Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
Summary
ACIE, an agentic RAG system for clinical information extraction, achieves 96.5% acceptance rate in nuclear-medicine physicians' judgments across 7,326 instances, addressing challenges of heterogeneous patient contexts and missing metadata.
View Cached Full Text
Cached at: 06/20/26, 02:26 PM
Paper page - Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
Source: https://huggingface.co/papers/2606.19602
Abstract
ACIE, an agentic RAG system deployed in a clinical setting, demonstrates high accuracy in extracting medical information from complex patient contexts, achieving 96.5% acceptance rate by nuclear-medicine physicians across 7,326 judgments.
Patient contextsspan hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for retrieval and triage is absent or incomplete. Standardretrieval-augmented generationfails on this data, mishandling temporal reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (AgenticClinical Information Extraction) at University Medicine Essen: an on-premiseagentic RAG pipelinethat reasons over completepatient contextsand grounds every answer insource passagesforclinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospectivelymphoma registry study, in whichnuclear-medicine physiciansverify every extracted value against its cited sources. Across 7,326 judgments, clinicians accepted 96.5\% of extractions, with per-type acceptance ranging from 80\% to 99\%.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2606\.19602
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.19602 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.19602 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.19602 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases
This paper introduces AgenticRAG, a framework from Microsoft that enhances enterprise knowledge base retrieval by equipping LLMs with tools for iterative search, document navigation, and analysis. It demonstrates significant improvements in recall and factuality over standard RAG pipelines on multiple benchmarks.
AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows
Researchers from Banting Health AI present an AI system using generative LLMs with Retrieval-Augmented Generation (RAG) for automated clinical trial protocol information extraction, achieving 89% accuracy compared to 62.6% for standalone LLMs, with AI-assisted workflows completing tasks 40% faster and reducing cognitive demand.
SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
SEMA-RAG is a self-evolving multi-agent RAG framework for medical question answering that decouples interpretation, exploration, and adjudication into three specialist agents, achieving significant accuracy improvements over baselines across multiple benchmarks.
Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
This paper presents a modular retrieval-augmented generation (RAG) pipeline for extracting structured clinical observations from conversational nurse-patient transcripts, using schema-constrained prompting and second-pass auditing with Llama and GPT backbones, achieving 80.36% F1 score.
Agentic Document Extraction
Agentic Document Extraction is a tool that uses AI agents to make documents computable by extracting structured data from unstructured documents.