EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY-NC-ND 4.0

Comparing three natural language processing methods for the automatic identification of epilepsy patients from French clinical notes

François Le Gac iD, Quentin Calonge iD, Candice Estellat, Vincent Navarro iD

Epilepsia · 2026

DOI: 10.1111/epi.18683 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Epilepsia, 2026. Verfasst von François Le Gac und 3 weiteren Autor:innen. Beteiligte Einrichtung: Paris Brain Institute-Institut du Cerveau, Institut National de la Santé Et de la Recherche Médicale (INSERM), Centre National de la Recherche Scient…. Hauptthemen laut MEDLINE: Natural Language Processing, Epilepsy, Electronic Health Records. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Direction Générale de l'offre de Soins, Agence Nationale de la Recherche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Manual review of clinical notes by experts remains the reference standard for identifying patients with epilepsy in health databases. However, this process is labor‐intensive and time‐consuming due to the unstructured nature of text. Prior studies have shown the potential of natural language processing for automated phenotyping. We aim to develop and validate algorithms capable of identifying patients with epilepsy based on a set of clinical notes.

Methods

A population of 109 448 patients was selected from the Assistance Publique‐Hôpitaux de Paris (AP‐HP) Clinical Data Warehouse (CDW) (38 hospitals in Paris, France) based on the presence of an International Classification of Diseases, Tenth Revision (ICD‐10) diagnostic code related to epilepsy (G40/G41) or mimicking disorders (R53/R55/R56), or the mention of at least one antiseizure medication in their medical chart. From this pre‐screened population, 6733 sentences (from 2700 patients) were labeled as indicative or not indicative of epilepsy, and 3000 patients were selected randomly for manual review by a neurologist. We compared a “basic” keyword‐based method, a rule‐based method, and a pretrained language model for identifying epilepsy‐related sentences and classifying patients with epilepsy. We reported the F 1 score of each method.

Results

At the sentence level, the pretrained language model reached the highest F 1 score of .95 (95% confidence interval [CI]: .95–.96) outperforming the rule‐based method .87 (95% CI: .86–.88) and the basic method .81 (95% CI: .80–.81). At the patient level, the pretrained language model also achieved the best F 1 score .95 (95% CI: .94–.96) compared to the rule‐based method .93 (95% CI: .91–.94) and the basic method .82 (95% CI: .81–.84). Significance 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingEpilepsyElectronic Health RecordsHumansFranceAlgorithmsMaleFemaleAdultMiddle AgedDatabases, Factual

Stichwörter der Autor:innen

Automated phenotypingClinical data warehousePretrained language modelelectronic health recordepilepsynatural language processing (NLP)

Autor:innen und Institutionen

  • Paris Brain Institute-Institut du Cerveau, Institut National de la Santé Et de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS), Pitié-Salpêtrière Hospital, Sorbonne Université, Paris,…
  • Epilepsy Unit, Département Médico-Universitaire Neurosciences, Pitié-Salpêtrière Hospital, AP-HP, Paris, France.
  • Center of Reference for Rare Epilepsies, ERN-Epicare, Département Médico-Universitaire Neurosciences, Pitié-Salpêtrière Hospital, AP-HP, Paris, France.
  • Département de Santé Publique, Centre de Pharmacoépidémiologie (Cephepi), Unité de Recherche Clinique PSL-CFX, CIC-1901, Institut Pierre Louis d'Epidémiologie et de Santé Publique, INSERM, Hôpital Pitié Salpêtrière, AP-…

ORCID-Profile: François Le Gac, Quentin Calonge, Vincent Navarro

Förderung

  • Direction Générale de l'offre de Soins
  • Agence Nationale de la Recherche

Zitieren

APA

Le Gac, F., Calonge, Q., Estellat, C., & Navarro, V. (2026). Comparing three natural language processing methods for the automatic identification of epilepsy patients from French clinical notes. Epilepsia. https://doi.org/10.1111/epi.18683

Vancouver

Le Gac F, Calonge Q, Estellat C, Navarro V. Comparing three natural language processing methods for the automatic identification of epilepsy patients from French clinical notes. Epilepsia. 2026. doi:10.1111/epi.18683

BibTeX
@article{LeGac2026,
  author = {Le Gac, François and Calonge, Quentin and Estellat, Candice and Navarro, Vincent},
  title = {Comparing three natural language processing methods for the automatic identification of epilepsy patients from French clinical notes},
  journal = {Epilepsia},
  year = {2026},
  doi = {10.1111/epi.18683}
}
Kostenlos starten →