1,676 FHIR-related articles (latest first)
As Artificial Intelligence (AI) expands into healthcare, challenges related to data acquisition, interoperability, and privacy are emerging. Solving these issues requires building a standardized 'single data platform' that integrates data from multiple sources.
A new fog-computing medical data gateway, the B-Health IoT Box, successfully demonstrated its ability to harmonize large volumes of health and well-being data from diverse devices. This marks a significant step toward building interoperable digital health ecosystems by addressing fragmented data streams and incompatible protocols.
Talend Data Mapper supports the import of FHIR specifications. For performance reasons, certain elements may be ignored during this process, but they can easily be recreated afterward.
Te Aho o Te Kahu has published a FHIR ValueSet defining the clinical N stage for female genital corpus uteri sarcoma, based on the AJCC cancer staging manual (8th edition). This resource standardizes the regional lymph node status (cN) before treatment initiation, aiding medical information exchange.
Equideum Health has introduced FHIRBlocks, a solution that enables fine-grained consent management for health data. This allows developers to rapidly build new applications while reducing compliance risks for organizations like providers and payers.
This article emphasizes that digital health companies must build scalable FHIR integration infrastructure capable of supporting multiple EHR vendors and emerging AI use cases. Early adoption is crucial, transforming the capability from a one-off IT project into a long-term competitive advantage.
Firely released .NET SDK 6 to address challenges in handling FHIR data. This version unifies two previously separate data models, POCO and ITypedElement, creating a more flexible and future-proof structure.
Google has accelerated its development cycle, releasing an early preview of Android 16. This update includes features such as the ability for medical apps to read and write health data using the FHIR standard, which is relevant to building electronic patient record systems in Japan.
Google provides a de-identification function for FHIR data, as well as DICOM images and metadata, through the Cloud Healthcare API. This tool is intended only for demonstration purposes and does not call the actual de-identification API.
Computable Publishing LLC provides the 'FEvIRยฎ: Resource Viewer,' an environment for viewing FHIR-based resources. This tool enables data display based on FHIR and EBMonFHIR IGs.
The European healthcare business intelligence (BI) market is growing, driven by the shift to value-based care models and EU-level interoperability initiatives. The adoption of standards like HL7 FHIR enables cross-border analysis, contributing to cost containment and quality improvement.
The article explains the technical flow for asynchronous FHIR operations, where clients initiate jobs and servers execute them in the background. This prevents system blocking, enabling reliable processing of large volumes of data or reindexing.
The Cloud Healthcare API bridges the gap between care systems and applications built on Google Cloud. By utilizing this API, it becomes possible to ingest industry-standard data formats like FHIR and HL7v2, enabling advanced utilization for analytics in BigQuery and machine learning.
This guide demonstrates how to process clinical data in Fast Healthcare Interoperability Resources (FHIR) format using Google Cloud's Cloud Healthcare API. By deleting or modifying Personally Identifiable Information (PII) and Protected Health Information (PHI), users can prepare the data for analysis and research while protecting patient privacy.
This paper introduces FHIR Lens, an interactive graph-based platform designed to address the challenge of exploring complex relationships within Electronic Health Record (EHR) data. By leveraging FHIR resources as RDF and utilizing SPARQL for dynamic querying, it enables deep semantic exploration.
Appian, alongside Ignyte Group, announced success in the HL7 AI Challenge, achieving enhanced health data interoperability using AI. Their 'Bring AI to Work(flow)' solution integrates AI into patient and operational workflows, aiming for improved efficiency and cost reduction.
This article analyzes interoperability challenges in medical imaging, arguing that the shift from the traditional messaging standard HL7 V2 to the modern API-based FHIR is essential. While V2 operates on a rigid, 'push' model for data transfer, FHIR utilizes 'pull'-based web APIs to enable AI integration and the creation of true longitudinal patient records.
Health leaders from Southeast Asian countries gathered at RODHS 2025 in India to aim for common standards and safe systems for data exchange. The adoption of Fast Healthcare Interoperability Resources (FHIR) was a key outcome, with nations agreeing to proceed through gradual implementation.
HL7 released a guide detailing the use of FHIR for labeling XML and SPL transitions.
InterSystems provides a function via the class HS.FHIR.DTL.SDA3.vR4.PractitionerRole.PractitionerRole that transforms PractitionerRole data from SDA3 format into vR4 format. This is a technical mechanism designed to ensure interoperability between different versions of data structures.