Scholarlink

We present MedNuggetizer ( https://mednugget-ai.de/ ; access is available upon request.), a tool for query-driven extraction and clustering of information nuggets from medical documents to support clinicians in exploring underlying medical evidence. Backed by a large language model (LLM), MedNuggetizer performs repeated extractions of information nuggets that are then grouped to generate reliable evidence within and across multiple documents. We demonstrate its utility on the clinical use case of antibiotic prophylaxis before prostate biopsy by using major urological guidelines and recent PubMed studies as sources of information. Evaluation by domain experts shows that MedNuggetizer provides clinicians and researchers with an efficient way to explore long documents and easily extract reliable, query-focused medical evidence.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MedNuggetizer: Confidence-Based Information Nugget Extraction from Medical Documents

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gregor Donabauer,
  • Samy Ateia,
  • Udo Kruschwitz,
  • Maximilian Burger,
  • Matthias May,
  • Christian Gilfrich,
  • Maximilian Haas,
  • Julio Ruben Rodas Garzaro,
  • Christoph Eckl

摘要

We present MedNuggetizer ( https://mednugget-ai.de/ ; access is available upon request.), a tool for query-driven extraction and clustering of information nuggets from medical documents to support clinicians in exploring underlying medical evidence. Backed by a large language model (LLM), MedNuggetizer performs repeated extractions of information nuggets that are then grouped to generate reliable evidence within and across multiple documents. We demonstrate its utility on the clinical use case of antibiotic prophylaxis before prostate biopsy by using major urological guidelines and recent PubMed studies as sources of information. Evaluation by domain experts shows that MedNuggetizer provides clinicians and researchers with an efficient way to explore long documents and easily extract reliable, query-focused medical evidence.