Generative Models and Sentence Transformers for the Recognition and Normalization of Continuous and Discontinuous Phenotype Mentions: Model Development and Evaluation
The findings suggest that exact extraction of entity spans may not always be necessary for successful normalization. Partial mention matches can be sufficient as long as they capture the essential concept information, supporting the system's utility in clinical downstream tasks.
Authors
- Goran Nenadić (ORCID: https://orcid.org/0000-0003-0795-5363)
- Viktor Schlegel (ORCID: https://orcid.org/0000-0002-6391-2950)
- Areej Alhassan (ORCID: https://orcid.org/0000-0001-7780-9463)
- Riza Batista-Navarro (ORCID: https://orcid.org/0000-0001-6693-7531)
- Monira Aloud (ORCID: https://orcid.org/0000-0002-0472-5151)
Institutions
- King Saud University (SA)
- University of Manchester (GB)
- Imperial College London (GB)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-08-15
- DOI
- https://doi.org/10.2196/68558
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00