Using large language models for temporal relation extraction from pediatric clinical reports
Our few-shot prompting approach demonstrated promising results in secure environments. This methodology allows technique sharing without exposing sensitive data, advancing research possibilities for clinical natural language processing in restricted settings.
Authors
- Nicolas Garcelon (ORCID: https://orcid.org/0000-0002-3326-2811)
- Marc Vincent (ORCID: https://orcid.org/0000-0002-0985-4550)
- Anita Burgun (ORCID: https://orcid.org/0000-0001-6855-4366)
- Joseph Le Potier (ORCID: https://orcid.org/0009-0000-5160-7927)
- Judith Jeyafreeda Andrew (ORCID: https://orcid.org/0000-0002-2305-1439)
Institutions
- Hôpital Necker-Enfants Malades (FR)
- Inserm (FR)
- Université Paris Cité (FR)
- Institut Necker Enfants Malades (FR)
- Assistance Publique – Hôpitaux de Paris (FR)
- Intelligence in Medical Technologies (France) (FR)
- Institut des Maladies Génétiques Imagine (FR)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-09-30
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf121
- Citations
- 1
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.81