| title | Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why |
|---|---|
| authors | Osman Alperen Çinar-Koraş, Marie Bauer, Sameh Khattab, Merlin Engelke, Moon Kim, Stephan Settelmeier, Shigeyasu Sugawara, Fabian Freisleben, Felix Nensa, Jens Kleesiek |
| date | 2026-06-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.19602 |
| affiliation | IKIM |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | 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\%. |
cite
@misc{inarkora2026configurable,
title={Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why},
author={Osman Alperen Çinar-Koraş and Marie Bauer and Sameh Khattab and Merlin Engelke and Moon Kim and Stephan Settelmeier and Shigeyasu Sugawara and Fabian Freisleben and Felix Nensa and Jens Kleesiek},
year={2026},
eprint={2606.19602},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.19602}
}