Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports
JCO Clinical Cancer Informatics · 2025
DOI: 10.1200/cci-25-00130 ↗Kurz gefasst
Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Nicolas Wagneur und 6 weiteren Autor:innen. Beteiligte Einrichtung: Radiotherapy Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France. Hauptthemen laut MEDLINE: Natural Language Processing, Prostatic Neoplasms, Data Mining, Electronic Health Records. Die Arbeit nennt 31 Literaturangaben.
Abstract (Originalsprache)
PURPOSE This study presents a new method based on regular expressions (ReGex) and artificial intelligence for extracting relevant medical data from clinical reports. This hybrid approach is designed to address the limitations of each technique. The pipeline is evaluated for its effectiveness in extracting key clinical information from prostate cancer medical reports. METHODS We developed a hybrid pipeline that combines ReGex for initial data extraction with a Natural Language Inference model for classification. This approach was retrospectively applied to 1,000 reports randomly selected among all consultation reports of patients with prostate cancer treated at the institute, focusing on identifying key clinical information such as rectal bleeding, dysuria, pollakiuria, and hematuria. The model's performance was evaluated using precision, recall, accuracy, F1-score, and Cohen's kappa coefficient. RESULTS The pipeline demonstrated high performance, with precision scores ranging from 0.778 to 0.954 and recall consistently high at 0.920 to 1.00. F1-scores indicated balanced accuracy across symptoms, and Cohen's kappa values (0.871 to 0.951) reflected strong agreement with physician-labeled data. CONCLUSION The proposed pipeline is both efficient and fast while being computationally lightweight. It achieves high accuracy in extracting medical data from clinical reports, making it an effective and practical tool for clinical research and health care applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Radiotherapy Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France.
- Artificial Intelligence Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France.
- Oncology Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France.
- Data Factory & Analytics Department, Institut de Cancérologie de l'Ouest, Nantes-Angers, France.
- Law and Social Change Laboratory, Faculty of Law and Political Sciences, CNRS UMR 6297, Nantes University, Nantes, France.
- Center for Research in Cancerology and Immunology Nantes-Angers, INSERM UMR 1232, Nantes University and Angers University, Nantes-Angers, France.
ORCID-Profile: Nicolas Wagneur, Florent Le Borgne, François Bocquet, Tanguy Perennec
Zitieren
APA
Wagneur, N., Capitain, O., Supiot, S., Le Borgne, F., Bocquet, F., Campone, M., & Perennec, T. (2025). Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00130
Vancouver
Wagneur N, Capitain O, Supiot S, Le Borgne F, Bocquet F, Campone M, et al. Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00130
BibTeX
@article{Wagneur2025,
author = {Wagneur, Nicolas and Capitain, Olivier and Supiot, Stéphane and Le Borgne, Florent and Bocquet, François and Campone, Mario and Perennec, Tanguy},
title = {Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
doi = {10.1200/cci-25-00130}
}
EUVIMED