EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Transforming Annotated Clinical Narratives into Pruned Interoperable Knowledge Graphs with SNOMED CT

Amila Kugic, Markus Kreuzthaler, Stefan Schulz

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Amila Kugic und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria. Hauptthemen laut MEDLINE: Systematized Nomenclature of Medicine, Natural Language Processing, Electronic Health Records, Health Information Interoperability. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Clinical narratives are difficult to process due to unstructured text, abbreviations, and jargon, which limit semantic interoperability. Converting them into knowledge graphs (KGs) and pruning SNOMED CT enables focused, interoperable representations without losing essential information.

Methods

KGs were built from the n2c2 2019 dataset using SNOMED CT and UMLS to model concept relationships. Subgraphs were merged, redundancies removed, and interoperability enforced via mappings to ICD-10-CM, RxNorm, and LOINC. Non-interoperable or disconnected nodes were pruned, and experts evaluated pruning quality.

Results

Radical pruning improved interoperability but often removed contextual detail. Context-aware pruning preserved clinically meaningful structures while producing compact, semantically rich KGs suitable for downstream NLP tasks.

Conclusion

The approach enables interoperable, pruned KGs from clinical narratives, with future work focusing on hybrid pruning and clinical NLP applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Systematized Nomenclature of MedicineNatural Language ProcessingElectronic Health RecordsHealth Information InteroperabilityNarrationHumansUnified Medical Language SystemSemantics

Stichwörter der Autor:innen

Electronic Health RecordsNatural Language ProcessingTerminology

Autor:innen und Institutionen

  • Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria.

Zitieren

APA

Kugic, A., Kreuzthaler, M., & Schulz, S. (2026). Transforming Annotated Clinical Narratives into Pruned Interoperable Knowledge Graphs with SNOMED CT. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260347

Vancouver

Kugic A, Kreuzthaler M, Schulz S. Transforming Annotated Clinical Narratives into Pruned Interoperable Knowledge Graphs with SNOMED CT. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260347

BibTeX
@article{Kugic2026,
  author = {Kugic, Amila and Kreuzthaler, Markus and Schulz, Stefan},
  title = {Transforming Annotated Clinical Narratives into Pruned Interoperable Knowledge Graphs with SNOMED CT},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260347}
}
Kostenlos starten →