Related Experiment Video
Updated: Dec 24, 2025
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
Prediction of Resting Energy Expenditure in Children: May Artificial Neural Networks Improve Our Accuracy?
Valentina De Cosmi1,2, Alessandra Mazzocchi2, Gregorio Paolo Milani2,3
1Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Pediatric Intermediate Care Unit, 20122, Milan, Italy.
Insights
Artificial neural networks (ANNs) improve resting energy expenditure (REE) prediction in children. This novel approach offers better insights into caloric needs and weight management for pediatric populations.
Area of Science:
- Pediatric Nutrition
- Computational Biology
- Metabolic Research
Background:
- Resting energy expenditure (REE) prediction formulas often inaccurately estimate children's energy metabolism.
- Inaccurate estimations can lead to clinical consequences due to under- or overestimation of caloric needs.
- Obesity in children presents unique challenges for accurate energy expenditure assessment.
Purpose of the Study:
- To evaluate the efficacy of artificial neural networks (ANNs) for predicting REE in children.
- To compare ANNs performance against traditional REE prediction formulas.
- To assess the utility of ANNs in managing energy requirements and weight in pediatric populations.
Main Methods:
- Utilized artificial neural networks (ANNs) incorporating anthropometric data for REE modeling.
- Measured REE in 561 healthy children (ages 2-17) using indirect calorimetry.
- Compared ANNs predictions with established formulas (WHO, Harris-Benedict, Schofield, Oxford).
Main Results:
- ANNs demonstrated a mean absolute prediction error of 95.8 ± 80.8, strongly correlated with REE (R² = 0.88).
- ANNs exhibited superior performance in obese children, with a lower imprecision rate of 5.4%.
- The ANNs approach showed higher accuracy compared to traditional prediction methods.
Conclusions:
- Artificial neural networks offer a more precise method for estimating REE in children.
- ANNs provide valuable data for optimizing energy requirements and weight management strategies in pediatrics.
- This computational approach holds promise for improving clinical outcomes in pediatric metabolic assessment.
Abstract:
The inaccuracy of resting energy expenditure (REE) prediction formulae to calculate energy metabolism in children may lead to either under- or overestimated real caloric needs with clinical consequences. The aim of this paper was to apply artificial neural networks algorithms (ANNs) to REE prediction. We enrolled 561 healthy children (2-17 years). Nutritional status was classified according to World Health Organization (WHO) criteria, and 113 were obese. REE was measured using indirect calorimetry and estimated with WHO, Harris-Benedict, Schofield, and Oxford formulae. The ANNs considered specific anthropometric data to model REE. The mean absolute error (mean ± SD) of the prediction was 95.8 ± 80.8 and was strongly correlated with REE values (R2 = 0.88). The performance of ANNs was higher in the subgroup of obese children (101 ± 91.8) with a lower grade of imprecision (5.4%). ANNs as a novel approach may give valuable information regarding energy requirements and weight management in children.
