{
  "abstract": "Clinical foundation models learn patterns in longitudinal health records that can be reused across prediction tasks. However, the relative strengths of representation-based and generation-based prediction across clinical tasks remain unclear. Using longitudinal electronic health records from 3.77 million patients at a single hospital, we developed FERMAT (Foundation model for Exploring Real-world Multimodal health data using Autoregressive Trajectory modeling), a 65-million-parameter clinical foundation model. We compared predictions from task-specific predictors trained on patient representations with those derived from generated clinical event sequences. Representation-based prediction performed better in the disease-risk comparisons. In detailed analyses of five-year chronic kidney disease, fatty liver, and diabetes risk in a test cohort of 10,000 patients, representation-based predictors exceeded generation-based estimates by 0.098-0.115 in observation-weighted AUROC and had lower probability error. Generation-based prediction, in turn, performed better in predicting diagnoses, prescriptions, and procedures recorded on the same day, a task motivated by the frequent presence of multiple events with the same date in hospital EHRs. Using 50 generated trajectories per patient, it achieved a Recall@10 of 71.0%, compared with 55.7% for representation-based prediction, with a paired improvement of 15.31 percentage points (95% CI, 13.92-16.79; n = 1,862). These findings demonstrate task-dependent strengths of representation-based and generation-based applications within a single clinical foundation model, providing an empirical basis for exploring how the two approaches can be used individually or combined to address clinical prediction needs.",
  "abstract_shown": true,
  "affiliations": [
    "Seoul National University"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "J. Jung"
    },
    {
      "affs": [
        0
      ],
      "name": "H.-C. Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/aw3x1wp1z5dj8.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.11.26365210",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365210v1.full",
  "id": "aw3x1wp1z5dj8",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365210v1",
  "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",
      "public and global health"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7221633431",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365210v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-11",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/aw3x1wp1z5dj8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:45Z",
      "native_id": "10.64898/2026.10.11.26365210",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365210v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:public and global health",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "FERMAT: An Autoregressive Clinical Foundation Model for Disease Risk and Clinical Event Prediction",
  "title_text": "FERMAT: An Autoregressive Clinical Foundation Model for Disease Risk and Clinical Event Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:45Z",
  "url": "https://research.draconitic.com/paper/aw3x1wp1z5dj8",
  "venue": "medRxiv",
  "versions": []
}