Dataset Information

Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: A free-living evaluation.

ABSTRACT: PURPOSE: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. METHODS: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. RESULTS: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. CONCLUSION:Machine learning EE prediction models trained on LAB and FL data had similar accuracy under free-living conditions.

SUBMITTER: Ahmadi MN

PROVIDER: S-EPMC7239487 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: A free-living evaluation.

Ahmadi Matthew N MN Chowdhury Alok A Pavey Toby T Trost Stewart G SG

PloS one 20200520 5

<h4>Purpose</h4>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.<h4>Methods</h4>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 ...[more]

PMID: 32433717

Similar Datasets

Project description:BackgroundDespite growing scientific interest in the benefits of breaking up sedentary time with intermittent standing or walking, few studies have investigated the energy cost of posture transitions. This study aimed to determine whether posture transitions are associated with increased energy expenditure in preschool children.MethodsForty children (mean age 5.3 ± 1.0y) completed a ~150-min room calorimeter protocol involving sedentary, light, and moderate- to vigorous-intensity activities. This study utilised data from ~65-min of the protocol, during which children were undertaking sedentary behaviours (TV viewing, drawing/colouring in, and playing with toys on the floor). Posture was coded as sit/lie, stand, walk, or other using direct observation; posture transitions were classified as sit/lie to stand/walk, sit/lie to other, stand/walk to other, or vice versa. Energy expenditure was calculated using the Weir equation and used to calculate individualised MET and activity energy expenditure (AEE) values. Spearman's rank correlations were used to compare the number of posture transitions, in the individual activities separately and combined, with corresponding MET and AEE values. Participants were divided into tertiles based on the number of posture transitions; MET and AEE values of children in the lowest and highest tertiles of posture transitions were compared using unpaired t-tests. Effect sizes (Cohen's d) were calculated.ResultsThere was a positive correlation between the total number of posture transitions and average METs (rs = 0.42, p = 0.02) and AEE (rs = 0.43, p = 0.02). MET differences between the lowest and highest tertiles of posture transitions resulted in a small effect size for playing with toys (d = 0.27), and moderate effect sizes for TV viewing, drawing and all three activities combined (d = 0.61, 0.50 and 0.64 respectively). Similar results were found for AEE.ConclusionsResults from this study showed that variation in posture transitions may be associated with variation in energy expenditure in preschool children. The findings suggest that the concept that variation in posture transitions may have meaningful biological or health effects in early childhood is worth investigating further.

Dataset Information

Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: A free-living evaluation.

Publications

Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: A free-living evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets