{
  "abstract": "BackgroundClinical registries and institutional quality control (QC) in pathology heavily depend on complex histopathological data. However, critical tumor characteristics are mostly locked in unstructured free-text reports. We hypothesize that locally deployed, resource-eWicient language models operating within a secure institutional network can reliably extract relevant variables from German reports of hepatocellular carcinoma (HCC), thereby enabling automated data curation without transferring sensitive patient data.\n\nMethodsWe developed a local, privacy-preserving open-weight Large Language Model (LLM) pipeline consisting of two consecutive stages: Stage 1 utilizes a lightweight gatekeeper model to isolate the target cohort of confirmed Hepatocellular Carcinoma cases from a screening pool of N = 2,864 reports. Stage 2 deploys a high-capacity model to extract 15 predefined histopathological variables, including tumor-node-metastasis staging, histological grading, vascular invasion, and selected immunohistochemical features into structured JSON format. For both Stages, pipeline performance was evaluated using Accuracy, Macro F1-scores, and Cohens kappa compared to expert-curated reference annotations.\n\nResultsThe top-performing Stage 1 gatekeeper isolated the target patient cohort with zero classification errors, effectively reaching complete agreement with the reference standard (ground truth) and correcting inaccurate administrative metadata. For Stage 2 feature extraction, current-generation models demonstrated robust structural reliability, reducing the burden of manual post-processing. The 31B model configuration (Gemma 4) virtually eliminated objective factual errors, achieving near-perfect agreement with the reference standard (Macro F1 > 0.99).\n\nConclusionLocal two-stage pipelines offer a highly accurate, resource-efficient, and secure solution for clinical text processing. This framework serves as a privacy-preserving engine for institutional quality control and the scalable curation of pathology registries.",
  "abstract_shown": true,
  "affiliations": [
    "Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "N. Koch"
    },
    {
      "name": "N. Hartmann"
    },
    {
      "name": "A. Maennel"
    },
    {
      "name": "G. Baretton"
    },
    {
      "name": "D. Aust"
    },
    {
      "name": "P. Hoenscheid"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a8g1k1h9d15gh.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.07.26364402",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.07.26364402v1.full",
  "id": "a8g1k1h9d15gh",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.07.26364402v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "pathology"
    ],
    [
      "openalex",
      "1312|Biomedical Text Mining and Ontologies"
    ]
  ],
  "openalex": "W7220964696",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.07.26364402v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a8g1k1h9d15gh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:26Z",
      "native_id": "10.64898/2026.10.07.26364402",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.07.26364402v1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Biomedical Text Mining and Ontologies",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Large Language Models for Structured Information Extraction from German Histopathology Reports - Hepatocellular Carcinoma",
  "title_text": "Large Language Models for Structured Information Extraction from German Histopathology Reports - Hepatocellular Carcinoma",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:26Z",
  "url": "https://research.draconitic.com/paper/a8g1k1h9d15gh",
  "venue": "medRxiv",
  "versions": []
}