Development of an AI-Driven Computational Framework for Integrated Dietary Pattern Assessment: A Simulation-Based...

Area of Science:

• Computational nutrition and environmental sustainability science.
• Development of artificial intelligence (AI) models for dietary assessment.
• Interdisciplinary research integrating food systems, public health, and environmental science.

Background:

• Conventional dietary assessments fail to integrate nutritional adequacy with environmental sustainability and economic factors.
• Food systems require methodologies that balance nutritional needs with resource conservation.
• A gap exists in computational tools for holistic dietary pattern evaluation.

Purpose of the Study:

• To develop and validate an AI-driven computational framework for integrated dietary assessment.
• To synthesize nutritional evaluation, environmental footprint quantification, and economic accessibility.
• To benchmark dietary patterns against sustainability thresholds and epidemiological data.

Main Methods:

• Simulation-based proof-of-concept study using a cohort of 1500 individuals.
• Integration of random forest classification, dimensionality reduction, and scenario-based optimization.
• Analysis of 55 foods across eight categories, incorporating greenhouse gas emissions, water use, and price data.

Main Results:

• AI framework achieved 39.1% classification accuracy, with cost, emissions, and water use as key discriminators.
• Dietary patterns showed similar macronutrient profiles but widespread calcium inadequacy.
• Scenario modeling identified flexible diets reducing water use by 13% with minimal cost increases.
• AI-driven assessment highlighted substantial energy intake deviations when prioritizing nutritional adequacy.

Conclusions:

• The developed AI framework provides a validated computational infrastructure for integrated dietary assessment.
• Demonstrates the feasibility of AI in evaluating dietary patterns across nutritional, environmental, and economic dimensions.
• Highlights the potential for optimizing food systems towards sustainability and improved public health outcomes.