{
  "abstract": "Background\n\nClinical practice guidelines are central instruments of evidence-based care; yet, in many domains, particularly rare or complex diseases, multiple guidelines coexist and frequently offer conflicting advice. Existing strategies for resolving such divergences are often labor-intensive, opaque, and insufficiently reproducible.Objective\n\nThis tutorial aimed to develop and demonstrate a reproducible workflow for transforming divergent clinical guideline recommendations and literature-derived white areas into human-reviewed Delphi-ready candidate items.Methods\n\nFollowing a step-by-step tutorial structure, we demonstrate the workflow using penile cancer as a worked example. The process comprises manual selection of clinical guidelines, a systematic PubMed search for literature-derived candidate issues potentially unaddressed by the selected guidelines, selection of 3 complementary large language models (LLMs), and execution of predefined prompts, multimodal recommendation extraction, semantic harmonization, and item-level guideline stance classification. The evaluative process combines a 3-LLM ensemble consistency check with an independent pre-Delphi appraisal by 4 penile cancer experts using a predefined 5-point suitability scale and acceptance threshold.Results\n\nIn the worked example in the field of penile cancer as a high-stakes use case, the workflow extracted 157 clinical recommendations from 5 guidelines and consolidated them into 68 harmonized guideline-derived items. Stance classification identified 15 uniformly supported items and 53 divergent, ambiguous, or incompletely addressed items. In parallel, literature processing generated 95 harmonized white-area items, of which 9 were classified as true white-area items not addressed by the included guidelines. The final methodological output was a set of 62 human-reviewed Delphi-ready candidate items for subsequent clinical consensus voting.Conclusions\n\nThis methodology provides a scalable, transparent, and transferable approach for identifying and structuring interguideline inconsistencies and evidence gaps. By combining LLM-assisted analysis with independent external expert appraisal, it supports the reproducible transformation of heterogeneous guideline content into Delphi-ready candidate items.",
  "abstract_shown": true,
  "affiliations": [
    "Department for Urology, University Hospital Regensburg, Caritas Krankenhaus St. Josef, Landshuter Str. 65, Regensburg, Bavaria, 93053, Germany, 49 941782 ext 3506.",
    "Department of Urology, University Hospital Augsburg, Augsburg, Bavaria, Germany.",
    "Department of Urology, Barmherzige Brüder Klinikum St. Elisabeth in Straubing, Straubing, Bavaria, Germany.",
    "Department of Epidemiology and Preventive Medicine, Medical Sociology, University of Regensburg, Regensburg, Bavaria, Germany.",
    "Department of Urology, Ludwig-Maximilians-Universität München, Munich, Bavaria, Germany.",
    "Faculty of Information Science, University of Regensburg, Regensburg, Germany."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 11,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Maximilian Haas",
      "orcid": "0000-0003-3132-0130"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Emily Rinderknecht",
      "orcid": "0009-0002-7283-5237"
    },
    {
      "affs": [
        2
      ],
      "name": "Matthias May",
      "orcid": "0000-0003-3896-0405"
    },
    {
      "affs": [
        0
      ],
      "name": "Maximilian Burger",
      "orcid": "0009-0005-5013-9435"
    },
    {
      "affs": [
        2
      ],
      "name": "Christian Gilfrich",
      "orcid": "0000-0003-0211-0636"
    },
    {
      "affs": [
        3
      ],
      "name": "Anne Herrmann",
      "orcid": "0000-0002-8855-4176"
    },
    {
      "affs": [
        4
      ],
      "name": "Sabine Brookman-May",
      "orcid": "0000-0003-2967-4028"
    },
    {
      "affs": [
        0
      ],
      "name": "Christoph Alexander Eckl",
      "orcid": "0009-0002-0075-3099"
    },
    {
      "affs": [
        5
      ],
      "name": "Udo Kruschwitz",
      "orcid": "0000-0002-5503-0341"
    },
    {
      "affs": [
        5
      ],
      "name": "Samy Ateia",
      "orcid": "0009-0000-2622-9194"
    },
    {
      "affs": [
        0,
        5
      ],
      "name": "Gregor Donabauer",
      "orcid": "0009-0002-8764-4943"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fpzsx00ztc6qn.bib",
  "cited_by": 0,
  "doi": "10.2196/96886",
  "fulltext_url": "https://europepmc.org/articles/PMC13683995",
  "id": "fpzsx00ztc6qn",
  "issns": [
    "1439-4456",
    "1438-8871"
  ],
  "landing_url": "https://europepmc.org/article/MED/42902842",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2739|Clinical practice guidelines implementation"
    ]
  ],
  "openalex": "W7212161870",
  "pdf_url": "https://europepmc.org/articles/PMC13683995?pdf=render",
  "pmcid": "PMC13683995",
  "pmid": "42902842",
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fpzsx00ztc6qn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:53Z",
      "native_id": "MED:42902842",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42902842"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2739|Clinical practice guidelines implementation",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "From Divergent Guidelines to Delphi-Ready Items: Tutorial for Large Language Model-Assisted Guideline Harmonization Using Penile Cancer as a Worked Example.",
  "title_text": "From Divergent Guidelines to Delphi-Ready Items: Tutorial for Large Language Model-Assisted Guideline Harmonization Using Penile Cancer as a Worked Example.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:53Z",
  "url": "https://research.draconitic.com/paper/fpzsx00ztc6qn",
  "venue": "Journal of medical Internet research",
  "versions": []
}