{
  "abstract": "PurposeTo evaluate how adaptive LLM swarm revision changes ICU mortality-risk outputs and to characterize evidence use, explanation indicators, auditability, and computational burden in final adaptive outputs relative to an independently executed fixed-voting (FV) architecture.\n\nMethodsWe retrospectively analyzed 1,607 eICU encounters (1,500 stays) and 1,607 ICU-2012 encounters. Initial (ASI) and final (ASF) adaptive outputs were compared within runs for revision engagement and risk-score drift; final ASF and separately generated FV outputs were compared for evidence use, explanation indicators, auditability, and computation. Paired differences and 95% confidence intervals used 10,000 hospital-stay-clustered bootstrap replicates.\n\nResultsAt least one specialist revision trace occurred in 84.32% of eICU and 56.44% of ICU-2012 encounters. Mean ASF-minus-ASI risk-score changes were +0.0810 and +0.0539; 757 of 761 0.50-threshold crossings moved toward mortality, without clear AUROC or AUPRC improvement. In the independent benchmark, ASF explanations contained 1.26 and 0.55 more supporting-evidence items than FV, but counterevidence acknowledgement was 21.59 and 7.47 percentage points lower and unsupported-claim flags were 1.43 and 0.68 points higher. All final records met the reconstruction-completeness criterion, although ASF generated more warnings and required 1.97 and 1.52 times the FV runtime.\n\nConclusionAdaptive revision materially changed swarm operating behaviour. Independently, final ASF outputs showed greater supporting-evidence use but less balanced evidence engagement, more process warnings, and greater computational burden than FV. These automated artifact-level findings do not establish superior explanation quality or isolate revision as their cause.",
  "abstract_shown": true,
  "affiliations": [
    "University of Ottawa"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "C. Anderson"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bec21vshqqe8h.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.01.26361960",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.01.26361960v1.full",
  "id": "bec21vshqqe8h",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.01.26361960v1",
  "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",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7211958102",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.01.26361960v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bec21vshqqe8h.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:54Z",
      "native_id": "10.64898/2026.09.01.26361960",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.01.26361960v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Revision Behavior and Explainability in Adaptive LLM Swarms for ICU Mortality Risk Prediction: A Two-Dataset Evaluation",
  "title_text": "Revision Behavior and Explainability in Adaptive LLM Swarms for ICU Mortality Risk Prediction: A Two-Dataset Evaluation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:54Z",
  "url": "https://research.draconitic.com/paper/bec21vshqqe8h",
  "venue": "medRxiv",
  "versions": []
}