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

TL;DR

This paper introduces MediGRAF, a hybrid graph retrieval framework that combines structured and unstructured data querying to improve clinical AI safety and accuracy in patient information retrieval.

Contribution

MediGRAF is the first system to integrate Neo4j Text2Cypher with vector embeddings for comprehensive clinical data retrieval, enhancing safety and effectiveness.

Findings

Achieved 100% recall for factual queries.

Attained a mean expert quality score of 4.25/5 on complex inference tasks.

Demonstrated zero safety violations in clinical question answering.

Abstract

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.