Related Experiment Video
Updated: Jun 6, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.0K
Translational Algorithms for Technological Dietary Quality Assessment Integrating Nutrimetabolic Data with Machine
Víctor de la O1,2, Edwin Fernández-Cruz1,2, Pilar Matía Matin3,4
1Cardiometabolic Nutrition Group, Precision Nutrition Program, Research Institute on Food and Health Sciences IMDEA Food, Consejo Superior de Investigaciones Científicas-Universidad Autónoma de Madrid (CSIC-UAM), 28049 Madrid, Spain.
Nutrients
|November 27, 2024
Summary
Machine learning algorithms effectively predict dietary patterns using biochemical markers, distinguishing between pro-Mediterranean and pro-Western diets. This advances personalized nutrition assessment.
Area of Science:
- Biochemistry
- Nutritional Science
- Computational Biology
Background:
- Dietary assessment is evolving with machine learning (ML) and omics data.
- Biomarkers are key for personalized precision nutrition.
- AI tools can analyze biomarkers to understand food intake and dietary patterns.
Purpose of the Study:
- To evaluate AI and ML in analyzing biomarkers for dietary assessment.
- To characterize food and nutrient intake using biomarkers.
- To predict dietary patterns through biomarker analysis.
Main Methods:
- Analysis of data from 138 subjects including examinations, questionnaires, and blood samples.
- Dietary clustering based on 72-hour recall, sex, age, and BMI.
- Exploratory factor analysis and elastic net regression to identify biomarkers and construct algorithms.
Main Results:
- Two dietary patterns identified: pro-Mediterranean (pro-MP) and pro-Western (pro-WP).
- Biochemical markers related to lipid metabolism, liver function, and metabolic factors distinguished patterns.
- Three algorithms developed for predicting pro-WP pattern classification, with a supervised algorithm showing high predictive capability (ROC=0.91, PRC=0.80).
Conclusions:
- Biochemical markers hold significant potential for predicting nutritional patterns.
- Algorithms can be developed to classify dietary clusters effectively.
- This research advances dietary intake assessment technologies through biomarker analysis.
