MedNuggetizer: Confidence-Based Information Nugget Extraction from Medical Documents

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), $\mathit{\text{MedNuggetizer}}$ 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 $\mathit{\text{antibiotic}}\mathit{\text{prophylaxis}}\mathit{\text{before}}\mathit{\text{prostate}}\mathit{\text{biopsy}}$ by using major urological guidelines and recent PubMed studies as sources of information. Evaluation by domain experts shows that $\mathit{\text{MedNuggetizer}}$ provides clinicians and researchers with an efficient way to explore long documents and easily extract reliable, query-focused medical evidence.