mlsanityData to 14 Oct 2026

Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QA

arXiv 2602.00009 ↗First posted 27 Nov 2025cs.CL cs.AI cs.IRcited by 1

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

Abstract (arXiv)

Electronic health record (EHR) systems present clinicians with vast repositories of clinical information, creating a significant cognitive burden where critical details are easily overlooked. While Large Language Models (LLMs) offer transformative potential for data processing, they face significant limitations in clinical settings, particularly regarding context grounding and hallucinations. Current solutions typically isolate retrieval methods focusing either on structured data (SQL/Cypher) or unstructured semantic search but fail to integrate both simultaneously. This work presents MediGRAF (Medical Graph Retrieval Augmented Framework), a novel hybrid Graph RAG system that bridges this gap. By uniquely combining Neo4j Text2Cypher capabilities for structured relationship traversal with vector embeddings for unstructured narrative retrieval, MediGRAF enables natural language querying of the complete patient journey. Using 10 patients from the MIMIC-IV dataset (generating 5,973 nodes and 5,963 relationships), we generated enough nodes and data for patient level question answering (QA), and we evaluated this architecture across varying query complexities. The system demonstrated 100% recall for factual queries which means all relevant information was retrieved and in the output, while complex inference tasks achieved a mean expert quality score of 4.25/5 with zero safety violations. These results demonstrate that hybrid graph-grounding significantly advances clinical information retrieval, offering a safer, more comprehensive alternative to standard LLM deployments.

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 19 of its 45 references that are in the map. First posted on arXiv 27 Nov 2025.

Builds on

19 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation8 Aug
  2. 2023Almanac: Retrieval-Augmented Language Models for Clinical Medicine1 Mar

Other references · 17

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2019Publicly Available Clinical BERT Embeddingscited by 1,002
  8. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  9. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  10. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 388
  11. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 265
  12. 2016Language to Logical Form with Neural Attentioncited by 158
5 more
  1. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncited by 93
  2. 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 77
  3. 2024Text2Cypher: Bridging Natural Language and Graph Databasescited by 30
  4. 2018A Comparison of Word Embeddings for the Biomedical Natural Language Processingcited by 29
  5. 2019SECNLP: A Survey of Embeddings in Clinical Natural Language Processingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IVcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge
  2. 2026Harnessing Large Language Models for Precision Querying and Retrieval-Augmented Knowledge Extraction in Clinical Data Science
  3. 2026CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain
  4. 2024REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models
  5. 2026A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench
  6. 2026EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records
  7. 2026Hybrid-IR: Dual-Path Hybrid Retrieval with Iterative Reasoning for Complex Medical Question Answering
  8. 2025ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems