Artificial intelligence in functional food innovation: Bioactive enhancement and formulation optimization: A...

Area of Science:

• Food Science
• Computational Biology
• Nutritional Science

Background:

• Artificial intelligence (AI) is increasingly utilized in functional food research.
• A quasi-systematic review of 53 studies (2015-2025) was conducted to analyze AI applications.
• The review focuses on AI's role in antioxidant food development, compound discovery, metabolomics, and consumer modeling.

Purpose of the Study:

• To synthesize current AI applications in functional food research.
• To identify emerging directions and knowledge gaps, particularly in antioxidant food development.
• To emphasize opportunities for methodological integration of AI in food science.

Main Methods:

• Analysis of 53 peer-reviewed studies from 2015-2025.
• Categorization of AI approaches including data-driven AI (classical machine learning) and deep learning.
• Examination of AI applications in predicting antioxidant activity, identifying bioactive compounds, metabolomic data analysis, and consumer modeling.

Main Results:

• AI methods successfully predict antioxidant activity and identify bioactive compounds.
• Machine learning aids in clustering metabolomic data and optimizing food attributes.
• Current AI findings are predominantly computational (in silico) with limited experimental validation.
• Consumer modeling is largely predictive and lacks ethical/regulatory integration.

Conclusions:

• AI shows significant potential in advancing functional food research, especially for antioxidant development.
• There is a critical need for experimental and clinical validation of AI-driven predictions.
• Enhanced collaboration between food and data scientists is crucial for translating AI insights into real-world applications.