Evidence mapPaperPMID 40604147Full record

ArticleNPJ digital medicine2025

Retrieval-augmented generation elevates local LLM quality in radiology contrast media consultation.

Akihiko Wada, Yuya Tanaka, Mitsuo Nishizawa, Akira Yamamoto, Toshiaki Akashi, Akifumi Hagiwara, Yayoi Hayakawa, Junko Kikuta, Keigo Shimoji, Katsuhiro Sano and 3 more

Abstract read
In one paragraph

Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 10 papers.

0numbers the graph read from it
0cells of the map it votes in
10citing papers in PubMed
field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

10 citing papers in PubMed.

  1. Article
  2. Article
  3. Article
  4. Review
  5. Article
  6. Article
  7. LabSage: Structural-Semantic Decoupling for Enhanced Retrieval-Augmented Generation in Clinical Laboratories.AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science · 2026
    Article
  8. Article
  9. Review
  10. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

13 authors.

Akihiko WadaDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan. a-wada@juntendo.ac.jp.
Yuya TanakaDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Mitsuo NishizawaDepartment of Radiology, Juntendo University Urayasu Hospital, 2-1-1 Tomioka, Urayasu, Chiba, 279-0021, Japan.
Akira YamamotoFaculty of Health Data Science, Juntendo University Graduate School of Medicine, 6-8-1 Hinode, Urayasu, Chiba, 279-0013, Japan.
Toshiaki AkashiDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Akifumi HagiwaraDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Yayoi HayakawaDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Junko KikutaDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Keigo ShimojiDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Katsuhiro SanoDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Koji KamagataDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Atsushi NakanishiDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.
Shigeki AokiDepartment of Radiology, Juntendo University Graduate School of Medicine, 2-1-1 Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.

Funding

Japan Society for the Promotion of Science 25K02609
6 · The paper itself

Abstract

Large language models (LLMs) demonstrate significant potential in healthcare applications, but clinical deployment is limited by privacy concerns and insufficient medical domain training. This study investigated whether retrieval-augmented generation (RAG) can improve locally deployable LLM for radiology contrast media consultation. In 100 synthetic iodinated contrast media consultations we compared Llama 3.2-11B (baseline and RAG) with three cloud-based models-GPT-4o mini, Gemini 2.0 Flash and Claude 3.5 Haiku. A blinded radiologist ranked the five replies per case, and three LLM-based judges scored accuracy, safety, structure, tone, applicability and latency. Under controlled conditions, RAG eliminated hallucinations (0% vs 8%; χ²₍Yates₎ = 6.38, p = 0.012) and improved mean rank by 1.3 (Z = -4.82, p < 0.001), though performance gaps with cloud models persist. The RAG-enhanced model remained faster (2.6 s vs 4.9-7.3 s) while the LLM-based judges preferred it over GPT-4o mini, though the radiologist ranked GPT-4o mini higher. RAG thus provides meaningful improvements for local clinical LLMs while maintaining the privacy benefits of on-premise deployment.

Identifiers

PMID40604147
PMCPMC12223273

What Socratic holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.