FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support

Evidence-based clinical guidelines are essential for high-quality care yet translating them into personalized clinical decision support remains resource-intensive and time-consuming. Large language models (LLMs) show promise for supporting clinical decision-making, but their limited access to patient-specific data and explicit guideline sources constrains trustworthiness, personalization, and clinical applicability. Retriev-al-augmented generation (RAG) addresses part of this challenge by grounding model outputs in curated evidence sources; however, true personalization requires structured access to electronic health record data. This study presents FHIR-RAG-MEDS, a medical decision support system that integrates HL7 Fast Healthcare Interoperability Resources (FHIR) with a RAG-enhanced LLM to enable patient-specific, guideline-concordant clinical recommendations. Through SMART on FHIR, the system retrieves real-time patient data from FHIR servers, generates structured medical summaries, and incorpo-rates this personalized context into the RAG pipeline, grounding responses in evi-dence-based clinical guidelines stored in a vector database. FHIR-RAG-MEDS was evaluated using 70 physician-generated clinical questions covering dementia, chronic obstructive pulmonary disease, hypertension, and sarcopenia. Performance was assessed using automated metrics, RAG-specific evaluation frameworks, and independent expert physician review. The system consistently outperformed state-of-the-art medical LLMs, demonstrating higher semantic accuracy, improved faithfulness to guideline content, and stronger clinical relevance. Integrating HL7 FHIR with RAG-based LLMs enables trustworthy, personalized clinical decision support, bridging the gap between static language models and real-world, patient-centered care.