{
  "abstract": "BackgroundLate-stage cancer incidence is being considered as an earlier endpoint in cancer-screening trials, but its trial-level association with cancer-specific mortality may depend on evidence selection and endpoint harmonization. We evaluated the robustness of this association to source-verified additions.\n\nMethodsWe reconstructed the PubMed corpus underlying a 41-comparison review. Gemini 3.1 Pro Preview was used only to prioritize reports for blinded human reassessment. Reviewers determined eligibility, linked reports from the same trial, harmonized endpoints, and verified comparison-level data. We recalculated unweighted Pearson correlations overall and by cancer type after adding earliest-compatible trial comparisons.\n\nResultsAmong 1209 candidate records, 996 PDFs were assessed. Thirty-three reports absent from the source review were prioritized; 26 were eligible, representing 18 trials, and 8 provided compatible comparisons. Adding these comparisons increased the dataset from 41 to 49 and attenuated the overall correlation from 0.73 (95% confidence interval [CI] = 0.55 to 0.85) to 0.59 (95% CI = 0.37 to 0.75). Updated correlations were 0.49 (95% CI = -0.26 to 0.87) for breast, - 0.23 (95% CI = -0.71 to 0.40) for colorectal, and 0.83 (95% CI = 0.54 to 0.95) for lung cancer. One sparse-event comparison influenced the colorectal estimate.\n\nConclusionsThe overall association was sensitive to evidence composition, and cancer-specific stability varied. Late-stage incidence should be evaluated by cancer type and with prespecified sensitivity analyses for evidence selection and endpoint definitions. Model-assisted prioritization cannot replace human eligibility review, trial reconciliation, and source verification.",
  "abstract_shown": true,
  "affiliations": [
    "The University of Arizona"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "name": "S. Li"
    },
    {
      "name": "W. Zhang"
    },
    {
      "name": "X. Xing"
    },
    {
      "name": "Z. Shen"
    },
    {
      "name": "Y. Wang"
    },
    {
      "name": "Z. Chen"
    },
    {
      "name": "O. Neto"
    },
    {
      "name": "Y. Yu"
    },
    {
      "name": "C. Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "L. Lin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8j93b95z9gf6m.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.29.26361733",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.08.29.26361733v1.full",
  "id": "8j93b95z9gf6m",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.08.29.26361733v1",
  "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",
      "oncology"
    ],
    [
      "openalex",
      "2730|Global Cancer Incidence and Screening"
    ]
  ],
  "openalex": "W7204930567",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.08.29.26361733v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8j93b95z9gf6m.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.64898/2026.08.29.26361733",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.08.29.26361733v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:oncology",
      "subfield": "oncology"
    }
  ],
  "title": "LLM-assisted evidence audit of late-stage cancer incidence as a screening trial endpoint",
  "title_text": "LLM-assisted evidence audit of late-stage cancer incidence as a screening trial endpoint",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/8j93b95z9gf6m",
  "venue": "medRxiv",
  "versions": []
}