{
  "abstract": "Clinical prediction models often perform worse after transfer between hospital systems, but deterioration becomes apparent only once outcomes are known. We investigated whether uncertainty measures available at prediction time warn of performance loss and can help identify individual predictions requiring review. Three neural network architectures were trained on MIMIC-IV for in-hospital mortality prediction and evaluated on eICU-CRD. Measures included predictive entropy, mutual information from Monte Carlo dropout and deep ensembles, and representation density. After transfer, AUROC fell from 0.86-0.87 to 0.76-0.77 and calibration worsened, while entropy and mutual information were lower. None of the measures reliably indicated the reduced performance. Deferring the 20% with the highest entropy reduced the remaining error rate from 17.5-20.1% to 6.3-8.0%; the deferred patients included 91-99% of false alarms but only 2-7% of missed deaths, which carried low uncertainty. Uncertainty therefore supported selective review but failed to reveal performance loss.",
  "abstract_shown": true,
  "affiliations": [
    "Charité – Universitätsmedizin Berlin"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. Behling"
    },
    {
      "name": "M. Schulte-Althoff"
    },
    {
      "name": "S. Haufe"
    },
    {
      "name": "E. Grünewald"
    },
    {
      "name": "F. Balzer"
    },
    {
      "name": "N. Frey"
    },
    {
      "name": "S. D. Boie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2pvke81nrkmn9.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.03.26367064",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367064v1.full",
  "id": "2pvke81nrkmn9",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367064v1",
  "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",
      "health informatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367064v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2pvke81nrkmn9.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:20:42Z",
      "native_id": "10.64898/2026.11.03.26367064",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367064v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Evaluating uncertainty for detecting performance loss and guiding deferral after model transfer between hospital systems",
  "title_text": "Evaluating uncertainty for detecting performance loss and guiding deferral after model transfer between hospital systems",
  "type": "preprint",
  "updated_at": "2026-11-06T00:20:58Z",
  "url": "https://research.draconitic.com/paper/2pvke81nrkmn9",
  "venue": "medRxiv",
  "versions": []
}