MedNuggetizer: Confidence-Based Information Nugget Extraction from Medical Documents
By: Gregor Donabauer , Samy Ateia , Udo Kruschwitz and more
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), \textit{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 \textit{antibiotic prophylaxis before prostate biopsy} by using major urological guidelines and recent PubMed studies as sources of information. Evaluation by domain experts shows that \textit{MedNuggetizer} provides clinicians and researchers with an efficient way to explore long documents and easily extract reliable, query-focused medical evidence.
Similar Papers
The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models
Information Retrieval
Tests AI answers automatically, saving time.
GINGER: Grounded Information Nugget-Based Generation of Responses
Computation and Language
Makes AI answers more truthful and shows where they came from.
Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses
Information Retrieval
Checks if AI answers have all the important facts.