{
  "abstract": "Large language models require reproducible outputs for systematic evaluation in tumor boards. We developed a sarcoma tumor-board simulator using Claude Opus 4.5 at temperature 0.0, schema-enforced JSON output, and prompt-specified semantic and conditional-logic rules. The framework was evaluated on 51 de-identified cases across 154 runs. Reproducibility was defined as agreement across all runs of a case per decision code. In the 41 cases not used during development, reproducibility was 94.2% (cluster-bootstrap 95% CI 91.9–96.1); in the 10 development cases, 93.3% (95% CI 88.6–97.6). Pooled, it was 94.0% (95% CI 92.0–95.8); 17 cases agreed on all 21 codes. Estimates are model-specific. A post hoc ablation on 15 cases compared the framework with and without these rules: 94.6% versus 82.5% (difference 12.1 points; 95% CI 7.6–17.1). The improvement was driven mainly by exact wording agreement in three free-text fields (+ 60.0 points), whereas the 18 categorical and numeric codes differed by 4.1 points (95% CI − 0.7 to 9.3). Without any schema, a decision was stated for only 37.6% of instances versus 100% under schema enforcement; seven codes were never addressed. Single-reviewer screening detected no fabricated numbers, references, or measurements. Clinical correctness was not assessed. Consistent recommendations may still be incorrect.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "name": "Tekoshin Ammo"
    },
    {
      "name": "Moritz Englich"
    },
    {
      "name": "Fabio Dos Santos Adrego"
    },
    {
      "name": "Maximilian Jacobi"
    },
    {
      "name": "Alida Wilckens"
    },
    {
      "name": "Philipp Kruppa"
    },
    {
      "name": "Bastian Bonaventura"
    },
    {
      "name": "Stefan Niemuth"
    },
    {
      "name": "Selina M. Weiler"
    },
    {
      "name": "Victoria Wachenfeld-Teschner"
    },
    {
      "name": "Anja M. Boos"
    },
    {
      "name": "Gerrit Freund"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1vka76xzwfbek.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-74868-8",
  "fulltext_url": null,
  "id": "1vka76xzwfbek",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://www.nature.com/articles/s41598-026-74868-8",
  "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": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7221355146",
  "pdf_url": "https://www.nature.com/articles/s41598-026-74868-8.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-11",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/1vka76xzwfbek.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.1038/s41598-026-74868-8",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41598-026-74868-8"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "A schema-enforced large language model framework produces largely reproducible decision codes in simulated sarcoma tumor boards",
  "title_text": "A schema-enforced large language model framework produces largely reproducible decision codes in simulated sarcoma tumor boards",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:26Z",
  "url": "https://research.draconitic.com/paper/1vka76xzwfbek",
  "venue": "Scientific Reports",
  "versions": []
}