ePI Digital Solutions addresses the challenge of critical pharmaceutical knowledge being trapped in non-structured formats like PDFs and offers a solution to convert this data into validated, structured FHIR R5 XML. This capability is crucial for adapting to the transition toward electronic Product Information (ePI) within the European Union.
This paper addresses the complex challenges of integrating and ensuring interoperability of healthcare data, which is exacerbated by the rapid adoption of Artificial Intelligence (AI). It proposes a new data integration model leveraging HL7 FHIR standards combined with cloud APIs to achieve optimal patient care while maintaining regulatory compliance.
This article introduces a configurable Model Context Protocol (MCP) server designed to interact with FHIR APIs. The server enhances security and usability by incorporating AI-powered clinical insights, detailed resource management, and support for multiple authentication methods.
This study proposes the 'FHIR-RAG-MEDS' system, which integrates Health Level 7 FHIR with a Retrieval-Augmented Generation (RAG)-based system. The goal is to improve personalized medical decision support based on evidence-based clinical guidelines.
Rad AI Reporting utilizes deep-linking via a custom protocol to directly access specific FHIR resources within the desktop application. This streamlines the report creation process linked to data such as ImagingStudy.
This article demonstrates how detailed breast lesion data, such as from mammography, is structured using the FHIR Observation resource. It presents specific data elements to show a mechanism where clinical findings (like BIRADS assessment) are electronically recorded and exchanged according to standard specifications.
FHIRInternational🏛University of Augsburg; BIFOLD – Berlin Institute for the Foundations of Learning and Data; Technische Universität Berlin; German Research Center for Artificial Intelligence (DFKI); Charité - UniversiEnrichedSep 8, 2025
A team of universities and research institutions proposed 'Infherno,' a new framework for end-to-end synthesis of FHIR resources from unstructured clinical notes. The system utilizes LLM agents and code execution to overcome limitations of previous methods, such as limited generalizability.
EldoNova+ offers solutions utilizing Fast Healthcare Interoperability Resources (FHIR) to solve challenges in data exchange and application development across healthcare institutions. This enables seamless integration with Electronic Health Records (EHR) and improves patient information management, facilitating advanced healthcare operations.
HL7 has published the code system 'Diagnostic Service Section ID,' which defines specific sections of diagnostic services in clinical records. This code system is used in HL7 v2.x messages' OBR and OM4 segments, standardizing the types of tests or examinations performed by healthcare institutions.
Healthcare organizations can achieve advanced interoperability by adopting open standards like FHIR and establishing data exchange and governance. This is a strategic priority that improves care coordination and supports decision-making.
HL7 has published the definition for the code system 'Type of Referenced Data (2.3.1 - 1.2.0)', which declares the general type of media data that is encoded. Although it was used in versions prior to v2.5.1 and later replaced by IANA media types, it remains an important referenced specification.
A unified standard, SMART on FHIR, championed by Professor Ken Mandl, is profoundly impacting electronic health records. This standardization allows medical data and applications to be easily shared on a common platform, realizing a future that improves efficiency in healthcare settings and enhances patient self-management capabilities.
In a healthcare setting facing data sharing challenges, a development team enhanced the reference information within FHIR's EpisodeOfCare resources. This embedded contextual details like patient identifiers and facility names, significantly improving data searchability, usability, and interoperability across multiple systems.
This presentation proposes a solution to healthcare interoperability challenges using platform engineering principles. It details how an AI-enhanced, multi-layered architecture based on FHIR can securely and efficiently share fragmented patient data.
This paper presents a prototype ETL pipeline that uses pure functions to enrich patient data. The pipeline focuses on the process of converting Electronic Health Record (EHR) data into a knowledge graph, utilizing HL7 FHIR resources and RDF.
Researchers developed an open-source compiler called MaLaC-HD to solve the performance issues of executing FHIR Mapping Language (FML). This tool compiles FML code into Python, achieving data transformation speeds nearly 100 times faster than existing tools.
This page provides information regarding an HL7 FHIR converter offered by the AI, ChatGPT. Users can utilize this tool to handle healthcare data according to standard specifications.
WHO released the data dictionary for SMART DAK PNC (v1.0.0). This guide defines a minimum set of data corresponding to various workflow points in the PNC process, usable for service delivery and decision support logic implementation. It is based on the FHIR R4 standard.