Predicting carbohydrate quality in a global database of packaged foods

BackgroundCarbohydrates are the major contributor to the energy intake of worldwide population. There is established evidence of links of carbohydrate quality with human health. Knowledge of specific carbohydrate in packaged food, such as added and free sugars, could help further investigate this li...

Full description

Saved in:
Bibliographic Details
Main Authors: Eric Antoine Scuccimarra, Alexandre Arnaud, Marie Tassy, Kim-Anne Lê, Fabio Mainardi
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Nutrition
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnut.2025.1530846/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037579884265472
author Eric Antoine Scuccimarra
Alexandre Arnaud
Marie Tassy
Marie Tassy
Kim-Anne Lê
Fabio Mainardi
author_facet Eric Antoine Scuccimarra
Alexandre Arnaud
Marie Tassy
Marie Tassy
Kim-Anne Lê
Fabio Mainardi
author_sort Eric Antoine Scuccimarra
collection DOAJ
description BackgroundCarbohydrates are the major contributor to the energy intake of worldwide population. There is established evidence of links of carbohydrate quality with human health. Knowledge of specific carbohydrate in packaged food, such as added and free sugars, could help further investigate this link, however this information is generally not available.ObjectiveTo develop an algorithm to predict the content of free sugars in a global database of packaged foods and beverages; and test the applicability of the algorithm to assess carbohydrate quality in packaged food products from different countries and monitor the evolution over time. Carbohydrate quality was defined using a 10:1|1:2 ratio for carbohydrate, fibers and free sugar, i.e., for every 10 g of total carbohydrates in a diet or product, there is at least 1 g of dietary fibers, and less than 2 g of free sugars for every 1 g of dietary fibers.MethodsWe used a machine learning approach to predict added and free sugars, which enabled us to predict the carbohydrate quality of products from a global database of packaged food. Our predictions were tested by splitting the dataset into training, validation, and test sets, using US data.ResultsWe were able to predict free sugars and carbohydrate quality for 424,543 products in the U.S. and in 14 countries. The overall mean absolute error on the test set was 0.96 g/100 g of product. The predictions generalized with a high accuracy to non-US countries, and we were able to effectively predict the proportion of products meeting the 10:1|1:2 criteria in the food supply of 15 countries.ConclusionOur methodology achieved high accuracy and is fully automated; it may be applied to other databases of packaged products and can be easily applied for continuous monitoring of the carbohydrate quality of the global supply of packaged food.
format Article
id doaj-art-6ff9201d1dc74665bcdb75a593e0ce96
institution DOAJ
issn 2296-861X
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Nutrition
spelling doaj-art-6ff9201d1dc74665bcdb75a593e0ce962025-08-20T02:56:50ZengFrontiers Media S.A.Frontiers in Nutrition2296-861X2025-03-011210.3389/fnut.2025.15308461530846Predicting carbohydrate quality in a global database of packaged foodsEric Antoine Scuccimarra0Alexandre Arnaud1Marie Tassy2Marie Tassy3Kim-Anne Lê4Fabio Mainardi5Nestlé Institute of Health Sciences, Nestlé Research, Société des Produits Nestlé, Lausanne, SwitzerlandNestlé Institute of Health Sciences, Nestlé Research, Société des Produits Nestlé, Lausanne, SwitzerlandNestlé Institute of Health Sciences, Nestlé Research, Société des Produits Nestlé, Lausanne, SwitzerlandDivision of Human Nutrition and Health, Wageningen University & Research, Wageningen, NetherlandsNestlé Institute of Health Sciences, Nestlé Research, Société des Produits Nestlé, Lausanne, SwitzerlandNestlé Institute of Health Sciences, Nestlé Research, Société des Produits Nestlé, Lausanne, SwitzerlandBackgroundCarbohydrates are the major contributor to the energy intake of worldwide population. There is established evidence of links of carbohydrate quality with human health. Knowledge of specific carbohydrate in packaged food, such as added and free sugars, could help further investigate this link, however this information is generally not available.ObjectiveTo develop an algorithm to predict the content of free sugars in a global database of packaged foods and beverages; and test the applicability of the algorithm to assess carbohydrate quality in packaged food products from different countries and monitor the evolution over time. Carbohydrate quality was defined using a 10:1|1:2 ratio for carbohydrate, fibers and free sugar, i.e., for every 10 g of total carbohydrates in a diet or product, there is at least 1 g of dietary fibers, and less than 2 g of free sugars for every 1 g of dietary fibers.MethodsWe used a machine learning approach to predict added and free sugars, which enabled us to predict the carbohydrate quality of products from a global database of packaged food. Our predictions were tested by splitting the dataset into training, validation, and test sets, using US data.ResultsWe were able to predict free sugars and carbohydrate quality for 424,543 products in the U.S. and in 14 countries. The overall mean absolute error on the test set was 0.96 g/100 g of product. The predictions generalized with a high accuracy to non-US countries, and we were able to effectively predict the proportion of products meeting the 10:1|1:2 criteria in the food supply of 15 countries.ConclusionOur methodology achieved high accuracy and is fully automated; it may be applied to other databases of packaged products and can be easily applied for continuous monitoring of the carbohydrate quality of the global supply of packaged food.https://www.frontiersin.org/articles/10.3389/fnut.2025.1530846/fullfood supplyfree sugarmissing value imputationcarbohydrate qualitymachine learningadded sugar
spellingShingle Eric Antoine Scuccimarra
Alexandre Arnaud
Marie Tassy
Marie Tassy
Kim-Anne Lê
Fabio Mainardi
Predicting carbohydrate quality in a global database of packaged foods
Frontiers in Nutrition
food supply
free sugar
missing value imputation
carbohydrate quality
machine learning
added sugar
title Predicting carbohydrate quality in a global database of packaged foods
title_full Predicting carbohydrate quality in a global database of packaged foods
title_fullStr Predicting carbohydrate quality in a global database of packaged foods
title_full_unstemmed Predicting carbohydrate quality in a global database of packaged foods
title_short Predicting carbohydrate quality in a global database of packaged foods
title_sort predicting carbohydrate quality in a global database of packaged foods
topic food supply
free sugar
missing value imputation
carbohydrate quality
machine learning
added sugar
url https://www.frontiersin.org/articles/10.3389/fnut.2025.1530846/full
work_keys_str_mv AT ericantoinescuccimarra predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods
AT alexandrearnaud predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods
AT marietassy predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods
AT marietassy predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods
AT kimannele predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods
AT fabiomainardi predictingcarbohydratequalityinaglobaldatabaseofpackagedfoods