Use of Artificial Intelligence in obtaining canine diets: nutritional inadequacy and the need for technical knowledge.
AI-generated dog diets show significant nutritional inadequacies and require expert oversight to ensure safety and adequacy.
Where it sits
this study against the rest of the melanotan 1 corpusSummary and findings
This study assessed the nutritional adequacy of dog diets formulated by four AI models against European Pet Food Industry Federation recommendations. It found that 61.3% of nutrients were below minimum recommended levels. The study concluded that AI-generated diets are insufficient without expert supervision.
Abstract
This study evaluated the nutritional adequacy of dog diets formulated by four widely used Artificial Intelligence models (Manus, ChatGPT, DeepSeek, and Gemini) against the recommendations of the European Pet Food Industry Federation. This was a theoretical, in silico study, no animals were fed or clinically evaluated. Using a standardized prompt, complete and balanced diets (beef and chicken) for an 8 kg adult dog were requested. Eleven formulations were analyzed using SuperCracPet® software based on United States Department of Agriculture data. Overall, 61.3% of nutrients were below the minimum recommended levels. Nutrient levels below FEDIAF minimum requirements were identified across multiple categories: energy supply was insufficient in 81% of diets, calcium levels were below recommendations in 91% of formulations, calcium-to-phosphorus ratios were outside the recommended range in 63% of diets, chlorine was absent in all formulations, vitamin D levels were below requirements in 63.7% of diets, choline in 81.8%, and linoleic acid in 72%. Only 18% of the formulations included supplementation, which was provided in insufficient quantity. If implemented chronically, these nutritional inadequacies may pose risks to bone, dermatological, immune, and metabolic health. It is concluded that, in their current form, the evaluated language models are insufficient for the autonomous formulation of canine diets, as the generated prescriptions presented multiple nutritional inadequacies. Safe application requires hybrid systems with mandatory supervision by animal scientists and veterinarians, as well as regulation to prevent avoidable risks to animal health.
Background
The study addresses the capability of AI models to formulate nutritionally adequate diets for dogs, which is a growing area of interest as AI technology becomes more integrated into various fields. Prior to this study, there was limited evidence on the effectiveness of AI in diet formulation for pets, highlighting a gap in knowledge regarding the reliability of AI-generated nutritional plans.
Methods
This was a theoretical, in silico study using four AI models: Manus, ChatGPT, DeepSeek, and Gemini. Diets for an 8 kg adult dog were formulated based on standardized prompts. Eleven formulations were analyzed using SuperCracPet® software, which relies on USDA data. The primary outcome was the nutritional adequacy compared to FEDIAF recommendations.
Results
The study found that 61.3% of nutrients in the AI-generated diets were below the minimum recommended levels. Specifically, energy supply was insufficient in 81% of diets, calcium was below recommendations in 91% of formulations, and chlorine was absent in all diets. Additionally, vitamin D and choline levels were below requirements in 63.7% and 81.8% of diets, respectively.
Interpretation
The findings suggest that current AI models are not reliable for independently formulating nutritionally adequate canine diets. While the study highlights significant deficiencies, it is limited by its theoretical nature and lack of clinical validation. The results underscore the need for expert oversight and regulation in using AI for diet formulation to prevent potential health risks.
Key findings
- 61.3% of nutrients were below minimum recommended levels.
- Energy supply was insufficient in 81% of diets.
- Calcium levels were below recommendations in 91% of formulations.
- Chlorine was absent in all formulations.
- Vitamin D levels were below requirements in 63.7% of diets.
Limitations
- In silico study, no clinical evaluation.
- Theoretical findings based on software analysis.
- No animal feeding trials conducted.
- Lack of real-world validation.