Prediction of energy expenditure and physical activity in preschoolers

Abstract

Purpose: Accurate, nonintrusive, and feasible methods are needed to predict energy expenditure (EE) and physical activity (PA) levels in preschoolers. Herein, we validated cross-sectional time series (CSTS) and multivariate adaptive regression splines (MARS) models based on accelerometry and heart rate (HR) for the prediction of EE using room calorimetry and doubly labeled water (DLW) and established accelerometry cut points for PA levels.

Methods: Fifty preschoolers, mean ± SD age of 4.5 ± 0.8 yr, participated in room calorimetry for minute-by-minute measurements of EE, accelerometer counts (AC) (Actiheart and ActiGraph GT3X+), and HR (Actiheart). Free-living 105 children, ages 4.6 ± 0.9 yr, completed the 7-d DLW procedure while wearing the devices. AC cut points for PA levels were established using smoothing splines and receiver operating characteristic curves.

Results: On the basis of calorimetry, mean percent errors for EE were -2.9% ± 10.8% and -1.1% ± 7.4% for CSTS models and -1.9% ± 9.6% and 1.3% ± 8.1% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. On the basis of DLW, mean percent errors were -0.5% ± 9.7% and 4.1% ± 8.5% for CSTS models and 3.2% ± 10.1% and 7.5% ± 10.0% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. Applying activity EE thresholds, final accelerometer cut points were determined: 41, 449, and 1297 cpm for Actiheart x-axis; 820, 3908, and 6112 cpm for ActiGraph vector magnitude; and 240, 2120, and 4450 cpm for ActiGraph x-axis for sedentary/light, light/moderate, and moderate/vigorous PA (MVPA), respectively. On the basis of confusion matrices, correctly classified rates were 81%-83% for sedentary PA, 58%-64% for light PA, and 62%-73% for MVPA.

Conclusions: The lack of bias and acceptable limits of agreement affirms the validity of the CSTS and MARS models for the prediction of EE in preschool-aged children. Accelerometer cut points are satisfactory for the classification of sedentary, light, and moderate/vigorous levels of PA in preschoolers.

Figure 1

A Bland-Altman plots evaluating the prediction of energy expenditure by cross-sectional time series models (CSTS) and multivariate adaptive regression splines (MARS) models using Actiheart and ActiGraph devices versus energy expenditure measured by room respiration calorimetry (n=50). The mean difference between measured EE and predicted EE is plotted against the mean of the two methods; the mean bias is shown by a solid line and the 95% limits of agreement are shown by dash lines. B Bland-Altman plots evaluating the prediction of total energy expenditure (TEE) by cross-sectional time series models (CSTS) and multivariate adaptive regression splines (MARS) models using Actiheart and ActiGraph devices versus TEE measured by doubly labeled water (DLW) method (n=105). The mean difference between measured TEE and predicted TEE is plotted against the mean of the two methods; the mean bias is shown by a solid line and the 95% limits of agreement are shown by dash lines.

Figure 2

Smoothing splines curve fitting used to define activity energy expenditure (AEE) levels for sedentary, light, moderate and vigorous physical activity in preschool-aged children from heart rate thresholds (A); smoothing splines curve fitting applied to the AEE and accelerometer counts to identify accelerometer cut-points for Actiheart x-axis (B), ActiGraph vector magnitude (C), and ActiGraph x-axis (D).