{
  "abstract": "Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry (N = 129,033). Standard Fitted Q-Evaluation (FQE) yields an apparent policy-improvement estimate of +0.0069; adding an Early Neurological Deterioration penalty increases it to +0.0101. We identify reward-embedded confounding, in which a proxy terminal reward encodes baseline severity and prognosis as well as treatment efficacy. A 2 x 2 factorial analysis finds that terminal reward confounding accounts for 218.6% of the observed signal change, so its removal overshoots the null. After DML-inspired GBM reward residualization, the FQE estimate attenuates to +0.0033 (p = 0.132), and full deconfounding yields +0.0025 (p = 0.291). FQE-based diagnostics, T-learner analyses, and direct recurrence analyses converge away from a clinically meaningful aggregate improvement. A 1-year mRS factorial analysis replicates the attenuation. We provide an empirically motivated six-step evaluation checklist. NIHSS-stratified heterogeneity is hypothesis-generating for prospective trial design; hospital-level disagreement does not persist after full reward deconfounding.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:1689-1725, 2026",
  "arxiv": "2608.30442",
  "author_total": 1,
  "authors": [
    {
      "name": "Kihun Rhee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fxyq4ydsyxp20.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.30442",
  "fulltext_url": null,
  "id": "fxyq4ydsyxp20",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.30442",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ]
  ],
  "openalex": "W7204963563",
  "pdf_url": "https://arxiv.org/pdf/2608.30442",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-31",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fxyq4ydsyxp20.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:26Z",
      "native_id": "2608.30442",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.30442"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry",
  "title_text": "Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:26Z",
  "url": "https://research.draconitic.com/paper/fxyq4ydsyxp20",
  "venue": "arXiv",
  "versions": []
}