to health markers than either intervention alone. Methods Fifty-seven overweight/obese participants (19M/39F) (mean ± SD; age 43.6 ± 9.9 y, BMI 35.1 ± 4.6 kg/m2) completed the 12-week study and were randomly assigned to 1) EX: exercise 5-days/week for 40-minutes/session at moderate intensity; 2) rST: reduce ST and increase non-exercise physical activity; 3) EX-rST: combination of EX and rST and 4) CON: maintain behavior. Fasting lipids, blood pressure (BP), VO2 peak, BMI and 2-hr oral glucose tolerance tests were completed pre- and post-intervention. Results EX and EX-rST increased VO2 peak by ~10% and decreased systolic BP (both p<0.001). BMI decreased by −3.3% (95% CI: −4.6 to −1.9%) for EX-rST and −2.2% (−3.5 to 0.0%) for EX. EX-rST significantly increased C-ISI by 17.8% (2.8 to 32.8%) and decreased insulin area-under-the-curve by 19.4% (−31.4 to −7.3%). No other groups improved in insulin action variables. rST group decreased ST by 7% (~50 min/day), however BP was the only health-related outcome that improved. Conclusions EX and EX-rST improved VO2 peak and BMI providing further evidence that moderate intensity exercise is beneficial. The within-group analysis provides preliminary evidence that exercising and reducing ST may result in improvements in metabolic biomarkers that are not seen with exercise alone, though between group differences did not reach statistical significance. Future studies, with larger samples, should examine health-related outcomes resulting from greater reductions in ST over longer intervention periods.