ExpRAG is a novel framework that improves LLM performance in clinical settings by incorporating real patient experiences from Electronic Health Records.

• Leverages retrieval-augmented generation with EHR data for clinical reasoning
• Enhances LLM accuracy for discharge-related questions
• Grounds AI responses in real-world patient contexts rather than just medical textbooks
• Demonstrates how experience-based retrieval outperforms traditional knowledge-only approaches

This research addresses a critical healthcare challenge: ensuring AI can reason with patient-specific contexts, making it more reliable for clinical decision support and potentially reducing medical errors.

Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA