% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Sasse:1026700,
author = {Sasse, Julia and Darms, Johannes and Fluck, Juliane},
title = {{S}emantic {M}etadata {A}nnotation {S}ervice},
reportid = {FZJ-2024-03514},
year = {2022},
abstract = {Operationalising the FAIR (Findable, Accessible,
Interoperable, Reusable) guiding principles for scientific
data management and stewardship [1] enhance the use of data
beyond its original purpose. Data analysis of different
sources for example requires interoperability that allows
machines to automatically combine and process the data.
Semantic interoperability, i.e., the ability to
automatically interpret the shared information in a
meaningful way, is given special attention in the biomedical
domain. Its realization by ontology-based semantic
annotation is still a challenge due to various standards and
semantic richness of the data. Plenty semi-structured and
structured study documents exist that are not yet
semantically annotated. Despite of the laborious annotation
process, semantic annotation is largely done manually and
annotators have to manage data standards and formats as well
as a variety of complex terminologies and ontologies for
annotation. Therefore, a semi-automatic approach to support
researchers in semantic annotation and handling the
different data formats is desirable. In this context, the
National Research Data Infrastructure for Personal Health
Data (NFDI4Health) aims to improve the FAIR access to
structured health data originating from epidemiology
studies, public health and clinical studies and support the
harmonization of (meta-)data [2]. For the latter, we present
an approach for a cross-domain and extensible semantic
metadata annotation service, that addresses the problems
stated above. Basic requirements for the metadata annotation
service are an open accessible web service, open code and an
interface to integrate different terminology lookup services
with access to terminology concepts depending on the use
case. For the medical domain, support for the SNOMED
terminology and common standards such as HL7 FHIR [3] are
additional requirements. While some metadata annotation
services already exist (e.g. [4]), they are in many cases
tailored to specific data formats and terminologies or they
do not meet all basic prerequisites. A first prototype was
developed that meets the basic requirements and can be
adapted to specific use cases. Terminology search via the
Ontology Lookup Service [5] was implemented in an
open-source web application to provide access to a wide
range of terminologies. Usability tests with users indicated
a good user experience. Currently, the annotation service is
being further adapted for a use case in the medical domain.
Therefore, the HL7 FHIR standard will be integrated and the
SNOMED CT terminology will be used for semantic annotation
of medical terms. References [1 ] Wilkinson, M.D.;
Dumontier, M.; Aalbersberg, I.J.J.; Appleton, G.; Axton, M.;
Baak, A.; Blomberg, N.; Boiten, J.-W.; da Silva Santos,
L.B.; Bourne, P.E.; et al. The FAIR Guiding Principles for
Scientific Data Management and Stewardship. Sci Data 2016,
3, 160018, doi:10.1038/sdata.2016.18. [2] Fluck, J.;
Lindstädt, B.; Ahrens, W.; Beyan, O.; Buchner, B.; Darms,
J.; Depping, R.; Dierkes, J.; Neuhausen, H.; Müller, W.; et
al. NFDI4Health – Nationale},
typ = {PUB:(DE-HGF)24},
doi = {10.5281/ZENODO.6366013},
url = {https://juser.fz-juelich.de/record/1026700},
}