Wrist accelerometers are being used in population level surveillance of physical activity (PA) but more research is needed to evaluate their validity for correctly classifying types of PA behavior and predicting energy expenditure (EE). In this study we compare accelerometers worn on the wrist and hip, and the added value of heart rate (HR) data, for predicting PA type and EE using machine learning. Forty adults performed locomotion and household activities in a lab setting while wearing three ActiGraph GT3X+ accelerometers (left hip, right hip, non-dominant wrist) and a HR monitor (Polar RS400). Participants also wore a portable indirect calorimeter (COSMED K4b2), from which EE and metabolic equivalents (METs) were computed for each minute. We developed two predictive models: a random forest classifier to predict activity type and a random forest of regression trees to estimate METs. Predictions were evaluated using leave-one-user-out cross-validation. The hip accelerometer obtained an average accuracy of 92.3% in predicting four activity types (household, stairs, walking, running), while the wrist accelerometer obtained an average accuracy of 87.5%. Across all 8 activities combined (laundry, window washing, dusting, dishes, sweeping, stairs, walking, running), the hip and wrist accelerometers obtained average accuracies of 70.2% and 80.2% respectively. Predicting METs using the hip or wrist devices alone obtained root mean square errors (rMSE) of 1.09 and 1.00 METs per 6-minute bout, respectively. Including HR data improved MET estimation, but did not significantly improve activity type classification. These results demonstrate the validity of random forest classification and regression forests for PA type and MET prediction using accelerometers. The wrist accelerometer proved more useful in predicting activities with significant arm movement, while the hip accelerometer was superior for predicting locomotion and estimating EE.

Purpose Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate, and need testing in free-living with wrist-worn devices. In this study we developed and tested the performance of machine learned (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. Methods Forty overweight or obese women (mean age = 55.2 ±15.3 yrs; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, non-dominant wrist) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, riding in a vehicle). Free-living wrist and hip ML classifiers were compared to each other, to traditional accelerometer cut points, and to an algorithm developed in a laboratory setting. Results The ML classifier obtained an average of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our dataset with an average of 28.4 minutes of walking or running per day, the ML classifier predicted an average of 28.5 minutes and 24.5 minutes of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cutpoints and the laboratory algorithm significantly underestimated walking minutes. Conclusions Our results demonstrate the superior performance of our PA type classification algorithm, particularly in comparison to traditional cut-points. While the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.

Researchers should be aware of the strengths and weaknesses of the 100-cpm accelerometer cutpoint for identifying sedentary behavior. The SenseCam may be a useful tool in free-living conditions to better understand health behaviors such as sitting.

Purpose To assess validity of the Personal Activity Location Measurement System (PALMS) for deriving time spent walking/running, bicycling, and in vehicle, using SenseCam as the comparison. Methods 40 adult cyclists wore a Qstarz BT-Q1000XT GPS data logger and SenseCam (camera worn around neck capturing multiple images every minute) for a mean of 4 days. PALMS used distance and speed between GPS points to classify whether each minute was part of a trip (yes/no), and if so, the trip mode (walking/running, bicycling, in vehicle). SenseCam images were annotated to create the same classifications (i.e., trip yes/no and mode). 2×2 contingency tables and confusion matrices were calculated at the minute-level for PALMS vs. SenseCam classifications. Mixed-effects linear regression models estimated agreement (mean differences and intraclass correlations [ICCs]) between PALMS and SenseCam with regards to minutes/day in each mode. Results Minute-level sensitivity, specificity, and negative predictive value were ≥88%, and positive predictive value was ≥75% for non mode-specific trip detection. 72–80% of outdoor walking/running minutes, 73% of bicycling minutes, and 74–76% of in-vehicle minutes were correctly classified by PALMS. For minutes/day, PALMS had a mean bias (i.e., amount of over or under estimation) of 2.4–3.1 minutes (11–15%) for walking/running, 2.3–2.9 minutes (7–9%) for bicycling, and 4.3–5 minutes (15–17%) for vehicle time. ICCs were ≥.80 for all modes. Conclusions PALMS has validity for processing GPS data to objectively measure time walking/running, bicycling, and in vehicle in population studies. Assessing travel patterns is one of many valuable applications of GPS in physical activity research that can improve our understanding of the determinants and health outcomes of active transportation as well as its impact on physical activity.

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data.Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time.Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%.Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

Purpose Walking for health is recommended by health agencies, partly based on epidemiological studies of self-reported behaviors. Accelerometers are now replacing survey data but it is not clear that intensity based cut points reflect the behaviors previously reported. New computational techniques can help classify raw accelerometer data into behaviors meaningful for public health. Methods 520 days of triaxial 30 hertz accelerometer data from 3 studies (n=78) were employed as training data. Study 1 included prescribed activities completed in natural settings. The other two studies included multiple days of free living data with SenseCam annotated ground truth. The two populations in the free living data sets were demographically and physical different. Random forest classifiers were trained on each data set and the classification accuracy on the training data set and applied to the other available data sets was assessed. Accelerometer cut points were also compared with the ground truth from the 3 datasets. Results The random forest classified all behaviors with over 80% accuracy. Classifiers developed on the prescribed data performed with higher accuracy than the free living data classifier, but did not perform as well on the free living datasets. Many of the observed behaviors occurred at different intensities than those identified by existing cut points. Conclusions New machine learned classifiers developed from prescribed activities (Study 1) were considerably less accurate when applied to free-living populations or to a functionally different population (Studies 2 & 3). These classifiers, developed on free living data, may have value when applied to large cohort studies with existing hip accelerometer data.

BackgroundProlonged sitting is associated with cardiometabolic and vascular disease. Despite emerging evidence regarding the acute health benefits of interrupting prolonged sitting time, the effectiveness of different modalities in older adults (who sit the most) is unclear.MethodsIn preparation for a future randomized controlled trial, we enrolled 10 sedentary, overweight or obese, postmenopausal women (mean age 66 years ±9; mean body mass index 30.6 kg/m2 ±4.2) in a 4-condition, 4-period crossover feasibility pilot study in San Diego to test 3 different sitting interruption modalities designed to improve glucoregulatory and vascular outcomes compared to a prolonged sitting control condition. The interruption modalities included: a) 2 minutes standing every 20 minutes; b) 2 minutes walking every hour; and c) 10 minutes standing every hour. During each 5-hr condition, participants consumed two identical, standardized meals. Blood samples, blood pressure, and heart rate were collected every 30 minutes. Endothelial function of the superficial femoral artery was measured at baseline and end of each 5-hr condition using flow-mediated dilation (FMD). Participants completed each condition on separate days, in randomized order. This feasibility pilot study was not powered to detect statistically significant differences in the various outcomes, however, analytic methods (mixed models) were used to test statistical significance within the small sample size.ResultsNine participants completed all 4 study visits, one participant completed 3 study visits and then was lost to follow up. Net incremental area under the curve (iAUC) values for postprandial plasma glucose and insulin during the 5-hr sitting interruption conditions were not significantly different compared to the control condition. Exploratory analyses revealed that the 2-minute standing every 20 minutes and the 2-minute walking every hour conditions were associated with a significantly lower glycemic response to the second meal compared to the first meal (i.e., condition-matched 2-hour post-lunch glucose iAUC was lower than 2-hour post-breakfast glucose iAUC) that withstood Bonferroni correction (p = 0.0024 and p = 0.0084, respectively). Using allometrically scaled data, the 10-minute standing every hour condition resulted in an improved FMD response, which was significantly greater than the control condition after Bonferroni correction (p = 0.0033).ConclusionThis study suggests that brief interruptions in prolonged sitting time have modality-specific glucoregulatory and vascular benefits and are feasible in an older adult population. Larger laboratory and real-world intervention studies of pragmatic and effective methods to change sitting habits are needed.Trial registrationClinicalTrials.gov NCT02743286.

Physical activity (PA) provides health benefits in older adults. Research suggests that exposure to nature and time spent outdoors may also have effects on health. Older adults are the least active segment of our population, and are likely to spend less time outdoors than other age groups. The relationship between time spent in PA, outdoor time, and various health outcomes was assessed for 117 older adults living in retirement communities. Participants wore an accelerometer and GPS device for 7 days. They also completed assessments of physical, cognitive, and emotional functioning. Analyses of variance were employed with a main and interaction effect tested for ±30 min PA and outdoor time. Significant differences were found for those who spent >30 min in PA or outdoors for depressive symptoms, fear of falling, and self-reported functioning. Time to complete a 400 m walk was significantly different by PA time only. QoL and cognitive functioning scores were not significantly different. The interactions were also not significant. This study is one of the first to demonstrate the feasibility of using accelerometer and GPS data concurrently to assess PA location in older adults. Future analyses will shed light on potential causal relationships and could inform guidelines for outdoor activity.