Accurate Clinical Entity Recognition and Code Mapping of Anatomopathological Reports Using BioClinicalBERT Enhanced by Retrieval-Augmented Generation: A Hybrid Deep Learning Approach
The pipeline provides robust automated extraction and multi-ontology coding of anatomopathological entities, supporting transformer-based named entity recognition with retrieval-augmented generation. However, given the limitations of this study, multi-institutional validation is needed before clinical deployment.
Authors
- R. Ben Salah (ORCID: https://orcid.org/0000-0002-0935-1865)
- Andrea de Giorgio (ORCID: https://orcid.org/0000-0001-6064-5634)
- Chamseddine Barki (ORCID: https://orcid.org/0000-0002-6595-3211)
- Nicola Luigi Bragazzi (ORCID: https://orcid.org/0000-0001-8409-868X)
- Hanene Boussi Rahmouni (ORCID: https://orcid.org/0000-0002-6282-4561)
- Halil İbrahim Ceylan (ORCID: https://orcid.org/0009-0005-2214-4667)
- Hamida Abdaoui
- Ismail Dergaa
- Karima Tlili
Institutions
- University of the West of England (GB)
- York University (CA)
- Accademia di Belle Arti di Napoli (IT)
- Military Hospital of Tunis (TN)
- Tunis El Manar University (TN)
- Atatürk University (TR)
- Manouba University (TN)
Publication Details
- Journal
- Bioengineering
- Published
- 2025-12-27
- DOI
- https://doi.org/10.3390/bioengineering13010030
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00