{
  "abstract": "Sepsis is a leading cause of hospital mortality, yet timely recognition is hampered by nonspecific presentations and label noise in code-based case definitions. We developed STRIDE, a machine-learning framework for sepsis detection across seven hospitals with a scalable approach to label quality. We refined a pragmatic operational definition using a large language model applied to discharge summaries, with an independent physician-adjudicated cohort as the gold standard. We compared 8-, 24-, and 48-hour observation windows and benchmarked against SOFA, SIRS, and Epic, assessing calibration and discrimination. Among 356,610 encounters, the 8-hour model achieved an AUC of 0.960 in derivation and 0.878 in physician-adjudicated validation, matching or outperforming longer-window models. STRIDE outperformed SOFA and Epic on discrimination and showed favorable calibration by Brier score, while retaining strong discrimination among SIRS-positive non-septic encounters and reaching 78.2% specificity at 80% sensitivity in validation. These findings support accurate sepsis surveillance while limiting unnecessary alerts and requiring minimal prior history.",
  "abstract_shown": true,
  "affiliations": [
    "Saïd Business School, University of Oxford"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "I. Kitsos Kalyvianakis"
    },
    {
      "name": "C. Perez de Amezaga"
    },
    {
      "name": "E. S. Lee"
    },
    {
      "name": "A. Palmer"
    },
    {
      "name": "J. Garner"
    },
    {
      "name": "U. S. Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "A. Orfanoudaki"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ff1ec7zsrp981.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.08.26362428",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362428v1.full",
  "id": "ff1ec7zsrp981",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362428v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "infectious diseases"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7212002137",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362428v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ff1ec7zsrp981.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:11Z",
      "native_id": "10.64898/2026.09.08.26362428",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.08.26362428v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:infectious diseases",
      "subfield": "infectious-disease"
    }
  ],
  "title": "Language model-assisted label refinement for accurate sepsis detection from electronic health records",
  "title_text": "Language model-assisted label refinement for accurate sepsis detection from electronic health records",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:11Z",
  "url": "https://research.draconitic.com/paper/ff1ec7zsrp981",
  "venue": "medRxiv",
  "versions": []
}