EUVIMEDEUVIMED entdecken
Open Access

Improving Dietary Supplement Information Retrieval: Development of a Retrieval-Augmented Generation System With Large Language Models

Yu Hou iD, Jeffrey R Bishop iD, Hongfang Liu iD, Rui Zhang iD

Journal of Medical Internet Research · 19.03.2025 · 27 · e67677

DOI: 10.2196/67677 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 19.03.2025. Verfasst von Yu Hou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Division of Computational Health Sciences, University of Minnesota, Minneapolis, MN, United States. Hauptthemen laut MEDLINE: Dietary Supplements, Information Storage and Retrieval. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NCCIH NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Dietary supplements (DSs) are widely used to improve health and nutrition, but challenges related to misinformation, safety, and efficacy persist due to less stringent regulations compared with pharmaceuticals. Accurate and reliable DS information is critical for both consumers and health care providers to make informed decisions.

Objective

This study aimed to enhance DS-related question answering by integrating an advanced retrieval-augmented generation (RAG) system with the integrated Dietary Supplement Knowledgebase 2.0 (iDISK2.0), a dietary supplement knowledge base, to improve accuracy and reliability.

Methods

We developed iDISK2.0 by integrating updated data from authoritative sources, including the Natural Medicines Comprehensive Database, the Memorial Sloan Kettering Cancer Center database, Dietary Supplement Label Database, and Licensed Natural Health Products Database, and applied advanced data cleaning and standardization techniques to reduce noise. The RAG system combined the retrieval power of a biomedical knowledge graph with the generative capabilities of large language models (LLMs) to address limitations of stand-alone LLMs, such as hallucination. The system retrieves contextually relevant subgraphs from iDISK2.0 based on user queries, enabling accurate and evidence-based responses through a user-friendly interface. We evaluated the system using true-or-false and multiple-choice questions derived from the Memorial Sloan Kettering Cancer Center database and compared its performance with stand-alone LLMs. Results iDISK2.0 integrates 174,317 entities across 7 categories, including 8091 dietary supplement ingredients; 163,806 dietary supplement products; 786 diseases; and 625 drugs, along with 6 types of relationships. The RAG system achieved an accuracy of 99% (990/1000) for true-or-false questions on DS effectiveness and 95% (948/100) for multiple-choice questions on DS-drug interactions, substantially outperforming stand-alone LLMs like GPT-4o (OpenAI), which scored 62% (618/1000) and 52% (517/1000) on these respective tasks. The user interface enabled efficient interaction, supporting free-form text input and providing accurate responses. Integration strategies minimized data noise, ensuring access to up-to-date, DS-related information.

Conclusions

By integrating a robust knowledge graph with RAG and LLM technologies, iDISK2.0 addresses the critical limitations of stand-alone LLMs in DS information retrieval. This study highlights the importance of combining structured data with advanced artificial intelligence methods to improve accuracy and reduce misinformation in health care applications. Future work includes extending the framework to broader biomedical domains and improving evaluation with real-world, open-ended queries.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Dietary SupplementsInformation Storage and RetrievalHumansKnowledge BasesDatabases, FactualLarge Language Models

Stichwörter der Autor:innen

dietary supplementsknowledge graphknowledge representationlarge language modelretrieval-augmented generationuser interface

Autor:innen und Institutionen

  • Division of Computational Health Sciences, University of Minnesota, Minneapolis, MN, United States.
  • Department of Experimental and Clinical Pharmacology, University of Minnesota, Minneapolis, MN, United States.
  • Department of Health Data Science and Artificial Intelligence, UTHealth, Houston, TX, United States.
  • Center for Learning Health System Sciences, University of Minnesota, Minneapolis, MN, United States.

ORCID-Profile: Yu Hou, Jeffrey R Bishop, Hongfang Liu, Rui Zhang

Förderung

  • NIA NIH HHS
  • NCCIH NIH HHS
  • NCI NIH HHS

Zitieren

APA

Hou, Y., Bishop, J. R., Liu, H., & Zhang, R. (2025). Improving Dietary Supplement Information Retrieval: Development of a Retrieval-Augmented Generation System With Large Language Models. Journal of Medical Internet Research, 27, e67677. https://doi.org/10.2196/67677

Vancouver

Hou Y, Bishop JR, Liu H, Zhang R. Improving Dietary Supplement Information Retrieval: Development of a Retrieval-Augmented Generation System With Large Language Models. Journal of Medical Internet Research. 2025;27:e67677. doi:10.2196/67677

BibTeX
@article{Hou2025,
  author = {Hou, Yu and Bishop, Jeffrey R and Liu, Hongfang and Zhang, Rui},
  title = {Improving Dietary Supplement Information Retrieval: Development of a Retrieval-Augmented Generation System With Large Language Models},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e67677},
  doi = {10.2196/67677}
}
Kostenlos starten →