Medical Data Engineering – Theory and Practice

Kock-Schoppenhauer, Ann-Kristin; Schreiweis, Björn; Ulrich, Hans; Reimer, Niklas; Wiedekopf, Joshua; Kinast, Benjamin; Busch, Hauke; Bergh, Björn; Ingenerf, Josef

doi:10.1007/978-3-030-87657-9_21

Cited by 5 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They promise to enhance patient care, advance medical research, and improve clinical decision-making. However, they also pose a formidable challenge -how to effectively harness the vast and diverse data from disparate silos [11]?…”

Section: Introductionmentioning

confidence: 99%

Open Health Knowledge Management Platform: A Comprehensive Evaluation of a Data-centric Approach for Patient Care and Research

Schreiweis,

Kinast,

Ulrich

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background In the evolving landscape of healthcare, the fragmented IT environment poses challenges to data utilization. This paper introduces the Open Health Knowledge Management Platform, designed to overcome data fragmentation, heterogeneity, and interoperability challenges. The platform aims to bridge the gap between research and patient care, showcased through real-world scenarios, emphasizing seamless data integration and collaborative research. The University Hospital Schleswig-Holstein's (UKSH) diverse IT landscape is a specific focus, and the platform proposes a solution to the separation between patient care and research, aligning with the Medical Informatics Initiative’s goal of efficient, unified data access. Methods The study evaluates the "open health knowledge management platform" designed to target data silos and interoperability issues. Utilizing the Framework for Evaluation in Design Science Research (FEDS), three hypotheses guide scenario-based evaluations: data integration, data quality, and scalability. The platform's technical evaluation, centered on interoperability, single-point-of-truth, and real-world scenarios, follows the FEDS framework and ISO/IEC 25000 standard. Three scenarios cardiology, neurology, and radiology are selected for a naturalistic, qualitative evaluation, showcasing the platform's effectiveness. The FEDS components Problem, Solution, Evaluation, and Communication guide a comprehensive understanding and dissemination of the platform's impact. The system architecture emphasizes interoperability, a single point of truth, and use case agnosticism. Results The Open Health Knowledge Management Platform has undergone successful evaluation at UKSH. Demonstrating adaptability across diverse data formats like HL7 V2 messages, CSV exports, and BIDS-formatted EEG data, the platform showed its efficacy in certain real-world scenarios of cardiology, neurology and radiology. Our evaluation confirms the platform’s capacity to bridge gaps between patient care and research data utilization, facilitating collaboration and advancing clinical decision-making. Conclusion Our evaluation of the open health knowledge management platform at UKSH reveals its capabilities in tackling data fragmentation, enhancing interoperability, and enabling seamless knowledge transfer between patient care and research. The platform's architecture and standardized terminologies significantly improved data quality and facilitated robust querying. Challenges notwithstanding, the platform demonstrated reliability in handling diverse data types, integration effectiveness, and scalability, validating our hypotheses. Ongoing development and potential quantitative measures will further enhance its applicability and performance in dynamic health care landscapes.

show abstract

Section: Introductionmentioning

confidence: 99%

Open Health Knowledge Management Platform: A Comprehensive Evaluation of a Data-centric Approach for Patient Care and Research

Schreiweis,

Kinast,

Ulrich

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Current (inter)national initiatives are integrating large volumes of data in clinical environments to enable their use [3][4][5]. The established data integration is close to the data origin which is highly desirable since a late mapping harbors disadvantages and issues can be addressed accordingly [6].…”

Section: Introductionmentioning

confidence: 99%

“…This process is time-consuming and demands a significant number of resources. This process occurs at every site involved, which commits a substantial additional number of stewards and health care professionals across the entire healthcare system [6,7]. Thus, sharing and reusing of these mappings is highly desirable and can release the needed resource and speed up the data enabling.…”

Section: Introductionmentioning

confidence: 99%

FML2Mirth: Generic Transformation of complex laboratory data based on FML-mapping rules and automatically generated Mirth channels (Preprint)

Kruse,

Wiedekopf,

Kock-Schoppenhauer

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Reaching a significant amount of interoperability between proprietary healthcare systems is an ubiquitous task in medical informatics, where communication servers are traditionally used for referring and transforming data from source to target systems. The Mirth Connect Server, which is an open-source communication server, offers in addition to the exchange functionality, also functions for the simultaneous manipulation of data. In recent times, the standard Fast Healthcare Interoperability Resources (FHIR) is becoming more and more prevalent in the German healthcare system. This standard specifies its own standardized mechanisms for transforming data structures in the form of StructureMaps and the FHIR Mapping Language. OBJECTIVE In this study, a generic approach will be developed, which allows to apply these formalized mapping rules defined by the FHIR Mapping Language in an exchangeable manner. A transformation engine is required to execute the mapping rules. METHODS FHIR natively defines resources to support conversion of instance data, the FHIR resource StructureMap. This resource encodes all information required to transform data from a source system into a target system. In our approach, this information is defined in an implementation-independent manner using the FHIR Mapping Language. Once the mapping has been defined, executable Mirth channels are automatically generated from the resources containing the mapping in form of JavaScript. These channels can be deployed to the Mirth Connect Server. RESULTS The resulting tool is called FML2Mirth, a Java-based transformer that derives Mirth channels from a given mapping based on the underlying StructureMaps that contain the detailed rules. The implementation of the translate functionality is guaranteed by the integration of a terminology server and to achieve conformity with existing profiles, validation via the FHIR validator is built in. The system is evaluated for its practical use by transforming LDTv.2 laboratory results into MIO lab reports according to NASHIP specifications and into to the HL7 Europe Laboratory Report. It is shown that the system can generate complex structures, but LDTv.2 lacks some information to fully comply with the specification. CONCLUSIONS The tool for the auto-generation of Mirth channels was successfully presented. Initial tests have shown that it is feasible to use the complex structures of the mapping language in combination with a terminology server to transform instance data. Although the Mirth Server and FHIR are well established in the field of medical informatics, the combination offers space for more research, especially with regard to the FHIR Mapping Language. At the same time, it can be stated that the Mapping Language still has implementation short comings that can be compensated by Mirth Connect as a base technology. CLINICALTRIAL N/A

show abstract

“…The junior research group IMPETUS is dedicated to precisely these challenges. The main goal of the IMPETUS project is to extend the Medical Data Integration Center (MeDIC) [2] established at UKSH as part of the HiGHmed consortium [3] to enable the integration and further reuse of all multimedia objects and reports, regardless of the format, storage or presentation in a standardized manner. The clinical routine IT systems mainly transmit data to the MeDIC via HL7 messages, which ultimately stores them in the openEHR repository for further research projects.…”

Section: Introductionmentioning

confidence: 99%

Large-Scale Standardized Image Integration for Secondary Use Research Projects

Ulrich,

Anywar,

Kinast

et al. 2024

Studies in Health Technology and Informatics

View full text Add to dashboard Cite

Imaging techniques are a cornerstone of today’s medicine and can be crucial for a successful therapy. But in addition, the generated imaging series are an important resource for new informatics’ methods, especially in the field of artificial intelligence. This paper describes the success of integrating clinical routine imaging data into a standardized format for research purposes. Thus, we designed an integration flow and successfully implemented it in the local data integration center of University Hospital Schleswig-Holstein. The flow integrates imaging series and radiological reports from the primary system into an openEHR repository with enrichment by semantic codes for better findability and retrieval using HL7 FHIR. As a result, 6.6 million radiological studies with 29 million image series are now available for further medical (informatics) research.

show abstract

Medical Data Engineering – Theory and Practice

Cited by 5 publications

References 41 publications

Open Health Knowledge Management Platform: A Comprehensive Evaluation of a Data-centric Approach for Patient Care and Research

Open Health Knowledge Management Platform: A Comprehensive Evaluation of a Data-centric Approach for Patient Care and Research

FML2Mirth: Generic Transformation of complex laboratory data based on FML-mapping rules and automatically generated Mirth channels (Preprint)

Large-Scale Standardized Image Integration for Secondary Use Research Projects

Contact Info

Product

Resources

About