Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review
Verbesserung von Large-Language-Model-Anwendungen in Medizin und Pflege mit Retrieval-Augmented Generation: Scoping Review
Journal of Medical Internet Research · 2025-10-21 · 27 · e80557
DOI: 10.2196/80557 ↗Auf einen Blick
Der Review beschreibt RAG-Anwendungen in Medizin und Pflege. 67 eingeschlossene Arbeiten zeigten, dass die meisten Systeme im medizinischen Bereich lagen und nur wenige Pflegeanwendungen adressierten.
Fragestellung
Wie ist der aktuelle Stand von RAG in Medizin und Pflege, einschließlich Einschränkungen und Entwicklungsrichtungen?
Methode
Scoping Review nach PRISMA-ScR; Suche in PubMed, Web of Science, IEEE Xplore und arXiv vom 1. November 2022 bis 31. Mai 2025.
Ergebnisse
917 Treffer, 67 eingeschlossen. 63/67 (94 %) medizinisch, 4/67 (6 %) Pflege. 5 RAG-Typen; 26 Studien mit expliziter Reasoning-Unterstützung, 12 zu Ethik.
Schlussfolgerung der Autor:innen
Die Autor:innen sehen 4 Entwicklungsverschiebungen, betonen aber, dass die meisten Systeme noch keine Reasoning-Methoden nutzen und meist auf datengetriebenen Assoziationen statt kausalem Modellieren beruhen.
Kernaussagen
- 67 Studien zu RAG in Medizin und Pflege
- Nur 4/67 Studien zu Pflegeanwendungen
- 26 Studien mit expliziter Reasoning-Unterstützung
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Scoping Review in Journal of Medical Internet Research, published online on 2025-10-21. Written by Yiqun Miao and 4 co-authors. Institution: School of Nursing, Capital Medical University, Bejing, China. Major MEDLINE topics: Information Storage and Retrieval, Large Language Models. Cited 53 times so far (Crossref); 109 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Retrieval-augmented generation (RAG) is increasingly used to improve large language models in the medical and nursing domains. However, a comprehensive understanding of its specific architecture and applications in medical and nursing reasoning remains limited.
Objective
We aimed to summarize the current state, existing limitations, and future development directions of RAG in the medical and nursing domains.
Methods
The PubMed, Web of Science, IEEE Xplore, and arXiv databases were searched for relevant articles using queries that combined terms related to RAG, medical, and nursing domains, covering the period from November 1, 2022, to May 31, 2025. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines.
Results
A total of 917 articles were retrieved, of which 67 met the inclusion criteria. Most studies focused on the medical domain (63/67, 94%), while only a few addressed nursing applications (4/67, 6%). The RAG frameworks included in this review were categorized into 5 functional types: text-based RAG (36/67, 54%), knowledge graph–enhanced RAG (17/67, 25%), agentic RAG (6/67, 9%), multimodal RAG (2/67, 3%), and plug-and-play RAG (6/67, 9%). On the basis of the Simon decision-making process theory, we divided the RAG workflow into 4 stages: intent recognition, knowledge retrieval, knowledge integration, and generation. Only 26 studies included explicit reasoning support, and few were aligned with real-world clinical workflows. Only 12 studies attempted to address ethical considerations related to RAG.
Conclusions
We identified 4 key shifts in recent RAG development: shifting from surface-level matching toward contextualized intent recognition, from vague semantics toward logic-driven dynamic retrieval, from passive toward active knowledge retrieval, and from simple aggregation toward coherent context construction. However, most RAG systems in the medical and nursing domains have not yet introduced reasoning methods, and those that have are still predominantly reliant on data‑driven associations without causal modeling. This highlights the need to integrate causal mechanisms for more effective and domain-relevant reasoning in health care. Trial Registration OSF Registries 10.17605/OSF.IO/WBSV5; https://osf.io/wbsv5
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- School of Nursing, Capital Medical University, Bejing, China.
- The Chinese Institutes for Medical Research, Bejing, China.
ORCID profiles: Yiqun Miao, Yuhan Zhao, Yuan Luo, Huiying Wang, Ying Wu
Cite
APA
Miao, Y., Zhao, Y., Luo, Y., Wang, H., & Wu, Y. (2025). Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review. Journal of Medical Internet Research, 27, e80557. https://doi.org/10.2196/80557
Vancouver
Miao Y, Zhao Y, Luo Y, Wang H, Wu Y. Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review. Journal of Medical Internet Research. 2025;27:e80557. doi:10.2196/80557
BibTeX
@article{Miao2025,
author = {Miao, Yiqun and Zhao, Yuhan and Luo, Yuan and Wang, Huiying and Wu, Ying},
title = {Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {27},
pages = {e80557},
doi = {10.2196/80557}
}
EUVIMED