{
  "abstract": "The rapid growth of medical knowledge and the increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) demonstrate value; however, inherent limitations remain. Retrieval-augmented generation (RAG) shows potential to enhance their clinical applicability. This study reviews RAG applications in medicine. We find that research primarily relies on publicly available data, with limited use of private data. For retrieval, approaches commonly rely on English-centric embedding models, while LLMs are mostly generic, with limited use of medical-specific LLMs. For evaluation, automated metrics evaluate generation quality and task performance, whereas human evaluation focuses on accuracy, completeness, relevance, and fluency, with insufficient attention to bias and safety. RAG applications are concentrated on question answering, report generation, text summarization, and information extraction. Overall, medical RAG remains at an early stage, requiring advances in clinical validation, cross-linguistic adaptation, and support for low-resource settings to enable trustworthy and responsible global use.",
  "abstract_shown": true,
  "affiliations": [
    "Centre for Biomedical Data Science, Duke-NUS Medical School, Singapore 169857, Singapore; Duke-NUS AI + Medical Sciences Initiative, Duke-NUS Medical School, Singapore 169857, Singapore",
    "School of Clinical Medicine, University of Cambridge, Cambridge CB2 0SP, UK",
    "Graduate School of Frontier Sciences, The University of Tokyo, Tokyo 277-8561, Japan",
    "Graduate School of Engineering, The University of Tokyo, Tokyo 113-8654, Japan",
    "Duke-NUS AI + Medical Sciences Initiative, Duke-NUS Medical School, Singapore 169857, Singapore; Division of Anesthesiology and Perioperative Medicine, Singapore General Hospital, Singapore 169608, Singapore",
    "Duke-NUS AI + Medical Sciences Initiative, Duke-NUS Medical School, Singapore 169857, Singapore; Division of Pharmacy, Singapore General Hospital, Singapore 169608, Singapore",
    "Department of Radiology and Medical Informatics, University of Geneva, 1202 Geneva, Switzerland",
    "Department of Biostatistics and Bioinformatics, Duke School of Medicine, Durham, NC 27710, USA; Duke Clinical Research Institute, Durham, NC 27705, USA",
    "Singapore Eye Research Institute, Singapore National Eye Center, Singapore 168751, Singapore; Byers Eye Institute, Stanford University, Stanford, CA 94303, USA; Artificial Intelligence Office, Singapore Health Services, Singapore 168582, Singapore"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 16,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Rui Yang"
    },
    {
      "affs": [
        1
      ],
      "name": "Matthew Yu Heng Wong",
      "orcid": "0009-0004-7633-4901"
    },
    {
      "affs": [
        0
      ],
      "name": "Huitao Li",
      "orcid": "0000-0002-5715-8250"
    },
    {
      "affs": [
        0
      ],
      "name": "Xin Li",
      "orcid": "0000-0002-7325-4250"
    },
    {
      "affs": [
        0
      ],
      "name": "Wentao Zhu"
    },
    {
      "affs": [
        0
      ],
      "name": "Jingchi Liao"
    },
    {
      "affs": [
        0
      ],
      "name": "Kunyu Yu"
    },
    {
      "affs": [
        0
      ],
      "name": "Jonathan Chong Kai Liew",
      "orcid": "0009-0007-4094-2050"
    },
    {
      "affs": [
        2
      ],
      "name": "Weihao Xuan",
      "orcid": "0009-0001-4271-9035"
    },
    {
      "affs": [
        3
      ],
      "name": "Yingjian Chen",
      "orcid": "0000-0001-7605-357X"
    },
    {
      "affs": [
        4
      ],
      "name": "Yuhe Ke",
      "orcid": "0000-0001-7193-4749"
    },
    {
      "affs": [
        5
      ],
      "name": "Jasmine Chiat Ling Ong",
      "orcid": "0000-0001-6916-5960"
    },
    {
      "affs": [
        6
      ],
      "name": "Douglas Teodoro",
      "orcid": "0000-0001-6238-4503"
    },
    {
      "affs": [
        7
      ],
      "name": "Chuan Hong",
      "orcid": "0000-0001-7056-9559"
    },
    {
      "affs": [
        8
      ],
      "name": "Daniel Shu Wei Ting",
      "orcid": "0000-0003-2264-7174"
    },
    {
      "name": "Nan Liu",
      "orcid": "0000-0003-1490-840X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3xvg12r45k0bk.bib",
  "cited_by": 18,
  "doi": "10.1016/j.xcrm.2026.102927",
  "fulltext_url": null,
  "id": "3xvg12r45k0bk",
  "issns": [
    "2666-3791"
  ],
  "landing_url": "https://doi.org/10.1016/j.xcrm.2026.102927",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W4416237197",
  "pdf_url": null,
  "pmcid": null,
  "pmid": "42476143",
  "published": "2026-07-01",
  "publisher": "Elsevier BV",
  "ris": "https://research.draconitic.com/paper/3xvg12r45k0bk.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:26:56Z",
      "native_id": "W4416237197",
      "source": "openalex",
      "url": "https://doi.org/10.1016/j.xcrm.2026.102927"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Retrieval-augmented generation in medicine: A scoping review of technical implementations, clinical applications, and ethical considerations",
  "title_text": "Retrieval-augmented generation in medicine: A scoping review of technical implementations, clinical applications, and ethical considerations",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:15Z",
  "url": "https://research.draconitic.com/paper/3xvg12r45k0bk",
  "venue": "Cell Reports Medicine",
  "versions": []
}