{
  "abstract": "The evolution of medical epistemology from the unassailable authority of eminence to the empirical rigour of evidence has prepared the healthcare system for its most profound transformation yet, intelligence-based medicine. Driven by the integration of artificial intelligence (AI), this emerging era offers unprecedented capabilities to process complex health data and personalise patient care within high-stakes environments like emergency departments. However, this paradigm shift simultaneously introduces a critical risk of modernised, digital dogma, manifesting as algorithmic paternalism. If AI systems are deployed without rigorous oversight, they threaten to silently amplify historical biases, diagnostic inaccuracies, and outdated clinical heuristics, trading the unquestioned authority of historical figures for the presumed infallibility of machines. To safeguard care in emergency departments, AI must not operate unchecked. Adapting existing Learning Health System frameworks offers a pragmatic solution to govern AI integration. By embedding these computational technologies within continuous, self-correcting clinical ecosystems, departments can enforce robust data hygiene and rigorously audit data provenance. An essential component of this approach is separating objective safety surveillance and adverse event reporting from the algorithm’s internal learning mechanisms to detect epistemic drift and automation bias. Ultimately, the successful and safe integration of intelligence-based medicine depends on an unwavering commitment to transparent governance. When computational power is harnessed as a regulated, transparent tool within an LHS, AI can actively dismantle entrenched clinical dogma, ensuring future care is anchored in dynamic, validated evidence rather than perpetuating the medical errors propagated by eminence from the past.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Perspective",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Viet Tran"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/crrxqgzx9xrqk.bib",
  "cited_by": 0,
  "doi": "10.3389/fpubh.2026.2009392",
  "fulltext_url": null,
  "id": "crrxqgzx9xrqk",
  "issns": [
    "2296-2565"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fpubh.2026.2009392",
  "language": null,
  "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": [
    [
      "feed-journal",
      "medicine/epidemiology-public-health"
    ]
  ],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-06",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/crrxqgzx9xrqk.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T12:20:49Z",
      "native_id": "10.3389/fpubh.2026.2009392",
      "source": "feed-frontiers",
      "url": "https://www.frontiersin.org/articles/10.3389/fpubh.2026.2009392"
    },
    {
      "first_seen": "2026-11-06T12:21:24Z",
      "native_id": "10.3389/fpubh.2026.2009392",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fpubh.2026.2009392/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "feed-journal:medicine/epidemiology-public-health",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "From eminence to evidence to intelligence-based medicine: optimising artificial intelligence to disrupt dogma in emergency departments",
  "title_text": "From eminence to evidence to intelligence-based medicine: optimising artificial intelligence to disrupt dogma in emergency departments",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T00:23:07Z",
  "url": "https://research.draconitic.com/paper/crrxqgzx9xrqk",
  "venue": "Frontiers in Public Health",
  "versions": []
}