Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
For clinical NLP practitioners, this work demonstrates a practical solution to the metadata gap in heterogeneous patient records, though the approach is domain-specific and incremental.
The paper addresses the problem of missing document-level metadata in clinical contexts, which hinders AI systems from performing temporal reasoning and cross-document retrieval. The authors deploy ACIE, an agentic RAG pipeline, at University Medicine Essen, achieving 96.5% clinician acceptance across 7,326 judgments.
Patient contexts span 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. Standard retrieval-augmented generation fails on this data, mishandling temporal reasoning, cross-document dependencies, and missing metadata. We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline that reasons over complete patient contexts and grounds every answer in source passages for clinician verification. We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study, in which nuclear-medicine physicians verify 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\%.