321P Survival GNNs using virtually multiplexed IHC and H&E-stained consecutive tissue sections

Evaluating potential data losses from mapping proprietary medical data formats to standards is essential for decision making. The article implements a method to evaluate the preliminary content overlap of proprietary medical formats, including national terminologies and Fast Healthcare Interoperability Resources (FHIR)-international medical standard. Three types of mappings were evaluated in the article: proprietary format matched to FHIR, national terminologies matched to the FHIR mappings, and concepts from national terminologies matched to Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT). We matched attributes of the formats with FHIR definitions and calculated content overlap. The article reports the results of a manual mapping between a proprietary medical format and the FHIR standard. The following results were obtained: 81% of content overlap for the proprietary format to FHIR mapping, 88% of content overlap for the national terminologies to FHIR mapping, and 98.6% of concepts matching can be reached from national terminologies to SNOMED CT mapping. Twenty tables from the proprietary format and 20 dictionaries were matched with FHIR resources; nine dictionaries were matched with SNOMED CT concepts. Mapping medical formats is a challenge. The obtained overlaps are promising in comparison with the investigated results. The study showed that standardization of data exchange between proprietary formats and FHIR is possible in Russia, and national terminologies can be used in FHIR-based information systems.

IntroductionInteroperability in healthcare is a fundamental principle for scalable deployment of novel tools. Fast Healthcare Interoperability Resources (FHIR) comprise data specifications and an application processing interface (API) for the secure...

ObjectiveTo assess whether HL7 Fast Healthcare Interoperability Resources (FHIR) can underpin a fully standards-based, end-to-end digital research architecture, demonstrate it in a live study, and quantify its benefits for interoperability and development efficiency.Materials and MethodsWe designed a generalizable standards-based architecture to accelerate digital health research relying on FHIR as the sole transactional model throughout a participant research lifecycle starting from API-based study discovery to results. It was instantiated for People Heart Study, a real-world digital health cardiovascular-risk assessment study with its protocol transformed into FHIR resources (eligibility, consent, tasks, and results). Evaluation examined workflow coverage, validator conformance across independent servers, and points requiring custom extensions or app logic.ResultsThe architecture was implemented using cloud managed FHIR stores including an illustrative public research discovery API for first-/third-party apps. A participant-facing iOS app was published on the App Store. Our evaluation reveals that 6 of 10 research app workflows could be executed entirely from FHIR artifacts; 2 were partially standards-driven and 2 remained limited requiring custom development. All FHIR resources passed structural, semantic validation with minimal custom extension usage and terminology integrity issues.DiscussionOur approach addresses persistent challenges in digital health research by enhancing data interoperability, minimizing redundant development, and supporting the full research lifecycle. The architecture aligns with national priorities and complements healthcare standardization efforts.ConclusionBy leveraging FHIR, our architecture enables generalizability, interoperability, and reuse across diverse digital health research contexts, transforming study design into data modeling rather than software development, and fostering a more inclusive and agile digital health ecosystem.

Over the past decade, Fast Healthcare Interoperability Resources (FHIR) have become increasingly relevant in health care data standardization. However, the complex structure of FHIR makes cohort analytics with many-to-many relations extremely time-consuming, and, impossible in many cases. To support exploratory cohort building and data visualization in oncology, especially for nontechnical users, we developed the DermaDashboard, an interactive dashboard built on top of a relational FHIR-compliant PostgreSQL database. Relevant oncology data was preaggregated with a materialized view, and the subsequent visualization layer was implemented using an open-source visualization tool, enabling clinicians to filter and analyze data without requiring familiarity with FHIR or SQL. The database encompassed data from 3949 patients with melanoma and included 82,783 health records. Core FHIR resources were Patient, DiagnosticReport, and QuestionnaireResponse, with 54 mapped attributes spanning demographics, stagings, mutations, and treatments. The resulting dashboard allowed filtering across 29 variables to construct subcohorts and generate aggregation analyses. This implementation shows how open interoperability data standards, such as FHIR, can be used in the development of modular, user-friendly clinical dashboards for cohort analysis, and the architecture demonstrates a feasible path toward democratizing access to structured health care data.

BackgroundKnowledge graphs (KGs) play a key role to enable explainable artificial intelligence (AI) applications in healthcare. Constructing clinical knowledge graphs (CKGs) against heterogeneous electronic health records (EHRs) has been desired by the research and healthcare AI communities. From the standardization perspective, community-based standards such as the Fast Healthcare Interoperability Resources (FHIR) and the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) are increasingly used to represent and standardize EHR data for clinical data analytics, however, the potential of such a standard on building CKG has not been well investigated. ObjectiveTo develop and evaluate methods and tools that expose the OMOP CDM-based clinical data repositories into virtual clinical KGs that are compliant with FHIR Resource Description Framework (RDF) specification. MethodsWe developed a system called FHIR-Ontop-OMOP to generate virtual clinical KGs from the OMOP relational databases. We leveraged an OMOP CDM-based Medical Information Mart for Intensive Care (MIMIC-III) data repository to evaluate the FHIR-Ontop-OMOP system in terms of the faithfulness of data transformation and the conformance of the generated CKGs to the FHIR RDF specification. ResultsA beta version of the system has been released. A total of more than 100 data element mappings from 11 OMOP CDM clinical data, health system and vocabulary tables were implemented in the system, covering 11 FHIR resources. The generated virtual CKG from MIMIC-III contains 46,520 instances of FHIR Patient, 716,595 instances of Condition, 1,063,525 instances of Procedure, 24,934,751 instances of MedicationStatement, 365,181,104 instances of Observations, and 4,779,672 instances of CodeableConcept. Patient counts identified by five pairs of SQL (over the MIMIC database) and SPARQL (over the virtual CKG) queries were identical, ensuring the faithfulness of the data transformation. Generated CKG in RDF triples for 100 patients were fully conformant with the FHIR RDF specification. ConclusionThe FHIR-Ontop-OMOP system can expose OMOP database as a FHIR-compliant RDF graph. It provides a meaningful use case demonstrating the potentials that can be enabled by the interoperability between FHIR and OMOP CDM. Generated clinical KGs in FHIR RDF provide a semantic foundation to enable explainable AI applications in healthcare.

The process of maintenance of an underlying semantic model that supports data management and addresses the interoperability challenges in the domain of telemedicine and integrated care is not a trivial task when performed manually. We present a methodology that leverages the provided serializations of the Health Level Seven International (HL7) Fast Health Interoperability Resources (FHIR) specification to generate a fully functional OWL ontology along with the semantic provisions for maintaining functionality upon future changes of the standard. The developed software makes a complete conversion of the HL7 FHIR Resources along with their properties and their semantics and restrictions. It covers all FHIR data types (primitive and complex) along with all defined resource types. It can operate to build an ontology from scratch or to update an existing ontology, providing the semantics that are needed, to preserve information described using previous versions of the standard. All the results based on the latest version of HL7 FHIR as a Web Ontology Language (OWL-DL) ontology are publicly available for reuse and extension.

Health Level 7’s (HL7’s) new standard, FHIR (Fast Health Interoperability Resources), is setting healthcare information technology and medical imaging specifically ablaze with excitement. This paper aims to describe the protocol’s advantages in some detail and explore an easy path for those unfamiliar with FHIR to begin learning the standard using free, open-source tools, namely the HL7 application programming interface (HAPI) FHIR server and the SIIM Hackathon Dataset.

The Fast Healthcare Interoperability Resources (FHIR) and Clinical Document Architecture (CDA) are standards for the healthcare industry, designed to improve the exchange of health data by interoperability. Both standards are constrained through what are known as Implementation Guides (IG) for specific use. Both of these two standards are widely in use and play an important role in the Austrian healthcare system. Concepts existing in CDA and FHIR must be aligned between both standards. Many existing approaches are presented and discussed, none are fully suited to the needs in Austria. The IG Publisher has already been used for CDA IGs, beside of its intended FHIR support, but never for both in one IG. Even the International Patient Summary (IPS), existing as CDA and FHIR specification, does not solve the needed comparability between these two. As the IG Publisher is widely used and supports CDA, it should be used for Dual Implementation Guides. Further work and extension of IG Publisher is necessary to enhance the readability of the resulting IGs.

ABSTRACTObjectiveMedication errors are the third leading cause of death. There are several methods to prevent prescription errors, one of which is to use a Computerized Physician Order Entry system (CPOE). In a CPOE system, necessary data needs to be collected so that making decisions about prescribing medications and treatment plans could be made. Although many CPOE systems have been developed worldwide, studies have yet to identify the necessary data and data elements of CPOE systems. This study aims to identify data elements of CPOE and standardize these data with Fast Healthcare Interoperability Resources (FHIR) to facilitate data sharing and integration with the electronic health record (EHR) system and reduce data diversity.MethodsPubMed, Web of Science, Embase, and Scopus databases for studies up to October 2019 were searched. Two reviewers independently assessed original articles to determine eligibility for inclusion in this review. All articles describing data elements of a COPE system were included. Data elements were obtained from the included articles’ text, tables, and figures.Classification of the extracted data elements and mapping them to FHIR was done to facilitate data sharing and integration with the electronic health record (EHR) system and reduce data diversity. The final data elements of CPOE were categorized into five main categories of FHIR (foundation, base, clinical, financial, and specialized) and 146 resources, where possible. One of the researchers did mapping and checked and verified by the second researcher. If a data element could not be mapped to any FHIR resources, this data element was considered an extension to the most relevant resource.ResultsWe retrieved 5162 articles through database searches. After the full-text assessment, 21 articles were included. In total, 270 data elements were identified and mapped to the FHIR standard. These elements have been reported in 26 FHIR resources of 146 ones (18%). In total, 71 data elements were considered an extension.ConclusionsThe results of this study showed that the same data elements were not used in the CPOE systems, and the degree of homogeneity of these systems is limited. The mapping of extracted data with data elements used in the FHIR standard shows the extent to which these systems comply with existing standards. Considering the standards in these systems’ design helps developers design more coherent systems that can share data with other systems.

BackgroundSemantic interoperability is essential for improving data quality and sharing. The ISO/IEC 11179 Metadata Registry (MDR) standard has been highlighted as a solution for standardizing and registering clinical data elements (DEs). However, the standard model has both structural and semantic limitations, and the number of DEs continues to increase due to poor term reusability. Semantic types and constraints are lacking for comprehensively describing and evaluating DEs on real-world clinical documents.MethodsWe addressed these limitations by defining three new types of semantic relationship (dependency, composite, and variable) in our previous studies. The present study created new and further extended existing semantic types (hybrid atomic and repeated and dictionary composite common data elements [CDEs]) with four constraints: ordered, operated, required, and dependent. For evaluation, we extracted all atomic and composite CDEs from five major clinical documents from five teaching hospitals in Korea, 14 Fast Healthcare Interoperability Resources (FHIR) resources from FHIR bulk sample data, and MIMIC-III (Medical Information Mart for Intensive Care) demo dataset. Metadata reusability and semantic interoperability in real clinical settings were comprehensively evaluated by applying the CDEs with our extended semantic types and constraints.ResultsAll of the CDEs (n = 1142) extracted from the 25 clinical documents were successfully integrated with a very high CDE reuse ratio (46.9%) into 586 CDEs (259 atomic and 20 unique composite CDEs), and all of CDEs (n = 238) extracted from the 14 FHIR resources of FHIR bulk sample data were successfully integrated with high CDE reuse ration (59.7%) into 96 CDEs (21 atomic and 28 unique composite CDEs), which improved the semantic integrity and interoperability without any semantic loss. Moreover, the most complex data structures from two CDE projects were successfully encoded with rich semantics and semantic integrity.ConclusionMDR-based extended semantic types and constraints can facilitate comprehensive representation of clinical documents with rich semantics, and improved semantic interoperability without semantic loss.

Background The current gap between the availability of routine imaging data and its provisioning for medical research hinders the utilization of radiological information for secondary purposes. To address this, the German Medical Informatics Initiative (MII) has established frameworks for harmonizing and integrating clinical data across institutions, including the integration of imaging data into research repositories, which can be expanded to routine imaging data.Objectives This project aims to address this gap by developing a large-scale data processing pipeline to extract, convert, and pseudonymize DICOM (Digital Imaging and Communications in Medicine) metadata into “ImagingStudy” Fast Healthcare Interoperability Resources (FHIR) and integrate them into research repositories for secondary use.Methods The data processing pipeline was developed, implemented, and tested at the Data Integration Center of the University Hospital Erlangen. It leverages existing open-source solutions and integrates seamlessly into the hospital's research IT infrastructure. The pipeline automates the extraction, conversion, and pseudonymization processes, ensuring compliance with both local and MII data protection standards. A large-scale evaluation was conducted using the imaging studies acquired by two departments at University Hospital Erlangen within 1 year. Attributes such as modality, examined body region, laterality, and the number of series and instances were analyzed to assess the quality and availability of the metadata.Results Once established, the pipeline processed a substantial dataset comprising over 150,000 DICOM studies within an operational period of 26 days. Data analysis revealed significant heterogeneity and incompleteness in certain attributes, particularly the DICOM tag “Body Part Examined.” Despite these challenges, the pipeline successfully generated valid and standardized FHIR, providing a robust basis for future research.Conclusion We demonstrated the setup and test of a large-scale end-to-end data processing pipeline that transforms DICOM imaging metadata directly from clinical routine into the Health Level 7-FHIR format, pseudonymizes the resources, and stores them in an FHIR server. We showcased that the derived FHIRs offer numerous research opportunities, for example, feasibility assessments within Bavarian and Germany-wide research infrastructures. Insights from this study highlight the need to extend the “ImagingStudy” FHIR with additional attributes and refine their use within the German MII.

Interoperability is recognized as an essential factor for the success of a Health Information System. Common standards can achieve interoperability, deciphering the meaning of the data exchanged. The general criterion that can be used is FHIR (Fast Healthcare Interoperability Resources). Data exchange with this standard is considered adequate and efficient when using the GraphQL approach because the client efficiently manages the requests he wants according to the data schema that has been defined. In addition, the Health Information System is said to be successful if electronic medical record data is always available if you want to use it. Therefore a storage system is needed to maintain the data's existence. The blockchain-based storage method with BigchainDB can solve this problem. These three technologies (FHIR, BigchainDB and GraphQL) are expected to produce a service-based system that can be used to exchange international standard electronic medical record data and can be applied across various systems. As a result, on one server node, the time required to read data is 0.32 ms, and the time needed to insert data is 47 ms. On three server nodes, the time necessary to read data is 0.175 ms and the time required to insert data is 1430 ms. The data insert process is relatively long because of the mechanism for creating a signature key for each data stored and the distribution of data to all nodes (more than one node system) interconnected in BigchainDB storage.

The conversion of unstructured clinical data into structured formats, such as Fast Healthcare Interoperability Resources (FHIR), is a critical challenge in healthcare informatics. This study explores the potential of large language models (LLMs) to automate this conversion process, aiming to enhance data interoperability and improve healthcare outcomes. The effectiveness of various LLMs in converting clinical reports into FHIR bundles was evaluated using different prompting techniques, including iterative correction and example-based prompting. The findings demonstrate the critical role of prompt engineering, with the two-step approach shown to significantly improve accuracy and completeness. While few-shot learning enhanced performance, it also introduced a risk of overreliance on examples. The performance of the LLMs is assessed based on the precision, hallucination rate, and resource mapping accuracy across mammography and dermatological reports from two clinics, providing insights into effective strategies for reliable FHIR data conversion and highlighting the importance of tailored prompting strategies.

Electronic health records (EHRs) constitute vital statistics, current health condition, ongoing therapies, and patient data; hence, their interoperability could be useful for epidemiologic and clinical research. Fast Healthcare Interoperability Resources (FHIR) and blockchain are currently "in-use" and tested for exchange of such data. The annual scientific production of publications for both FHIR and blockchain shows steady growth. The data interoperability and electronic data interchange have been introduced in the field of EHR in 2020, hence inferring that data interoperability is relatively a new domain. The thematic mapping suggested "interoperability" of EHR is well-developed and important for the structure of the research field.

<sec> <title>UNSTRUCTURED</title> Japan has universal coverage and designated pediatric oncology centers, yet the childhood cancer information ecosystem remains a “black box.” The incidence is measurable, but treatment exposure and long-term follow-up are not reliably linked across hospitals, registries, and survivorship services. The World Health Organization (WHO) CureAll framework highlights information governance as a lever for equity. This study aims to propose a formative design for national digital governance connecting registries, clinical systems, and survivorship in Japan. We synthesized international guidance and Japanese statutes, plans, and registry reports. Drawing on operational experience, we specified a minimal pediatric dataset, an HL7 Fast Healthcare Interoperability Resources (FHIR)–based interoperability architecture, and governance to align standards, consent, and data use. No new empirical data were collected. We outline a 4-layer architecture. Source systems (electronic health records, laboratory and radiology systems, pathology, and cooperative group databases) feed an HL7 FHIR gateway. A national Pediatric Data Steward governs standards and interoperability (FHIR profiles and application programming interfaces), terminology and coding (International Classification of Diseases for Oncology and International Classification of Childhood Cancer, with mappings to Systematized Nomenclature of Medicine–Clinical Terms and Logical Observation Identifiers Names and Codes), privacy and consent, data-use agreements, data quality, and audit. Outputs flow to the National and Hospital-based Cancer Registries and a patient-facing Digital Survivorship Passport, with bidirectional clinic updates and linkage to the resident registry and vital statistics. Security, audit, and public reporting span all layers. We define pediatric indicators and a staged road map. Transforming Japan’s pediatric oncology information into a learning system is chiefly a governance task. A Pediatric Data Steward, a harmonized pediatric data dictionary via FHIR, and a portable survivorship passport with layered consent can improve timeliness, completeness, follow-up, and transparency. </sec>