Development and Assessment of a Pipeline for Extracting Structured Data From Free-Text Medical Reports Using a Large Language Model
Our study provides strong evidence of the potential of LLMs like Mistral Large for extracting structured BC biomarker data from pathology reports and the potential of such methods for broader digital transformation of health care documents.
Authors
- Nicolas Wagneur (ORCID: https://orcid.org/0000-0001-6666-0210)
- Tanguy Perennec (ORCID: https://orcid.org/0000-0002-1118-2271)
- Mario Campone (ORCID: https://orcid.org/0000-0002-5196-5908)
- F. BOCQUET
- Florent Le Borgne
- Enzo Joseph
- Jean-Sébastien Frenel
- Paul Vallee
Institutions
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Centre de Recherche en Cancérologie et Immunologie Intégrée Nantes Angers (FR)
- Droit et changement social (FR)
- Institut de Cancérologie de l'Ouest (FR)
- Nantes Université (FR)
Publication Details
- Journal
- JCO Clinical Cancer Informatics
- Published
- 2026-02-18
- DOI
- https://doi.org/10.1200/cci-25-00133
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00