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

• URL: http://arxiv.org/abs/2606.19602v1
• Date: Wed, 17 Jun 2026 21:12:35 GMT
• Title: Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
• Abstract summary: Patient contexts span hundreds of heterogeneous documents and thousands of structured data points.<n>Standard retrieval-augmented generation fails on this data, temporal reasoning, cross-document dependencies, and missing metadata.<n>We deploy ACIE (Agentic Clinical Information Extraction) at University Medicine Essen: an on-premise agentic RAG pipeline.<n>We quantify the metadata gap, trace the architectural decisions it shaped, and evaluate extraction alongside an independent retrospective lymphoma registry study.
• Score: 4.527967729863067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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\%.

Related papers

• From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction [24.52832312973969]
  Clinically relevant oncology information is distributed across heterogeneous, longitudinal documentation.<n>OncoLens supplies multi-source, oncology-aware document selection, aggregation, and normalization from integrated EHRs.<n>NimbleMind Multi-Agent System (nMAS) is an oncology information-extraction workflow that extracts clinically relevant structured fields from fragmented oncology documentation.
  arXiv  Detail & Related papers  (2026-08-29T00:51:30Z)
• PatTree: a novel approach for automated creation of multimodal, graph-based patient representations for medical classification tasks [0.13999481573773073]
  PatTree is a graph-based representation of patients that can be derived from real-world clinical data.<n>We demonstrate that classification of patients is directly feasible on PatTree reaching state-of-the-art classification performance.
  arXiv  Detail & Related papers  (2026-08-03T09:44:35Z)
• VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards [1.5504500166769226]
  We introduce VISTA Architect, a database-oriented AI architecture for integrating large language models with longitudinal electronic health records.<n>At ingestion, it transforms complex clinical documentation into a persistent, provenance-linked knowledge graph.<n>Across 1,180 patients, VISTA Architect achieved 96.4% accuracy on 15 tumor board-salient variables.
  arXiv  Detail & Related papers  (2026-06-21T22:09:12Z)
• Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture [71.46525715889656]
  General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement.<n>We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record.<n>We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions.
  arXiv  Detail & Related papers  (2026-04-29T17:59:28Z)
• A Semi-Automated Annotation Workflow for Paediatric Histopathology Reports Using Small Language Models [0.0]
  We develop a resource-efficient semi-automated annotation workflow using small language models (SLMs) to extract structured information from unstructured EPR data.<n>As a proof-of-concept, we apply the workflow to paediatric renal biopsy reports, a domain chosen for its constrained diagnostic scope and well-defined underlying biology.<n>We develop the workflow iteratively with clinical oversight across three meetings, manually annotating 400 reports from a dataset of 2,111 at Great Ormond Street Hospital as a gold standard, while developing an automated information extraction approach using SLMs.
  arXiv  Detail & Related papers  (2026-04-05T16:15:39Z)
• HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Data [4.776184995012808]
  We propose an agentic framework that decomposes complex oncology data extraction into modular, adaptive tasks.<n> Evaluated on a large-scale dataset of over 400,000 unstructured clinical notes and scanned PDF reports spanning 2,250 cancer patients, our method achieves an average F1-score of 0.93.
  arXiv  Detail & Related papers  (2025-12-22T20:38:30Z)
• OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents Archive [50.468138755368805]
  Opioid crisis represents a significant moment in public health.<n>Data and documents disclosed in the UCSF-JHU Opioid Industry Documents Archive (OIDA)<n>In this paper, we tackle this challenge by organizing the original dataset according to document attributes.
  arXiv  Detail & Related papers  (2025-11-13T03:27:32Z)
• HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis [55.2480439325792]
  HySemRAG is a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG)<n>System addresses limitations in existing RAG architectures through a multi-layered approach.
  arXiv  Detail & Related papers  (2025-08-01T20:30:42Z)
• Radiology Report Generation Using Transformers Conditioned with Non-imaging Data [55.17268696112258]
  This paper proposes a novel multi-modal transformer network that integrates chest x-ray (CXR) images and associated patient demographic information. The proposed network uses a convolutional neural network to extract visual features from CXRs and a transformer-based encoder-decoder network that combines the visual features with semantic text embeddings of patient demographic information.
  arXiv  Detail & Related papers  (2023-11-18T14:52:26Z)
• Towards Unifying Anatomy Segmentation: Automated Generation of a Full-body CT Dataset via Knowledge Aggregation and Anatomical Guidelines [113.08940153125616]
  We generate a dataset of whole-body CT scans with $142$ voxel-level labels for 533 volumes providing comprehensive anatomical coverage. Our proposed procedure does not rely on manual annotation during the label aggregation stage. We release our trained unified anatomical segmentation model capable of predicting $142$ anatomical structures on CT data.
  arXiv  Detail & Related papers  (2023-07-25T09:48:13Z)
• Detecting automatically the layout of clinical documents to enhance the performances of downstream natural language processing [53.797797404164946]
  We designed an algorithm to process clinical PDF documents and extract only clinically relevant text. The algorithm consists of several steps: initial text extraction using a PDF, followed by classification into such categories as body text, left notes, and footers. Medical performance was evaluated by examining the extraction of medical concepts of interest from the text in their respective sections.
  arXiv  Detail & Related papers  (2023-05-23T08:38:33Z)
• Event-based clinical findings extraction from radiology reports with pre-trained language model [0.22940141855172028]
  We present a new corpus of radiology reports annotated with clinical findings. The gold standard corpus contained a total of 500 annotated computed tomography (CT) reports. We extracted triggers and argument entities using two state-of-the-art deep learning architectures, including BERT.
  arXiv  Detail & Related papers  (2021-12-27T05:03:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.