mlsanityData to 14 Oct 2026

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

arXiv 2606.19602 ↗First posted 17 Jun 2026cs.AIcited by 1

On the map: Retrieval-augmented generation → Medical and biomedical RAG

also in 1 more
Abstract (arXiv)

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%.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 38 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

13 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions1 Aug

Other references · 12

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  5. 2022Large Language Models are Few-Shot Clinical Information Extractorscited by 207
  6. 2024Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Modelscited by 96
  7. 2020Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkitcited by 66
  8. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 57
  9. 2024ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agentscited by 20
  10. 2025Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidencecited by 16
  11. 2025HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Datacited by 2
  12. 2026Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A Living Benchmark for Information Retrieval from Electronic Health Recordscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
  2. 2025DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
  3. 2025Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards
  4. 2025Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge
  5. 2025Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QA
  6. 2026ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
  7. 2026Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science
  8. 2026AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows