FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support
AI · 02.07.2026 · 7 (7) · 246
DOI: 10.3390/ai7070246 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, online erschienen am 02.07.2026. Verfasst von Yildiray Kabak und 9 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.
Abstract (Originalsprache)
Background
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. Retrieval-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.
Methods
This study presents FHIR-RAG-MEDS, a medical decision support system that integrates HL7 Fast Healthcare Interoperability Resources (FHIR) with an 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 incorporates this personalized context into the RAG pipeline, grounding responses in evidence-based clinical guidelines stored in a vector database.
Results
FHIR-RAG-MEDS was evaluated using 139 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.
Conclusions
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.
Förderung
- European Union
Zitieren
APA
Kabak, Y., Erturkmen, G. B. L., Gencturk, M., Namli, T., Sinaci, A. A., Corcoles, R. A., Ballesteros, C. G., Abizanda, P., Atmis, V., & Dogac, A. (2026). FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support. AI, 7(7), 246. https://doi.org/10.3390/ai7070246
Vancouver
Kabak Y, Erturkmen GBL, Gencturk M, Namli T, Sinaci AA, Corcoles RA, et al. FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support. AI. 2026;7(7):246. doi:10.3390/ai7070246
BibTeX
@article{Kabak2026,
author = {Kabak, Yildiray and Erturkmen, Gokce B. Laleci and Gencturk, Mert and Namli, Tuncay and Sinaci, A. Anil and Corcoles, Ruben Alcantud and Ballesteros, Cristina Gómez and Abizanda, Pedro and Atmis, Volkan and Dogac, Asuman},
title = {FHIR-RAG-MEDS: Integrating HL7 FHIR with Retrieval-Augmented Large Language Models for Enhanced Medical Decision Support},
journal = {AI},
year = {2026},
volume = {7},
number = {7},
pages = {246},
doi = {10.3390/ai7070246}
}
EUVIMED