Ontology enrichment using a large language model: Applying lexical, semantic, and knowledge network-based similarity for concept placement
The contributions of this work are: Extracting semantic triples from PubMed abstracts using GPT-4-1201 utilizing prompt chaining; showing the superiority of triples from GPT-4-1201 over triples from SemMedDB for SDoH; using lexical and semantic similarity search techniques with knowledge network-based search to identify the concepts to be added to the ontology; confirming the quality of the new concepts with human experts.
Authors
- Julia Xu (ORCID: https://orcid.org/0000-0003-4147-8388)
- Navya Martin Kollapally
- Zhe He (ORCID: https://orcid.org/0000-0003-3608-0244)
- James Geller (ORCID: https://orcid.org/0000-0002-9120-525X)
- Vipina K. Keloth (ORCID: https://orcid.org/0000-0001-6919-1122)
Institutions
- Florida State University (US)
- New Jersey Institute of Technology (US)
- Yale University (US)
- Bexon Clinical Consulting (United States) (US)
- Kean University (US)
Publication Details
- Journal
- Journal of Biomedical Informatics
- Published
- 2025-06-19
- DOI
- https://doi.org/10.1016/j.jbi.2025.104865
- Citations
- 4
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 3.22
Funders
- Foundation for the National Institutes of Health
- U.S. National Library of Medicine