EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT

Frederic Ehrler, Florian Singer, Deniz Geçer, Julien Houeix, Emmanuel Durand

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Frederic Ehrler und 4 weiteren Autor:innen. Beteiligte Einrichtung: Direction of Digital Transformation and Augmented Intelligence, University Hospitals of Geneva. Hauptthemen laut MEDLINE: Large Language Models, Systematized Nomenclature of Medicine, Semantics, Information Storage and Retrieval. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mapping local clinical concepts to standardized terminologies such as SNOMED CT is essential for semantic interoperability and large-scale research, but manual mapping is labor-intensive and difficult to scale. We report a preliminary evaluation of a hybrid approach combining retrieval-augmented generation (RAG) and a large language model (LLM) to support the mapping of hospital datalake concepts to SNOMED CT. Using a dataset of 2,768 concepts annotated by the SIMED across five semantic categories (organisms, healthcare locations, laboratory samples, allergies, and clinical assessments), the pipeline consistently outperformed retrieval-only baselines. For organism concepts, strict accuracy reached 92.8% (weighted 98.0%, top-3 96.7%), while allergy and assessment concepts achieved 84.7% and 72.1% strict accuracy, respectively. Healthcare location and laboratory sample concepts remained more challenging, with strict accuracies of 57.5% and 57.1%, and weighted accuracy varied strongly depending on frequency distributions. Overall, strict accuracy was 72.8%, weighted accuracy 76.1%, and top-3 accuracy 83.1%. These findings suggest that combining RAG with LLM-based reasoning can reduce expert workload while maintaining accuracy, representing a step toward scalable, AI-assisted semantic interoperability in healthcare. The approach relies on a retrieval-augmented generation pipeline using embedding-based candidate retrieval followed by LLM-based disambiguation (GPT-4.1-mini), and is evaluated against a retrieval-only baseline. By improving semantic consistency in clinical data lakes, it indirectly supports interoperable access to patient-level health data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsSystematized Nomenclature of MedicineSemanticsInformation Storage and RetrievalElectronic Health RecordsNatural Language ProcessingHumans

Stichwörter der Autor:innen

Artificial IntelligenceDatabase Management SystemsMedical InformaticsNatural Language ProcessingSNOMED CTSemantics

Autor:innen und Institutionen

  • Direction of Digital Transformation and Augmented Intelligence, University Hospitals of Geneva.

Zitieren

APA

Ehrler, F., Singer, F., Geçer, D., Houeix, J., & Durand, E. (2026). Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260288

Vancouver

Ehrler F, Singer F, Geçer D, Houeix J, Durand E. Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260288

BibTeX
@article{Ehrler2026,
  author = {Ehrler, Frederic and Singer, Florian and Geçer, Deniz and Houeix, Julien and Durand, Emmanuel},
  title = {Leveraging Large Language Models with Retrieval-Augmented Generation for Semantic Mapping of Clinical Data Lakes to SNOMED CT},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260288}
}
Kostenlos starten →