EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY-NC 4.0

Ontology-Enriched Guidelines Retrieval for Complex Rheumatological Cases

Tommaso Mario Buonocore, Sara Marino, Giuseppe Albi, Garifallia Sakellariou, Arianna Dagliati, Enea Parimbelli, Lucia Sacchi

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260345 ↗

Kurz gefasst

Leitlinie in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Tommaso Mario Buonocore und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer, Electrical and Biomedical Engineering, University of Pavia, Pavia, Italy. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Practice Guidelines as Topic, Rheumatic Diseases, Information Storage and Retrieval. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) integrated with Retrieval-Augmented Generation (RAG) can enhance clinical decision support and triage. However, semantic retrieval often fails to capture the structured relationships of medical knowledge, especially in complex scenarios. This study explores the use of ontology-based knowledge graphs to improve retrieval, combining SNOMED CT and rheumatology guidelines within a graph database. Retrieval was evaluated on clinical queries using three configurations: embeddings-only, knowledge graph-only, and a hybrid approach. Results indicate that while embeddings suffice for simple cases, ontology-based knowledge graphs are crucial for complex reasoning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalPractice Guidelines as TopicRheumatic DiseasesInformation Storage and RetrievalBiological OntologiesRheumatologyLarge Language ModelsHumansSystematized Nomenclature of MedicineGenerative Artificial Intelligence

Stichwörter der Autor:innen

Clinical Decision SupportGenerative AIKnowledge GraphsLarge Language ModelsRetrieval-Augmented GenerationRheumatic Diseases

Autor:innen und Institutionen

  • Department of Computer, Electrical and Biomedical Engineering, University of Pavia, Pavia, Italy.
  • IRCCS Mondino Foundation, Pavia, Italy.
  • Department of Internal Medicine and Therapeutics, University of Pavia, Pavia, Italy.
  • Istituti Clinici Scientifici Maugeri, Pavia, Italy.

Zitieren

APA

Buonocore, T. M., Marino, S., Albi, G., Sakellariou, G., Dagliati, A., Parimbelli, E., & Sacchi, L. (2026). Ontology-Enriched Guidelines Retrieval for Complex Rheumatological Cases. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260345

Vancouver

Buonocore TM, Marino S, Albi G, Sakellariou G, Dagliati A, Parimbelli E, et al. Ontology-Enriched Guidelines Retrieval for Complex Rheumatological Cases. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260345

BibTeX
@article{Buonocore2026,
  author = {Buonocore, Tommaso Mario and Marino, Sara and Albi, Giuseppe and Sakellariou, Garifallia and Dagliati, Arianna and Parimbelli, Enea and Sacchi, Lucia},
  title = {Ontology-Enriched Guidelines Retrieval for Complex Rheumatological Cases},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260345}
}
Kostenlos starten →