{
  "abstract": "BackgroundPeople affected by cancer often face difficulty finding relevant clinical, psychological, and practical support services. AI-powered navigation assistants may improve access to these resources, but their retrieval performance must be reliable.\n\nObjectiveTo develop a single-pass retrieval-augmented generation assistant for cancer-care navigation and compare the retrieval strategies, including their robustness to reworded questions.\n\nMethodsWe created a database of 853 cancer-support resources reviewed by librarians, clinicians, researchers, and patient partners. We evaluated the system using 100 questions derived from questions submitted by patients. We compared keyword-based, semantic, and hybrid retrieval using Precision@K, Hit@K, and nDCG@K. The best-performing configuration was then tested using semantically equivalent rewordings of the original questions.\n\nResultsKeyword-based retrieval performed poorly, achieving a P@1 of 25.0% and Hit@5 of 43.0%. Semantic retrieval improved these results to 58.0% and 86.0%, respectively. The best hybrid configuration achieved a P@1 of 64.0%, Hit@5 of 90.0%, and nDCG@5 of 51.0%. Performance remained relatively stable when the questions were reworded, with a P@1 of 61.0%, Hit@5 of 88.0%, and nDCG@5 of 46.1%.\n\nConclusionsHybrid retrieval performed best and remained relatively stable when questions were reworded. However, its limited ability to rank a relevant resource first highlights the limitations of single-pass retrieval for patient-facing cancer navigation. Future work will explore metadata filtering and a multi-agent architecture to improve retrieval reliability.",
  "abstract_shown": true,
  "affiliations": [
    "The University of British Columba\\BC Cancer"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 13,
  "authors": [
    {
      "name": "E. Hasan"
    },
    {
      "name": "Y. Zhang"
    },
    {
      "name": "O. Cook"
    },
    {
      "name": "A. Loe"
    },
    {
      "name": "M. Sha"
    },
    {
      "name": "L. T'ien"
    },
    {
      "name": "M. Ng"
    },
    {
      "name": "C. Rauscher"
    },
    {
      "name": "S. Raman"
    },
    {
      "name": "J. L. Bender"
    },
    {
      "name": "R. T. Ng"
    },
    {
      "name": "A. Bates"
    },
    {
      "affs": [
        0
      ],
      "name": "J.-J. Nunez"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0vfwt8tcympfm.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.31.26361774",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361774v1.full",
  "id": "0vfwt8tcympfm",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361774v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "1710|Information Retrieval and Search Behavior"
    ]
  ],
  "openalex": "W7208707272",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361774v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-31",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0vfwt8tcympfm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:44Z",
      "native_id": "10.64898/2026.08.31.26361774",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.08.31.26361774v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Limits of Single-Pass Retrieval-Augmented Generation for AI-Powered Cancer Care Navigation: A Comparison of Retrieval Strategies",
  "title_text": "Limits of Single-Pass Retrieval-Augmented Generation for AI-Powered Cancer Care Navigation: A Comparison of Retrieval Strategies",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:44Z",
  "url": "https://research.draconitic.com/paper/0vfwt8tcympfm",
  "venue": "medRxiv",
  "versions": []
}