{
  "abstract": "Objective: To develop and independently validate a decomposed, modality-specific large language model (LLM) pipeline that abstracts structured variables from the free-text neuroimaging reports of a multimodal stroke workup, and to validate the resulting structured dataset for reuse in downstream research. Materials and Methods: A frozen pipeline (temperature 0) extracting 22 variables across CT head, CT angiography, CT perfusion, and MRI brain was applied to 1,669 ED encounters for dizziness or vertigo; 11 variables were pre-specified as primary (Tier 1). Reproducibility used three same-session runs and a nine-week repeat run; three frontier models (Claude Sonnet 4.6, GPT-5.4, Gemini 3.5 Flash) measured cross-model agreement (Cohen's/Fleiss' kappa). Accuracy was assessed in an independent 200-encounter cohort (150 random, 50 enriched for rare findings); 100 were double-read by two blinded reviewers with discordances adjudicated. Results: Test-retest reproducibility was high (Tier 1 Fleiss' kappa = 0.993; 99.8% exact) and stable nine weeks later (kappa = 0.992); inter-model agreement was kappa = 0.962. Against the adjudicated reference, pooled Tier 1 accuracy was 0.971 to 0.988 across models (Cohen's kappa 0.959 to 0.982), comparable to inter-reviewer agreement (kappa = 0.932). Accuracy was 0.980 to 0.983 in random and 0.955 to 0.977 in enriched encounters (agreement on model-flagged findings, not sensitivity). Discussion: A decomposed LLM pipeline produced reproducible, model-portable, stable, and accurate multimodal abstraction. Because schema design and validation are up-front costs, such pipelines scale to larger research cohorts. Conclusion: The quantified per-field error rates support reuse of this dataset with field-specific review, and such pipelines offer a practical path to large-scale, reproducible research datasets.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Neurology, Staten Island University Hospital, Northwell Health, Staten Island, NY, USA; Zucker School of Medicine at Hofstra/Northwell, Hempstead,"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "J. Shahani"
    },
    {
      "name": "A. R. Ousta"
    },
    {
      "name": "S. Shaulov"
    },
    {
      "affs": [
        0
      ],
      "name": "Y. El-Sherif"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bhs4jfkcw1mjf.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.03.26367160",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367160v1.full",
  "id": "bhs4jfkcw1mjf",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367160v1",
  "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",
      "neurology"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367160v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bhs4jfkcw1mjf.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:20:38Z",
      "native_id": "10.64898/2026.11.03.26367160",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.11.03.26367160v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:neurology",
      "subfield": "neurology"
    }
  ],
  "title": "A Reproducible Decomposed Large Language Model Pipeline for Structured Abstraction of Multimodal Neuroimaging Reports: Development and Independent Validation in 1,669 Emergency Department Encounters for Dizziness and Vertigo",
  "title_text": "A Reproducible Decomposed Large Language Model Pipeline for Structured Abstraction of Multimodal Neuroimaging Reports: Development and Independent Validation in 1,669 Emergency Department Encounters for Dizziness and Vertigo",
  "type": "preprint",
  "updated_at": "2026-11-06T00:20:52Z",
  "url": "https://research.draconitic.com/paper/bhs4jfkcw1mjf",
  "venue": "medRxiv",
  "versions": []
}