Artificial Intelligence Applications to Personalized Dietary Recommendations: A Systematic Review.

Area of Science:

• Precision Medicine
• Computational Biology
• Nutritional Science

Background:

• Personalized dietary recommendations are crucial for managing chronic conditions like diabetes and irritable bowel syndrome (IBS).
• Traditional dietary approaches often fail to address individual metabolic variations.
• Artificial intelligence (AI) offers a novel approach to tailor dietary interventions.

Purpose of the Study:

• To systematically review the effectiveness of AI-generated dietary interventions in improving clinical outcomes in adults.
• To evaluate the impact of AI on metabolic health, glycemic control, and psychological well-being.

Main Methods:

• A systematic review following PRISMA guidelines was conducted across six databases.
• Studies published between November 2015 and September 2024 involving adults (18-91 years) receiving AI dietary recommendations were included.
• Included study designs were randomized controlled trials (RCTs), pre-post studies, and cross-sectional analyses, with evidence quality assessed using the GRADE system.

Main Results:

• Eleven studies (five RCTs, five pre-post, one cross-sectional) met the criteria, primarily utilizing machine learning (ML) and deep learning (DL) algorithms.
• AI interventions demonstrated significant improvements in glycemic control, metabolic health, and psychological well-being.
• Key outcomes included a 39% reduction in IBS symptom severity and a 72.7% diabetes remission rate, with most comparative studies showing AI group superiority.

Conclusions:

• AI-generated dietary interventions show significant promise over traditional methods by providing personalized, data-driven nutritional advice.
• Further research is warranted to confirm long-term efficacy, optimize intervention strategies, and improve patient adherence.
• AI holds potential for advancing chronic disease management in both clinical and public health settings.