Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?

•First study to compare nutrients in meal plans created by ChatGPT and Bard.•Most meal plans fell below the requirements for energy exceeded them for protein and were below the requirements for vitamin D and fluoride.•ChatGPT occasionally recommended vitamin B12 supplementation for vegan meal plans....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nutrition research (New York, N.Y.) N.Y.), 2024-08, Vol.128, p.105-114
Hauptverfasser: Hieronimus, Bettina, Hammann, Simon, Podszun, Maren C.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•First study to compare nutrients in meal plans created by ChatGPT and Bard.•Most meal plans fell below the requirements for energy exceeded them for protein and were below the requirements for vitamin D and fluoride.•ChatGPT occasionally recommended vitamin B12 supplementation for vegan meal plans.•Bard included milk-based products in vegan diets.•Currently, ChatGPT offers a slight advantage over Bard in the generation of meal plans. Artificial intelligence chatbots based on large language models have recently emerged as an alternative to traditional online searches and are also entering the nutrition space. In this study, we wanted to investigate whether the artificial intelligence chatbots ChatGPT and Bard (now Gemini) can create meal plans that meet the dietary reference intake (DRI) for different dietary patterns. We further hypothesized that nutritional adequacy could be improved by modifying the prompts used. Meal plans were generated by 3 accounts for different dietary patterns (omnivorous, vegetarian, and vegan) using 2 distinct prompts resulting in 108 meal plans total. The nutrient content of the plans was subsequently analyzed and compared to the DRIs. On average, the meal plans contained less energy and carbohydrates but mostly exceeded the DRI for protein. Vitamin D and fluoride fell below the DRI for all plans, whereas only the vegan plans contained insufficient vitamin B12. ChatGPT suggested using vitamin B12 supplements in 5 of 18 instances, whereas Bard never recommended supplements. There were no significant differences between the prompts or the tools. Although the meal plans generated by ChatGPT and Bard met most DRIs, there were some exceptions, particularly for vegan diets. These tools maybe useful for individuals looking for general dietary inspiration, but they should not be relied on to create nutritionally adequate meal plans, especially for individuals with restrictive dietary needs. We compared the nutritional adequacy of meal plans generated by the artificial intelligence tools ChatGPT and Bard for omnivorous, vegetarian, and vegan meal plans. Although most plans exceeded protein requirements, they consistently fell short in energy and carbohydrate content. Deficiencies in vitamin D, fluoride, and vitamin B12 for vegan plans were noted. ChatGPT occasionally recommended vitamin B12 supplementation for vegans, whereas Bard did not. Bard further included milk-based products in the vegan plans. Overall, the analysis underscores st
ISSN:0271-5317
1879-0739
1879-0739
DOI:10.1016/j.nutres.2024.07.002