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

• URL: http://arxiv.org/abs/2506.13800v1
• Date: Fri, 13 Jun 2025 04:07:19 GMT
• Title: Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework
• Authors: Abul Ehtesham, Aditi Singh, Saket Kumar,
• Abstract summary: This paper presents an open-source framework that integrates Large Language Models (LLMs) with HL7 FHIR data via the Model Context Protocol (MCP)<n>The proposed method delivers scalable, explainable, and interoperable AI-powered EHR applications.
• Score: 0.9246281666115259
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes [37.88754205269813]
  We propose an end-to-end framework powered by LLM agents, code execution, and healthcare terminology database tools to address these issues.<n>Our solution, called Infherno, is designed to adhere to the FHIR document schema and competes well with a human baseline in predicting FHIR resources from unstructured text.
  arXiv  Detail & Related papers  (2025-07-16T14:06:51Z)
• Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support [11.927390747231588]
  This paper explores the application of advanced language models to leverage diverse data sources for improved clinical decision support.<n>We will discuss how text-based features, often overlooked in traditional high dimensional EHR analysis, can provide semantically rich representations.
  arXiv  Detail & Related papers  (2025-06-01T05:07:51Z)
• Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings [44.99833362998488]
  This paper introduces CXR-TextInter, a novel framework that repurposes powerful text-centric language models for chest X-rays interpretation.<n>We augment this LLM-centric approach with an integrated medical knowledge module to enhance clinical reasoning.<n>Our work validates an alternative paradigm for medical image AI, showcasing the potential of harnessing advanced LLM capabilities.
  arXiv  Detail & Related papers  (2025-05-03T06:18:12Z)
• ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration [14.180987429395584]
  ColaCare is a framework that enhances Electronic Health Record (EHR) modeling through multi-agent collaboration driven by Large Language Models (LLMs)<n>Our approach seamlessly integrates domain-specific expert models with LLMs to bridge the gap between structured EHR data and text-based reasoning.
  arXiv  Detail & Related papers  (2024-10-03T14:55:22Z)
• FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models [54.09244105445476]
  This study introduces a novel knowledge injection approach, FedKIM, to scale the medical foundation model within a federated learning framework.<n>FedKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model.<n>Our experiments across twelve tasks in seven modalities demonstrate the effectiveness of FedKIM in various settings.
  arXiv  Detail & Related papers  (2024-08-17T15:42:29Z)
• Multimodal Fusion of EHR in Structures and Semantics: Integrating Clinical Records and Notes with Hypergraph and LLM [39.25272553560425]
  We propose a new framework called MINGLE, which integrates both structures and semantics in EHR effectively. Our framework uses a two-level infusion strategy to combine medical concept semantics and clinical note semantics into hypergraph neural networks. Experiment results on two EHR datasets, the public MIMIC-III and private CRADLE, show that MINGLE can effectively improve predictive performance by 11.83% relatively.
  arXiv  Detail & Related papers  (2024-02-19T23:48:40Z)
• REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models [19.62552013839689]
  Existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge. We propose REALM, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR representations. Our experiments on MIMIC-III mortality and readmission tasks showcase the superior performance of our REALM framework over baselines.
  arXiv  Detail & Related papers  (2024-02-10T18:27:28Z)
• Automated Fusion of Multimodal Electronic Health Records for Better Medical Predictions [48.0590120095748]
  We propose a novel neural architecture search (NAS) framework named AutoFM, which can automatically search for the optimal model architectures for encoding diverse input modalities and fusion strategies. We conduct thorough experiments on real-world multi-modal EHR data and prediction tasks, and the results demonstrate that our framework achieves significant performance improvement over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-20T15:14:14Z)
• Multi-Site Clinical Federated Learning using Recursive and Attentive Models and NVFlare [13.176351544342735]
  This paper develops an integrated framework that addresses data privacy and regulatory compliance challenges. It includes the development of an integrated framework that addresses data privacy and regulatory compliance challenges while maintaining elevated accuracy and substantiating the efficacy of the proposed approach.
  arXiv  Detail & Related papers  (2023-06-28T17:00:32Z)
• Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching [49.78442796596806]
  We propose an innovative privacy-aware data augmentation approach for patient-trial matching (LLM-PTM) Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%.
  arXiv  Detail & Related papers  (2023-03-24T03:14:00Z)
• Modular Clinical Decision Support Networks (MoDN) -- Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments [46.434488407226155]
  We propose Modular Clinical Decision Support Networks (MoDN) MoDN allows flexible, privacy-preserving learning across IIO datasets. It creates dynamic personalised representations of patients, and can make multiple predictions of diagnoses.
  arXiv  Detail & Related papers  (2022-11-12T11:10:46Z)
• MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation [110.31526448744096]
  We argue that unlocking this potential requires a systematic way to measure the performance of medical AI models on large-scale heterogeneous data. We are building MedPerf, an open framework for benchmarking machine learning in the medical domain.
  arXiv  Detail & Related papers  (2021-09-29T18:09:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.