{
  "abstract": "Background: The first 24 h after ICU admission in critically ill patients with heart failure yield heterogeneous EHR evidence across vital signs, laboratory tests, treatments, organ support, and nurse-charted monitoring. Conventional scores and flat-vector ML models may not preserve individual variable identity or context.\n\nMethods: We developed FTCT, encoding each predictor recorded during the first 24 h after ICU admission as a clinically tagged token (value, missingness, identity, group). MIMIC-IV (2008–2019) served for development, validation, and internal testing; eICU-CRD (2014–2015) served for external validation. Included were adults with heart failure, a complete 24-h ICU observation window, and known discharge status. The endpoint was in-hospital all-cause death.\n\nResults: MIMIC-IV included 11,156 stays and 1,484 deaths, partitioned into training ( n = 7,809), validation ( n = 1,673), and internal test ( n = 1,674) sets. eICU-CRD included 9,837 stays and 1,319 deaths. FTCT achieved an AUROC of 0.849 (95% CI, 0.835–0.863) internally and 0.804 (0.788–0.820) externally. Patient-paired AUROC differences vs. XGBoost were 0.027 (0.011–0.043) internally and 0.032 (0.014–0.050) externally. A matched FT-Transformer-style baseline achieved an external AUROC of 0.781 (0.760–0.801). In eICU-CRD, FTCT achieved an AUPRC of 0.296 (0.278–0.314), Brier score of 0.091 (0.085–0.097), and expected calibration error of 0.036 (0.030–0.042). In a post hoc cohort-specific descriptive operating analysis targeting approximately 85% specificity, external sensitivity was 0.662 (0.636–0.687), positive predictive value 0.406 (0.385–0.427), negative predictive value 0.942 (0.937–0.947), and F1 score 0.503. Removing feature-token encoding produced the largest ablation loss in external AUROC (−0.031).\n\nConclusions: FTCT combines established feature-token Transformer modeling with clinical-group embeddings, explicit missingness representation, and group-aware pooling for 24-h landmark mortality risk stratification from structured EHR data recorded during the first 24 h after ICU admission. Its external validation and ablation results support prospective investigation, but do not yet demonstrate clinical utility, workflow integration, admission-time applicability, or autonomous use.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Cardiology, The First Affiliated Hospital of Soochow University"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Mianxian Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuefei Zhou"
    },
    {
      "affs": [
        0
      ],
      "name": "Chun Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9qkc7wb7n7v5z.bib",
  "cited_by": 0,
  "doi": "10.3389/fcvm.2026.1945947",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13717714/?tool=EBI",
  "id": "9qkc7wb7n7v5z",
  "issns": [
    "2297-055X"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fcvm.2026.1945947/full",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7222183077",
  "pdf_url": "https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2026.1945947/pdf",
  "pmcid": "PMC13717714",
  "pmid": "42959899",
  "published": "2026-10-15",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/9qkc7wb7n7v5z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:10Z",
      "native_id": "10.3389/fcvm.2026.1945947",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fcvm.2026.1945947/full"
    },
    {
      "first_seen": "2026-10-31T00:20:37Z",
      "native_id": "PMC:PMC13717714",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13717714"
    },
    {
      "first_seen": "2026-10-31T12:21:46Z",
      "native_id": "MED:42959899",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42959899"
    },
    {
      "first_seen": "2026-11-02T12:21:59Z",
      "native_id": "PMC13717714",
      "source": "pmc",
      "url": "https://doi.org/10.3389/fcvm.2026.1945947"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:2297-055X",
      "subfield": "cardiovascular"
    }
  ],
  "title": "Feature-token clinical transformer for 24-h landmark mortality risk stratification in critically ill patients with heart failure: development and multicenter external validation",
  "title_text": "Feature-token clinical transformer for 24-h landmark mortality risk stratification in critically ill patients with heart failure: development and multicenter external validation",
  "type": "peer-reviewed",
  "updated_at": "2026-11-02T12:21:59Z",
  "url": "https://research.draconitic.com/paper/9qkc7wb7n7v5z",
  "venue": "Frontiers in Cardiovascular Medicine",
  "versions": []
}