EUVIMEDEUVIMED entdecken
EvaluationsstudieOpen Access · CC BY 4.0

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

Bettina Hieronimus, Simon Hammann, Maren C Podszun

Nutrition Research · 2024-08 · 128 · 105-114

DOI: 10.1016/j.nutres.2024.07.002 ↗

Kurz gefasst

Evaluationsstudie in der Zeitschrift Nutrition Research, 2024-08. Verfasst von Bettina Hieronimus und 2 weiteren Autor:innen. Beteiligte Einrichtung: Max Rubner-Institut, Department of Physiology and Biochemistry of Nutrition, Karlsruhe, Germany. Hauptthemen laut MEDLINE: Artificial Intelligence, Energy Intake, Meals. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceEnergy IntakeMealsHumansDietary CarbohydratesDietary SupplementsNutrientsNutritive ValueRecommended Dietary Allowances

Stichwörter der Autor:innen

AI in health careArtificial intelligenceBardChatGPTDietary patternsDigital nutrition toolsMeal plans

Substanzen

Dietary CarbohydratesNutrients

Autor:innen und Institutionen

  • Max Rubner-Institut, Department of Physiology and Biochemistry of Nutrition, Karlsruhe, Germany.
  • Department of Chemistry and Pharmacy, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Department of Food Chemistry and Analytical Chemistry (170a), Institute of Food Chemistry, University of Hohenh…
  • Institute of Nutritional Science, Department of Food Biofunctionality, University of Hohenheim, Stuttgart, Germany. Electronic address: maren.podszun@uni-hohenheim.de.

Zitieren

APA

Hieronimus, B., Hammann, S., & Podszun, M. C. (2024). Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?. Nutrition Research, 128, 105-114. https://doi.org/10.1016/j.nutres.2024.07.002

Vancouver

Hieronimus B, Hammann S, Podszun MC. Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?. Nutrition Research. 2024;128:105-114. doi:10.1016/j.nutres.2024.07.002

BibTeX
@article{Hieronimus2024,
  author = {Hieronimus, Bettina and Hammann, Simon and Podszun, Maren C},
  title = {Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?},
  journal = {Nutrition Research},
  year = {2024},
  volume = {128},
  pages = {105--114},
  doi = {10.1016/j.nutres.2024.07.002}
}
Kostenlos starten →