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 12, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

Evaluating a Multitask Artificial Intelligence Model Compared With Humans for Portion-Size Estimation.

Bibinur Nurmanova1, Zhuldyz Omarova1, Aibota Sanatbyek2

  • 1School of Medicine, Nazarbayev University, Astana, Kazakhstan.

The Journal of Nutrition
|June 10, 2026
PubMed
Summary
This summary is machine-generated.

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

Application of Sensory Evaluation to Understand Fresh Apple Cultivar Acceptance in Kazakhstan.

Foods (Basel, Switzerland)·2026
Same author

Edge-Based Vision-Language Assistive System for the Visually Impaired: A Quantized VLM Approach.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Mixed Reality and Desktop Hand Hygiene Training With Deep Learning-Based Step Recognition and Real-Time Decision Support.

IEEE transactions on visualization and computer graphics·2026
Same author

High salt intake and bone health in postmenopausal women: exposing the lack of studies - a systematic review and meta-analysis.

Frontiers in endocrinology·2025
Same author

Benchmarking ChatGPT and Other Large Language Models for Personalized Stage-Specific Dietary Recommendations in Chronic Kidney Disease.

Journal of clinical medicine·2025
Same author

Hyperspectral Imaging for Quality Assessment of Processed Foods: A Case Study on Sugar Content in Apple Jam.

Foods (Basel, Switzerland)·2025
Same journal

Evaluation of Energy and Nutrient Estimates from Large Language Models Using Text-Based Queries.

The Journal of nutrition·2026
Same journal

Considerations for Dietary Supplements After GLP-1RA Treatment: A Narrative Review.

The Journal of nutrition·2026
Same journal

The apple(juice) doesn't fall far from the tree: Children's hydration mirrors their parent's.

The Journal of nutrition·2026
Same journal

Microbial-derived polyphenol metabolites and the gut microbiota: A scoping review of clinical studies.

The Journal of nutrition·2026
Same journal

Hesperidin as an Emerging Nutraceutical in Modern Health and Preventive Medicine: A Narrative Review.

The Journal of nutrition·2026
Same journal

Short-Chain Fatty Acids in Livestock and Aquatic Animals: Metabolic Divergence, Physiological Functions, and Product Development.

The Journal of nutrition·2026
See all related articles

Visual food atlases significantly improve portion size estimation compared to unassisted judgment or AI models in Central Asia. AI tools need further development for complex foods and small servings.

Area of Science:

  • Nutrition science
  • Artificial intelligence
  • Dietary assessment

Background:

  • Accurate dietary assessment is crucial for precision nutrition and surveillance.
  • Portion size estimation is challenging in Central Asia due to cultural eating habits and non-standard measures.
  • AI offers potential solutions for food recognition and portion estimation, but direct comparisons are limited.

Purpose of the Study:

  • To compare the accuracy of unassisted human judgment, visual food atlas assistance, and an AI model for portion size estimation.
  • To evaluate these methods using Central Asian food items.

Main Methods:

  • 128 participants in Astana, Kazakhstan, estimated portion sizes of 51 foods and 8 beverages from photographs.
  • Participants were randomized to unassisted or atlas-assisted estimation.
Keywords:
AI-driven nutritionCentral Asiaartificial intelligencedietary assessmentdigital healthhuman–AI performanceprecision nutritiontelemedicine

Related Experiment Videos

Last Updated: Jun 12, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

  • An AI model trained on Central Asian food images was evaluated against actual food weights (reference).
  • Accuracy was measured using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE).

    • Main Results:

    • Atlas-assisted estimation was most accurate (MAE 80.81g, MAPE 44.76%), while unassisted estimation was least accurate (MAE 133.86g, MAPE 79.40%).
    • The AI model performed intermediately (MAE 97.37g, MAPE 67.81%), with best performance for beverages and average portions.
    • AI accuracy varied by food category and portion size, showing higher errors for small or complex foods.

    Conclusions:

    • Visual atlas use significantly enhances portion size estimation accuracy.
    • The AI model requires further refinement for complex foods and small servings.
    • Combining visual aids and AI tools can improve region-specific dietary monitoring.