{
  "abstract": "While large language models are powerful generators of new text, forecasting disease progression from longitudinal health histories remains a challenging problem. We introduce GenEHR, an autoregressive generative model trained on electronic health records (EHRs) from millions of patients in diverse health systems. The model learns from real-world multimodal patient histories, including diagnoses, medications, lab values, and procedures while explicitly representing irregular intervals between visits to forecast future clinical events. We combine the general-purpose patient representation learned during foundational training with parameter-efficient supervised adaptation for the task of risk stratification for 17 cancer types. In five large EHR cohorts, supervised adaptation substantially improved prediction performance of a first cancer diagnosis within a five year horizon window. Our retrospective results support the prospective evaluation of GenEHR-CancerRisk as a clinical decision-support tool for prioritizing high-risk patients for screening and prevention of aggressive cancer types, such as pancreatic and ovarian cancer.",
  "abstract_shown": true,
  "affiliations": [
    "Harvard Medical School"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 14,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. Khan"
    },
    {
      "name": "D. T. Forster"
    },
    {
      "name": "M. Harsh"
    },
    {
      "name": "C. Zheng"
    },
    {
      "name": "E. T. Warner"
    },
    {
      "name": "D. Ritter"
    },
    {
      "name": "A. Chang"
    },
    {
      "name": "Q. Wei"
    },
    {
      "name": "T. K. Sorensen"
    },
    {
      "name": "D. S. Marks"
    },
    {
      "name": "L. V. Sequist"
    },
    {
      "name": "J. J. Hadlock"
    },
    {
      "name": "N. R. Fillmore"
    },
    {
      "name": "C. Sander"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5hsqab4znapkn.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.09.26362676",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.09.26362676v1.full",
  "id": "5hsqab4znapkn",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.09.26362676v1",
  "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",
      "health informatics"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7212393413",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.09.26362676v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5hsqab4znapkn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:21Z",
      "native_id": "10.64898/2026.09.09.26362676",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.09.26362676v4"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Generative model of patient health states and pan-cancer risk stratification",
  "title_text": "Generative model of patient health states and pan-cancer risk stratification",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:38Z",
  "url": "https://research.draconitic.com/paper/5hsqab4znapkn",
  "venue": "medRxiv",
  "versions": []
}