EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Neural Embedding Approach to Mapping Health Concepts to Concept Unique Identifiers

Keyuan Jiang, Gordon R Bernard

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250943 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Keyuan Jiang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Purdue University Northwest. Hauptthemen laut MEDLINE: Natural Language Processing, Unified Medical Language System, COVID-19, Neural Networks, Computer. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding health concepts in free text is an important task in biomedical NLP. Being able to map the extracted concepts to unique concept identifiers can facilitate integration of and interoperability across biomedical informatics applications. Advancement of pretrained large language models made it possible to identify health concepts in free text with a high degree of accuracy. However, they lack the ability to map the concepts to unique identifiers correctly. In this study we investigated a neural embedding approach to mapping health concepts to the Unified Medical Language System (UMLS) Metathesaurus’ Concept Unique Identifier (CUIs). A vector store containing the embeddings of 57819 unique concepts and corresponding CUIs was created, and a collection of annotated COVID-19 signs and symptoms was tested on 3 combinations of neural embeddings and vector stores. The results show that the neural embedding approach does significantly outperform the baseline string match method by >200%, which is very encouraging. However, its performance will need to be further improved for integration with large language models (LLMs).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingUnified Medical Language SystemCOVID-19Neural Networks, ComputerHumansSARS-CoV-2

Stichwörter der Autor:innen

Health conceptconcept unique identifierneural embeddingsemantic searchvector store

Autor:innen und Institutionen

  • Purdue University Northwest.
  • Vanderbilt University.

Zitieren

APA

Jiang, K., & Bernard, G. R. (2025). A Neural Embedding Approach to Mapping Health Concepts to Concept Unique Identifiers. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250943

Vancouver

Jiang K, Bernard GR. A Neural Embedding Approach to Mapping Health Concepts to Concept Unique Identifiers. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250943

BibTeX
@article{Jiang2025,
  author = {Jiang, Keyuan and Bernard, Gordon R},
  title = {A Neural Embedding Approach to Mapping Health Concepts to Concept Unique Identifiers},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250943}
}
Kostenlos starten →