{
  "abstract": "Objective: Chronic kidney disease (CKD) is a progressive condition requiring evidence-based management, but adherence to complex guidelines remains challenging. Large Language Models (LLMs) could support clinical decision-making, yet their unreliability limits direct use. This study aimed to evaluate whether Retrieval-Augmented Generation (RAG), particularly a knowledge graph-enhanced pipeline (GraphRAG), improves guideline-based clinical decision support (CDS) in CKD management.\n\nMethods and analysis: We compared three approaches: a baseline LLM (GPT-4o), a vector-indexed RAG pipeline and a GraphRAG pipeline. Each model answered nine clinically relevant questions for a synthetic cohort of 70 CKD patients. Outputs were assessed for clinical correctness, patient specificity and clarity using both clinician-led evaluations and an LLM-as-Judge framework.\n\nResults: RAG achieved higher clinician-rated correctness than the baseline LLM (76.6% vs 70.8%), with GraphRAG showing a similar improvement (75.6%). GraphRAG produced the most patient-specific responses but was associated with substantially longer outputs and reduced clarity. Response length was strongly correlated with both specificity and clarity, indicating that this trade-off is largely length-driven. Agreement between clinician and LLM-based evaluation varied by task type (Cohen’s kappa 0.13–0.97), with lower agreement for open-ended tasks. All retrieval-based methods were constrained by the scope of the indexed guideline.\n\nConclusions: RAG and GraphRAG provide a scalable, auditable foundation for guideline-aligned CDS in CKD. RAG showed higher clinician-rated correctness, while GraphRAG improved patient specificity without a corresponding gain in correctness. Trade-offs between specificity and clarity were largely driven by response length. Effective deployment will require robust content management, calibrated evaluation frameworks and integration within clinical governance structures.",
  "abstract_shown": true,
  "affiliations": [
    "Artificial Intelligence & Mathematics Research Lab, London, UK",
    "King’s College London, London, UK",
    "Renal Department, Guy's and St Thomas’ Hospitals NHS Trust, London, UK"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "M Berkan Sesen"
    },
    {
      "affs": [
        1
      ],
      "name": "Joshua A Yeung"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Elham Asgari",
      "orcid": "0000-0002-5692-0784"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0jkhf7we2fe4g.bib",
  "cited_by": 2,
  "doi": "10.1136/bmjdh-2026-000041",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13735396/",
  "id": "0jkhf7we2fe4g",
  "issns": [
    "3049-575X"
  ],
  "landing_url": "https://doi.org/10.1136/bmjdh-2026-000041",
  "language": "en",
  "licence": "CC-BY-NC-4.0",
  "licence_label": "CC BY-NC 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "1506"
    ],
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W4416754409",
  "pdf_url": "https://bmjdigitalhealth.bmj.com/content/2/1/e000041.full.pdf",
  "pmcid": "PMC13735396",
  "pmid": "42990834",
  "published": "2026-11-02",
  "publisher": "BMJ Publishing Group",
  "ris": "https://research.draconitic.com/paper/0jkhf7we2fe4g.ris",
  "sources": [
    {
      "first_seen": "2026-11-09T12:21:05Z",
      "native_id": "PMC13735396",
      "source": "pmc",
      "url": "https://doi.org/10.1136/bmjdh-2026-000041"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Development and evaluation of Retrieval-Augmented Generation (RAG) and GraphRAG for guideline-based clinical decision support in chronic kidney disease",
  "title_text": "Development and evaluation of Retrieval-Augmented Generation (RAG) and GraphRAG for guideline-based clinical decision support in chronic kidney disease",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T12:21:05Z",
  "url": "https://research.draconitic.com/paper/0jkhf7we2fe4g",
  "venue": "BMJ Digital Health & AI",
  "versions": []
}