Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework

2025-06-13

AI Summary

This study addresses critical challenges in digital health—including insufficient clinical decision support (CDS), excessive documentation burden, and low patient health literacy—by proposing an open-source, agent-based framework integrating the Model Context Protocol (MCP) with the HL7 FHIR R4 standard. Methodologically, it introduces the first MCP-FHIR declarative configuration mechanism, enabling dynamic binding of large language models (LLMs) to FHIR resources, interpretable reasoning, and format-agnostic interaction. Validation is conducted within a FHIR-compliant environment using SMART-on-FHIR sandbox-synthesized data, demonstrating real-time EHR summarization, role-specific (clinician/patient/caregiver) personalized health information generation, and robust CDS capabilities. The key contributions include overcoming limitations of static clinical workflows while ensuring privacy preservation, interoperability, reproducibility, and system scalability. Empirical results indicate substantial reduction in documentation overhead, improved clinical efficiency, and enhanced patient health literacy.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Enhancing clinical decision support (CDS), reducing documentation burdens, and improving patient health literacy remain persistent challenges in digital health. This paper presents an open-source, agent-based framework that integrates Large Language Models (LLMs) with HL7 FHIR data via the Model Context Protocol (MCP) for dynamic extraction and reasoning over electronic health records (EHRs). Built on the established MCP-FHIR implementation, the framework enables declarative access to diverse FHIR resources through JSON-based configurations, supporting real-time summarization, interpretation, and personalized communication across multiple user personas, including clinicians, caregivers, and patients. To ensure privacy and reproducibility, the framework is evaluated using synthetic EHR data from the SMART Health IT sandbox (https://r4.smarthealthit.org/), which conforms to the FHIR R4 standard. Unlike traditional approaches that rely on hardcoded retrieval and static workflows, the proposed method delivers scalable, explainable, and interoperable AI-powered EHR applications. The agentic architecture further supports multiple FHIR formats, laying a robust foundation for advancing personalized digital health solutions.

Problem

• Enhancing clinical decision support using LLMs and FHIR
• Reducing EHR documentation burdens through dynamic data extraction
• Improving patient health literacy with personalized EHR communication

Innovation

• Integrates LLMs with FHIR via MCP
• Uses JSON configs for FHIR access
• Agentic architecture supports multiple FHIR formats