Explore the vast range of titles available.

[...]there is growing recognition that the relationship between accelerometer counts and energy expenditure is highly dependent on the activities included the calibration study; and that cut-points derived from a single regression model or Receiver Operating Characteristic curve cannot adequately characterise physical activity intensity across a wide range of physical activities [13]. [...]it is important to note that the Evenson cut-points still misclassified MVPA as light-intensity physical activity 20% of the time, and that light intensity physical activities were misclassified as sedentary at least 40% of the time [12]. [...]given that the relationship between activity counts and energy expenditure in children under five differs substantially to that observed in adolescent youth [14], the application of the Evenson cut-points in children aged 2- to 5-years by Steene-Johannessen must be questioned. When applied to youth, machine learning approaches have shown to provide more accurate predictions of physical activity intensity [13, 16]. [...]to cut-point methods, which only estimate time spend in MVPA, physical activity classification models can predict time spent in specific activity types (e.g., walking, running, dancing, cycling) or broader activity classes (e.g., active games or sports) [13, 16]. Because hip mounted accelerometers are typically placed on snug fitting elastic belts and worn over clothing, non-compliance and insufficient wear time were frequent problems in these studies.

Machine learning (ML) accelerometer data processing methods have potential to improve the accuracy of device-based assessments of physical activity (PA) in young children. Yet the uptake of ML methods by health researchers has been minimal and the use of cut-points (CP) continues to be the norm, despite evidence of significant misclassification error. The lack of studies demonstrating a relative advantage for ML approaches over CP methods maybe a key contributing factor. The current study compared the accuracy of PA intensity predictions provided by ML classification models and previously published CPs for preschool-aged children. In a free-living study, 31 preschool-aged children (mean age = 4.0 ± 0.9 y) wore wrist and hip ActiGraph GT3X+ accelerometers while completing a video recorded 20-minute free play session. Ground truth PA intensity was coded continuously using the Children's Activity Rating Scale (CARS). Accelerometer data was classified as sedentary (SED), light intensity (LPA), or moderate-to-vigorous intensity (MVPA) using ML random forest PA classifiers and published CPs for preschool-aged children. Performance differences were evaluated in a hold-out sample by comparing weighted kappa statistics, classification accuracy for each intensity band, and equivalence testing. ML classification models (hip: κ = 0.76; wrist: κ = 0.72) exhibited significantly higher agreement with ground truth PA intensity than CP methods (hip: κ = 0.38-0.49; wrist: κ = 0.31-0.44). For the ML models, classification accuracy for SED and LPA ranged from 83% - 88%, while classification accuracy for MVPA ranged from 68% - 78%. For the CP's, classification accuracy ranged from 50% - 94% for SED, 19% - 75% for LPA, and 44% - 76.1% for MVPA. ML classification models showed equivalence (within ± 0.5 SD) with directly observed time in SED, LPA, and MVPA. None of the CP's exhibited evidence of equivalence. Under free living conditions, ML classification models for hip or wrist accelerometer data provide more accurate assessments of PA intensity in young children than CP methods. The results demonstrate the relative advantage of ML methods over threshold-based approaches and adds to a growing evidence base supporting the feasibility and accuracy of ML accelerometer data processing methods.

Machine learning (ML) activity classification models trained on laboratory-based activity trials exhibit low accuracy under free-living conditions. Training new models on free-living accelerometer data, reducing the number of prediction windows comprised of multiple activity types by using shorter windows, including temporal features such as standard deviation in lag and lead windows, and using multiple sensors may improve the classification accuracy under free-living conditions. The objective of this study was to evaluate the accuracy of Random Forest (RF) activity classification models for preschool-aged children trained on free-living accelerometer data. Thirty-one children (mean age = 4.0 ± 0.9 years) completed a 20 min free-play session while wearing an accelerometer on their right hip and non-dominant wrist. Video-based direct observation was used to categorize the children’s movement behaviors into five activity classes. The models were trained using prediction windows of 1, 5, 10, and 15 s, with and without temporal features. The models were evaluated using leave-one-subject-out-cross-validation. The F-scores improved as the window size increased from 1 to 15 s (62.6%–86.4%), with only minimal improvements beyond the 10 s windows. The inclusion of temporal features increased the accuracy, mainly for the wrist classification models, by an average of 6.2 percentage points. The hip and combined hip and wrist classification models provided comparable accuracy; however, both the models outperformed the models trained on wrist data by 7.9 to 8.2 percentage points. RF activity classification models trained with free-living accelerometer data provide accurate recognition of young children’s movement behaviors under real-world conditions.

To evaluate the accuracy of LAB EE prediction models in preschool children completing a free-living active play session. Performance was benchmarked against EE prediction models trained on free living (FL) data. 25 children (mean age = 4.1±1.0 y) completed a 20-minute active play session while wearing a portable indirect calorimeter and ActiGraph GT3X+ accelerometers on their right hip and non-dominant wrist. EE was predicted using LAB models which included Random Forest (RF) and Support Vector Machine (SVM) models for the wrist, and RF and Artificial Neural Network (ANN) models for the hip. Two variations of the LAB models were evaluated; 1) an \"off the shelf\" model without additional training; 2) models retrained on free-living data, replicating the methodology used in the original calibration study (retrained LAB). Prediction errors were evaluated in a hold-out sample of 10 children. Root mean square error (RMSE) for the FL and retrained LAB models ranged from 0.63-0.67 kcals/min. In the hold out sample, RMSE's for the hip LAB (0.62-0.71), retrained LAB (0.58-0.62) and FL models (0.61-0.65) were similar. For the wrist placement, FL SVM had a significantly higher RMSE (0.73 ± 0.29 kcals/min) than the retrained LAB SVM (0.63 ± 0.30 kcals/min) and LAB SVM (0.64 ± 0.18 kcals/min). The LAB (0.64 ± 0.28), retrained LAB (0.64 ± 0.25), and FL (0.62 ± 0.26) RF exhibited comparable accuracy. Machine learning EE prediction models trained on LAB and FL data had similar accuracy under free-living conditions.

Background In 2017, the Australian Government funded the update of the National Physical Activity Recommendations for Children 0–5 years, with the intention that they be an integration of movement behaviours across the 24-h period. The benefit for Australia was that it could leverage research in Canada in the development of their 24-h guidelines for the early years. Concurrently, the Grading of Recommendations Assessment, Development and Evaluation (GRADE) working group published a model to produce guidelines based on adoption, adaption and/or de novo development using the GRADE evidence-to-decision framework. Referred to as the GRADE-ADOLOPMENT approach, it allows guideline developers to follow a structured and transparent process in a more efficient manner, potentially avoiding the need to unnecessarily repeat costly tasks such as conducting systematic reviews. The purpose of this paper is to outline the process and outcomes for adapting the Canadian 24-Hour Movement Guidelines for the Early Years to develop the Australian 24-Hour Movement Guidelines for the Early Years guided by the GRADE-ADOLOPMENT framework. Methods The development process was guided by the GRADE-ADOLOPMENT approach. A Leadership Group and Consensus Panel were formed and existing credible guidelines identified. The draft Canadian 24-h integrated movement guidelines for the early years best met the criteria established by the Panel. These were evaluated based on the evidence in the GRADE tables, summaries of findings tables and draft recommendations from the Canadian Draft Guidelines. Updates to each of the Canadian systematic reviews were conducted and the Consensus Panel reviewed the evidence for each behaviour separately and made a decision to adopt or adapt the Canadian recommendations for each behaviour or create de novo recommendations. An online survey was then conducted ( n  = 302) along with five focus groups ( n  = 30) and five key informant interviews ( n  = 5) to obtain feedback from stakeholders on the draft guidelines. Results Based on the evidence from the Canadian systematic reviews and the updated systematic reviews in Australia, the Consensus Panel agreed to adopt the Canadian recommendations and, apart from some minor changes to the wording of good practice statements, keep the wording of the guidelines, preamble and title of the Canadian Guidelines. The Australian Guidelines provide evidence-informed recommendations for a healthy day (24-h), integrating physical activity, sedentary behaviour (including limits to screen time), and sleep for infants (<1 year), toddlers (1–2 years) and preschoolers (3–5 years). Conclusions To our knowledge, this is only the second time the GRADE-ADOLOPMENT approach has been used. Following this approach, the judgments of the Australian Consensus Panel did not differ sufficiently to change the directions and strength of the recommendations and as such, the Canadian recommendations were adopted with very minor alterations. This allowed the Guidelines to be developed much faster and at lower cost. As such, we would recommend the GRADE-ADOLOPMENT approach, especially if a credible set of guidelines, with all supporting materials and developed using a transparent process, is available. Other countries may consider using this approach when developing and/or revising national movement guidelines.

This study examined the feasibility of a non-laboratory approach that uses machine learning on multimodal sensor data to predict relative physical activity (PA) intensity. A total of 22 participants completed up to 7 PA sessions, where each session comprised 5 trials (sitting and standing, comfortable walk, brisk walk, jogging, running). Participants wore a wrist-strapped sensor that recorded heart-rate (HR), electrodermal activity (Eda) and skin temperature (Temp). After each trial, participants provided ratings of perceived exertion (RPE). Three classifiers, including random forest (RF), neural network (NN) and support vector machine (SVM), were applied independently on each feature set to predict relative PA intensity as low (RPE ≤ 11), moderate (RPE 12–14), or high (RPE ≥ 15). Then, both feature fusion and decision fusion of all combinations of sensor modalities were carried out to investigate the best combination. Among the single modality feature sets, HR provided the best performance. The combination of modalities using feature fusion provided a small improvement in performance. Decision fusion did not improve performance over HR features alone. A machine learning approach using features from HR provided acceptable predictions of relative PA intensity. Adding features from other sensing modalities did not significantly improve performance.

Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were: (1) train and test a random forest activity classifier for wrist accelerometer data; and (2) determine if models trained on laboratory data perform well under free-living conditions. Twenty-one participants (mean age=27.6±6.2) completed seven lab-based activity trials and a 24h free-living trial (N=16). Participants wore a GENEActiv monitor on the non-dominant wrist. Classification models recognising four activity classes (sedentary, stationary+, walking, and running) were trained using time and frequency domain features extracted from 10-s non-overlapping windows. Model performance was evaluated using leave-one-out-cross-validation. Models were implemented using the randomForest package within R. Classifier accuracy during the 24h free living trial was evaluated by calculating agreement with concurrently worn activPAL monitors. Overall classification accuracy for the random forest algorithm was 92.7%. Recognition accuracy for sedentary, stationary+, walking, and running was 80.1%, 95.7%, 91.7%, and 93.7%, respectively for the laboratory protocol. Agreement with the activPAL data (stepping vs. non-stepping) during the 24h free-living trial was excellent and, on average, exceeded 90%. The ICC for stepping time was 0.92 (95% CI=0.75–0.97). However, sensitivity and positive predictive values were modest. Mean bias was 10.3min/d (95% LOA=−46.0 to 25.4min/d). The random forest classifier for wrist accelerometer data yielded accurate group-level predictions under controlled conditions, but was less accurate at identifying stepping verse non-stepping behaviour in free living conditions Future studies should conduct more rigorous field-based evaluations using observation as a criterion measure.

Background Establishing healthy eating behaviours in early life has implications for health over the life course. As the majority of Australian children aged five and under regularly attend early childhood education and care (ECEC) services, mealtimes at ECEC settings present opportunities to promote healthy eating behaviors. The purpose of this study was to explore children’s eating behaviours and interactions between peers and educators during mealtimes in ECEC settings, with the aim of constructing a grounded theory of children’s mealtimes in ECEC. Methods In-depth qualitative case studies were undertaken at two ECEC centres. Each centre had been assessed as meeting national quality standards and were located in a lower socioeconomic status area. Data collection consisted of direct observation, video recording, written memos, and daily field notes. The analysis included open coding of video recorded mealtimes and field notes resulting in the allocation of initial codes and focused codes. Codes were grouped to form thematic categories and emergent themes. Theoretical sampling was used to identify mealtime interactions exemplifying thematic categories. Results Data from 47 mealtimes was available. A grounded theory of children’s mealtimes was developed to demonstrate children’s outcomes at mealtimes. Outcomes were represented by five thematic categories: rituals, learning moments, food preference development, socialisation and child agency. Mealtimes offered opportunities for children to construct a community of peers with their educators by sharing information, stories and occasionally their food. Each centre established its own unique culture within mealtimes observed as the children were involved in routines and rituals. Conclusions Mealtimes in ECEC settings are a unique cultural phenomenon co-constructed by the ECEC community of children and educators. The findings highlight the importance of mealtimes as a time for learning and socialization. The routine and rituals of mealtimes provide an opportunity for educators to support the development of healthy food preferences.

Background Little is known about the influence of parental attributes and parental screen time behaviours on pre-schooler’s screen time and weight status in low-to-middle income countries. The purpose of this study was to examine the relationships between parental screen time, parental self-efficacy to limit screen time, child screen time and child BMI in preschool-aged children in Brazil. Methods Three hundred eighteen parent-child dyads from Caruaru, Brazil completed a survey measuring sociodemographic data, weekday and weekend screen time, and parental self-efficacy for limiting screen time. Height and weight were measured and used to derive BMI and BMI percentile. Observed variable path analysis was used to evaluate the relationships between the parental and child variables. Results Analyses were conducted for screen time on weekdays and weekend days. Parental screen time was positively associated with child screen time, either directly (weekdays = β = 0.27, p  < 0.001, weekends = β = 0.24, p  < 0.001) or indirectly through reduced self-efficacy to limit child screen time (weekdays = β = − 0.15, p  = 0.004, weekends = β = − 0.16, p  = 0.004). After controlling for household income, parental occupation, and parental BMI, greater child screen time on weekends, not weekdays, was associated with higher child BMI percentile (β = 0.15, p  = 0.006). Conclusions Parental screen time and self-efficacy to limit screen time are important influences on child screen time and weight status in pre-schoolers from Brazil. Reducing parental screen time and increasing parental confidence to limit screen time may be effective strategy to prevent overweight in Brazilian pre-schoolers.

Introduction Regular physical activity is important for children’s physical and mental health, yet many children do not achieve recommended amounts of physical activity. Dog ownership has been associated with increased physical activity in children, however, there have been no longitudinal studies examining this relationship. This study used data from the Play Spaces and Environments for Children’s Physical Activity (PLAYCE) cohort study to examine the longitudinal effects of dog ownership status on children’s movement behaviours. Methods Change in dog ownership from preschool (wave 1, age 2–5) to fulltime school (wave 2, age 5–7) was used as a natural experiment with four distinct dog ownership groups: continuing non-dog owners ( n  = 307), continuing dog owners ( n  = 204), dog acquired ( n  = 58), and dog loss ( n  = 31; total n  = 600). Daily movement behaviours, including physical activity, sedentary time, sleep, and screen time, were measured using accelerometry and parent-report surveys. Differences between groups over time and by sex were tested using linear mixed effects regression models. Results Girls who acquired a dog increased their light intensity activities and games by 52.0 min/day (95%CI 7.9, 96.0) and girls who lost a dog decreased their light intensity activities and games by 62.1 min/day (95%CI -119.3, -4.9) compared to no change among non-dog owners. Girls and boys who acquired a dog increased their unstructured physical activity by 6.8 (95%CI 3.2, 10.3) and 7.1 (95%CI 3.9, 10.3) occasions/week, compared to no changes among non-dog owners. Girls and boys who lost a dog reduced their unstructured physical activity by 10.2 (95%CI -15.0, -5.3) and 7.7 (95%CI -12.0, -3.5) occasions/week. Girls who lost a dog decreased their total physical activity by 46.3 min/day (95%CI -107.5, 14.8) compared to no change among non-dog owners. Continuing dog ownership was typically not associated with movement behaviours. Dog ownership group was not associated with changes in sleep and had mixed associations with screen time. Conclusion The positive influence of dog ownership on children’s physical activity begins in early childhood and differs by child sex. Further research should examine the specific contributions dog-facilitated physical activity makes to children’s overall physical activity, including the intensity and duration of dog walking and play.