Comparative analysis of AI on human nutrition knowledge: Evaluating large language model-based conversational agents against dietetics students and the general population
PLOS One · 08.12.2025 · 20 (12) · e0336577
DOI: 10.1371/journal.pone.0336577 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 08.12.2025. Verfasst von Nicola Luigi Bragazzi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Human Nutrition Unit, Department of Food and Drug, University of Parma, Parma, Italy. Hauptthemen laut MEDLINE: Artificial Intelligence, Dietetics, Health Knowledge, Attitudes, Practice, Language. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Recovery and Resilience Plan (NRRP), Italian Ministry of University and Research, European Union – NextGenerationEU.
Abstract (Originalsprache)
Understanding the core principles of nutrition is essential in the contemporary context of abundant and often contradictory dietary advice, to empower individuals to make informed dietary choices and manage diet-related non-communicable diseases. The role of Artificial Intelligence (AI) in providing nutritional information is increasingly prominent, but its reliability in this domain is not well-established yet. This study compares the nutrition knowledge of state-of-the-art Large Language Model (LLM)-based conversational agents and chatbots with that of human subjects having different levels of nutrition knowledge. The “General Nutrition Knowledge Questionnaire–Revised” (GNKQ-R) was administered to four LLMs (ChatGPT-3.5, ChatGPT-4, Google Bard, currently known as Google Gemini, and Microsoft Copilot), using zero-shot prompts. Responses were scored in accordance with the GNKQ-R’s guidelines. The average performance of AI systems across all LLMs was 77.3 ± 5.1 out of 88, comparable to that of dietetics students and significantly higher than English students. ChatGPT-4 scored highest among the LLMs (82/88), surpassing both groups of students (dietetics: 79.3/88, English: 67.7/88) as well as all other demographic groups. In “Dietary Recommendations”, ChatGPT-3.5 and ChatGPT-4 demonstrated comparable performance to dietetics students. ChatGPT-4 excelled in “Food Groups”, outperforming all human groups. In “Healthy Food Choices”, ChatGPT-4 achieved a perfect score, indicating a deep understanding of this subject. ChatGPT-3.5 excelled in “Diet, Disease and Weight Management”. Variations in the performances of the LLMs across different sections were observed, suggesting knowledge gaps in certain areas. Some of the tested LLMs, particularly ChatGPT-3.5 and ChatGPT-4, showed proficiency in nutrition knowledge, rivaling or even surpassing dietetics students in certain sections. This indicates their potential utility in nutritional guidance. However, this study also identified nuances and specific details where LLMs lack compared to specialized human education. The study highlights the potential of AI in public health and educational settings. However, LLMs may be limited in their capacity to generate personalized dietary advice that accounts for clinical complexity and individual variability, reinforcing the indispensable role of expert human judgment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Human Nutrition Unit, Department of Food and Drug, University of Parma, Parma, Italy.
- Department of Sciences and Method for Engineering, University of Modena and Reggio Emilia, Reggio Emilia, Italy.
- Department of Engineering for Industrial Systems and Technologies, University of Parma, Parma, Italy.
ORCID-Profile: Francesca Scazzina, Alice Rosi
Förderung
- National Recovery and Resilience Plan (NRRP)
- Italian Ministry of University and Research
- European Union – NextGenerationEU
- NextGenerationEU
Zitieren
APA
Bragazzi, N. L., Monica, S., Bergenti, F., Scazzina, F., & Rosi, A. (2025). Comparative analysis of AI on human nutrition knowledge: Evaluating large language model-based conversational agents against dietetics students and the general population. PLOS One, 20(12), e0336577. https://doi.org/10.1371/journal.pone.0336577
Vancouver
Bragazzi NL, Monica S, Bergenti F, Scazzina F, Rosi A. Comparative analysis of AI on human nutrition knowledge: Evaluating large language model-based conversational agents against dietetics students and the general population. PLOS One. 2025;20(12):e0336577. doi:10.1371/journal.pone.0336577
BibTeX
@article{Bragazzi2025,
author = {Bragazzi, Nicola Luigi and Monica, Stefania and Bergenti, Federico and Scazzina, Francesca and Rosi, Alice},
title = {Comparative analysis of AI on human nutrition knowledge: Evaluating large language model-based conversational agents against dietetics students and the general population},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {12},
pages = {e0336577},
doi = {10.1371/journal.pone.0336577}
}
EUVIMED