Skip to Main content Skip to Navigation
Journal articles

Energy Intake Evaluation by a Learning Approach Using the Number of Food Portions and Body Weight

Abstract : An accurate quantification of energy intake is critical; however, under-reporting is frequent. The aim of this study was to develop an indirect statistical method of the total energy intake estimation based on gender, weight, and the number of portions. The energy intake prediction was developed and evaluated for validity using energy expenditure. Subjects with various BMIs were recruited and assigned either in the training or the test group. The mean energy provided by a portion was evaluated by linear regression models from the training group. The absolute values of the error between the energy intake estimation and the energy expenditure measurement were calculated for each subject, by subgroup and for the whole group. The performance of the models was determined using the test dataset. As the number of portions is the only variable used in the model, the error was 26.5%. After adding body weight in the model, the error decreased to 8.8% and 10.8% for the normal-weight women and men, respectively, and 11.7% and 12.8% for the overweight women and men, respectively. The results prove that a statistical approach and knowledge of the usual number of portions and body weight is effective and sufficient to obtain a precise evaluation of energy intake after a simple and brief enquiry.
Document type :
Journal articles
Complete list of metadata
Contributor : Sylvie Rousset Connect in order to contact the contributor
Submitted on : Wednesday, November 17, 2021 - 3:10:05 PM
Last modification on : Sunday, June 26, 2022 - 3:19:50 AM


Distributed under a Creative Commons Attribution 4.0 International License



Sylvie Rousset, Sébastien Médard, Gérard Fleury, Anthony Fardet, Olivier Goutet, et al.. Energy Intake Evaluation by a Learning Approach Using the Number of Food Portions and Body Weight. Foods, MDPI, 2021, 10 (10), ⟨10.3390/foods10102273⟩. ⟨hal-03432960⟩



Record views


Files downloads