{
  "abstract": "Prognostic models in oncology are developed one cancer at a time, from that cancers own labelled outcomes, and fail where prognostic information is scarcest. Rare cancers account for roughly a fifth of diagnoses and most paediatric malignancies, yet seldom supply enough events for a reliable time-to-event model. We therefore asked whether a representation learned without outcome labels can supply what those cohorts cannot. A Transformer encoder was pretrained by masked field-value modelling on 9,425,135 tumour records from the SEER 17 registries, diagnosed in 2000-2023. Only diagnosis-time fields passing a fail-closed coding-verification gate were admitted, and each record was emitted as an era-specific and a harmonised view, keeping two decades of recoding auditable. The encoder was then frozen and read by a linear Cox head for overall survival. Nine rare cancers were removed from the pretraining corpus entirely, each requiring an independent pretraining run. On a sealed test partition, all nine exceeded an architecture-identical random frozen encoder in Harrell concordance by +0.0034 to +0.0368, every lower confidence limit above zero. At 256 labelled patients, all 67 cancers favoured the pretrained representation over budget-matched Cox regression, median difference +0.0283. The advantage was bounded: given the entire training set, Cox regression was favoured in seven of nine rare cancers. The encoder did not outperform a field-frequency baseline on its own objective, so upstream reconstruction did not predict downstream transfer. Outcome-agnostic registry pretraining carries prognostic signal into cancers it has never seen, and is most useful where labels are fewest, without establishing clinical utility.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Clinical Laboratory, Sir Run Run Shaw Hospital of Zhejiang University School of Medicine, Hangzhou, Zhejiang, China; Key Laboratory of Precision M"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "name": "Y. Gao"
    },
    {
      "name": "S. Yu"
    },
    {
      "name": "Y. Xia"
    },
    {
      "name": "S. Chen"
    },
    {
      "name": "S. Xia"
    },
    {
      "name": "R. An"
    },
    {
      "name": "J. Zeng"
    },
    {
      "name": "F. Zhao"
    },
    {
      "name": "Y. Ma"
    },
    {
      "name": "Y. Wang"
    },
    {
      "name": "X. Xie"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/68jmaa17z09rc.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.08.30.26361693",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.08.30.26361693v1.full",
  "id": "68jmaa17z09rc",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.08.30.26361693v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "oncology"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.08.30.26361693v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/68jmaa17z09rc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:39Z",
      "native_id": "10.64898/2026.08.30.26361693",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.08.30.26361693v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:oncology",
      "subfield": "oncology"
    }
  ],
  "title": "Pretrained transformers applied to population cancer registries improve survival prediction in label-scarce and previously unseen cancers",
  "title_text": "Pretrained transformers applied to population cancer registries improve survival prediction in label-scarce and previously unseen cancers",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:39Z",
  "url": "https://research.draconitic.com/paper/68jmaa17z09rc",
  "venue": "medRxiv",
  "versions": []
}