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 Experiment Video

Updated: Jun 14, 2026

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

Comparative Performance of Machine Learning Models Using Food Intake Frequency Versus Vegetable Intake Data to

Naoki Sakane1, Yaeko Kawaguchi1, Junichiro Somei1

  • 1Division of Preventive Medicine, Clinical Research Institute, National Hospital Organisation NHO Kyoto Medical Centre, Kyoto, Japan.

Journal of Mother and Child
|June 12, 2026
PubMed
Summary

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

Short-form measures of hypoglycemia problem-solving ability: the Hypoglycemia Problem-Solving Scale (HPSS)-5 and HPSS-1, a post-hoc analysis of the PR-IAH study.

Diabetology international·2026
Same author

Type 1 diabetes-specific distress among adults with type 1 diabetes in Japan.

Journal of diabetes investigation·2026
Same author

Data-driven cluster analysis of adults with prediabetes: Findings from the Japan diabetes prevention study.

Journal of diabetes investigation·2026
Same author

Selective Eating Behavior and Delayed Bedtime in Children Aged 3-6 Years: The Mediating Role of Breakfast Tryptophan Intake.

Journal of nutritional science and vitaminology·2026
Same author

Hypoglycemia problem-solving ability as a key predictor of severe hypoglycemia: a machine learning approach in adults with type 1 diabetes.

Diabetology international·2026
Same author

A machine learning approach to predicting severe diabetes distress in adults with type 1 diabetes mellitus.

Journal of diabetes investigation·2026
This summary is machine-generated.

Machine learning models using vegetable intake data are more effective than food frequency questionnaires for identifying selective eating in children. Early detection through detailed dietary assessment is crucial.

Area of Science:

  • Pediatric Nutrition
  • Computational Health
  • Behavioral Science

Background:

  • Selective eating in children can cause nutritional imbalances and mealtime stress.
  • Early identification of selective eating is essential for intervention.

Purpose of the Study:

  • To compare the predictive performance of machine learning (ML) models for identifying selective eating in children.
  • To evaluate models using vegetable intake data versus food frequency questionnaire (FFQ) responses.

Main Methods:

  • Analysis of a cross-sectional dataset of 283 children aged 3-6 years.
  • Training and evaluation of eleven ML algorithms with 11,253 feature-model combinations.
  • Performance assessment using 5-fold cross-validation (accuracy, precision, recall, F1, ROC-AUC) and permutation importance analysis.
Keywords:
foodmachine learningmachine performancemealtime behaviourpreschool childrenvegetable

More Related Videos

Control of Eating Behavior Using a Novel Feedback System
04:48

Control of Eating Behavior Using a Novel Feedback System

Published on: May 8, 2018

Related Experiment Videos

Last Updated: Jun 14, 2026

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

Control of Eating Behavior Using a Novel Feedback System
04:48

Control of Eating Behavior Using a Novel Feedback System

Published on: May 8, 2018

Main Results:

  • The L1 logistic regression model using vegetable intake data achieved the highest performance (ROC-AUC = 0.717, accuracy = 0.647).
  • Key predictors identified included tomato, green onion, and taro intake.
  • FFQ-based Naïve Bayes model showed moderate discrimination (ROC-AUC = 0.619).

Conclusions:

  • ML models based on vegetable intake data demonstrated superior effectiveness in detecting selective eating.
  • Detailed dietary assessments are valuable for the early detection of selective eating behaviors.