Comparing three natural language processing methods for the automatic identification of epilepsy patients from French clinical notes
Both the rule-based and the pretrained language models achieved high performance. These algorithms can automatically identify patients with epilepsy from unstructured clinical notes in French data warehouses, supporting large-scale phenotyping and the detection of epilepsy as a comorbidity.
Authors
- Candice Estellat (ORCID: https://orcid.org/0000-0002-7588-1813)
- Vincent Navarro (ORCID: https://orcid.org/0000-0003-0077-8114)
- Quentin Calonge (ORCID: https://orcid.org/0009-0004-5874-3947)
- François Le Gac
Institutions
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Sorbonne Université (FR)
- Pitié-Salpêtrière Hospital (FR)
- Institut Pierre Louis d‘Épidémiologie et de Santé Publique (FR)
- Institut du Cerveau (FR)
Publication Details
- Journal
- Epilepsia
- Published
- 2025-10-24
- DOI
- https://doi.org/10.1111/epi.18683
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Agence Nationale de la Recherche