Nutritional analysis of AI-generated diet plans based on popular online diet trends

BAYRAM H. M., Arslan S.

Journal of Food Composition and Analysis, vol.145, 2025 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 145
  • Publication Date: 2025
  • Doi Number: 10.1016/j.jfca.2025.107850
  • Journal Name: Journal of Food Composition and Analysis
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Analytical Abstracts, BIOSIS, Biotechnology Research Abstracts, CAB Abstracts, Food Science & Technology Abstracts, Veterinary Science Database
  • Keywords: Artificial intelligence, Diet analysis, High protein diet, Low sodium diet, Popular diets, Raw diet, The Mediterranean diet, Vegetarian diet
  • Istanbul Gelisim University Affiliated: Yes

Abstract

This study aimed to evaluate the nutritional composition and consistency of 1500 kcal daily diet plans generated by four generative Artificial Intelligence (AI) tools (ChatGPT-4, ChatGPT-4o, Mistral, and Claude) based on five popular diet types identified via Google Trends (keto, paleo, Mediterranean, intermittent fasting, and raw). Each AI model was prompted with standardized requests, and the resulting menus were analyzed using Nutrition Information System (BeBIS) (version 9.0) to determine energy, macronutrient, and micronutrient content. Nutrient composition differences across AI tools were statistically assessed using SPSS 24.0 (ANOVA, p < 0.05). Results showed significant variations between AI outputs, with energy values ranging from 1357 kcal to 2273 kcal and protein intake varying by up to 65 g across models. Notable inconsistencies were also found in micronutrients such as calcium, iron, and vitamin D. AI models often failed to meet targeted caloric levels and showed inconsistent adherence to diet-specific nutrient profiles. These discrepancies suggest limitations not only in the AI tools’ capabilities but also in their interpretation of user prompts. The findings highlight the need for improved prompt design, database integration, and AI training for safe and reliable use in personalized nutrition.