Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Discovery of potent low-toxicity antimicrobial peptides through diffusion modeling.

Nature communications·2026
Same author

Artificial intelligence for food innovation.

Nature food·2026
Same author

Association between dietary polyphenol intake and polyphenol-utilizing bacteria in healthy adults.

Food & function·2026
Same author

Artificial intelligence for plant-based meat alternatives: Pathways to a sustainable future.

Food research international (Ottawa, Ont.)·2026
Same author

Translating dietary standards into healthy meals with few-ingredient substitutions.

PLOS digital health·2026
Same author

Stool microbial composition is associated with recent and future diarrhea and fever events in breastfed Danish infants.

mSystems·2026

Related Experiment Video

Updated: Jan 1, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Nutrient Estimation from 24-Hour Food Recalls Using Machine Learning and Database Mapping: A Case Study with Lactose.

Elizabeth L Chin1,2, Gabriel Simmons3, Yasmine Y Bouzid1,4

  • 1Western Human Nutrition Research Center, USDA ARS, Davis, CA 95616, USA.

Nutrients
|December 19, 2019
PubMed
Summary

Automated Self-Administered 24-Hour Dietary Assessment Tool (ASA24) data can now estimate missing nutrients. Computational methods, particularly database matching, successfully estimated NCC-exclusive nutrients like lactose from ASA24 reports.

Keywords:
database matchingdietary recallmachine learningnutrient database

More Related Videos

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake
04:46

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake

Published on: September 18, 2018

7.7K
Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

11.1K

Related Experiment Videos

Last Updated: Jan 1, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake
04:46

'Boden Food Plate': Novel Interactive Web-based Method for the Assessment of Dietary Intake

Published on: September 18, 2018

7.7K
Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

11.1K

Area of Science:

  • Nutrition Science
  • Computational Biology
  • Data Science

Background:

  • The Automated Self-Administered 24-Hour Dietary Assessment Tool (ASA24) is a widely used, free dietary assessment system.
  • ASA24 provides fewer nutrients than the licensed Nutrition Data System for Research (NDSR), which utilizes the NCC Food and Nutrient Database.
  • Manual nutrient data transfer from ASA24 to NDSR is labor-intensive and the only current method for obtaining exclusive nutrients.

Purpose of the Study:

  • To evaluate computational methods for estimating NCC-exclusive nutrients from ASA24 data.
  • To compare machine learning and database matching approaches for nutrient estimation.
  • To assess the feasibility of automating the acquisition of exclusive nutrients.

Main Methods:

  • Developed nine machine learning models to predict lactose from shared nutrients between ASA24 and NCC databases.
  • Created database matching algorithms using nutrient-only or nutrient and text descriptions to link NCC foods to ASA24 foods.
  • Used manually curated lactose estimates from NDSR as the ground truth for training and testing computational models.

Main Results:

  • The XGB-Regressor machine learning model achieved an R-squared of 0.33 for predicting lactose.
  • Database matching using both nutrient and text descriptions (Nutrient + Text) yielded the best lactose estimates with an R-squared of 0.76.
  • Computational methods demonstrated significant improvement over the absence of estimates for NCC-exclusive nutrients.

Conclusions:

  • Computational approaches, especially database matching with text and nutrient data, can effectively estimate NCC-exclusive nutrients from ASA24 dietary reports.
  • These methods offer a viable alternative to time-consuming manual data lookup.
  • Automating nutrient estimation enhances the utility of ASA24 data for comprehensive nutritional analysis.