Downloads · 30 days
0
bright-eds-dates_outcomes
raphael-r/bright-eds-dates_outcomes
bright-eds-dates_outcomes is a machine learning model from raphael-r. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a EDS-NLP (CamemBERT + CRF) architecture fine-tuned to extract clinical neuro-oncology entities related to the datesoutcomes semantic group. It was trained on a synthetic dataset generated for the properly de-…
Access
Public
Updated Apr 7, 2026
Repo size
483 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors483 MB · 99%
At a glance
- Access
- Public
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026
- SHA
- 526b25fb
Model card
From the Hugging Face model README
BRIGHT NER: EDS-NLP (CamemBERT + CRF) fine-tuned for dates_outcomes
Description
This is a EDS-NLP (CamemBERT + CRF) architecture fine-tuned to extract clinical neuro-oncology entities related to the dates_outcomes semantic group. It was trained on a synthetic dataset generated for the properly de-identified BRIGHT project dataset (see the generated_data folder in the primary repository).
This model repository was specifically designed to fit within the bright_db overarching namespace.
Fields
It extracts the following fields (described in French):
- date_chir: Date intervention neurochirurgicale ou résection
- date_rcp: Date réunion concertation pluridisciplinaire
- dn_date: Date dernières nouvelles ou dernier suivi
- date_deces: Date décès patient (seulement si décédé)
- date_1er_symptome: Date apparition premiers symptômes
- exam_radio_date_decouverte: Date premier examen découvrant la tumeur
- date_progression: Date récidive/progression
- survie_globale: Durée survie en mois
- infos_deces: Circonstances décès
Performance on Validation Set
Aggregates:
- Macro F1: 0.3203 (Precision: 0.3367, Recall: 0.3229)
- Micro F1: 0.7421 (Precision: 0.7662, Recall: 0.7195)
Per-Label Breakdowns:
| Label | Precision | Recall | F1 |
|---|---|---|---|
| date_chir | 0.1429 | 0.2500 | 0.1818 |
| date_rcp | 0.9211 | 0.8974 | 0.9091 |
| dn_date | 0.0000 | 0.0000 | 0.0000 |
| date_deces | 0.0000 | 0.0000 | 0.0000 |
| date_1er_symptome | 0.0000 | 0.0000 | 0.0000 |
| exam_radio_date_decouverte | 0.1667 | 0.3333 | 0.2222 |
| date_progression | 0.0000 | 0.0000 | 0.0000 |
| survie_globale | 1.0000 | 0.6250 | 0.7692 |
| infos_deces | 0.8000 | 0.8000 | 0.8000 |
Usage
# Inference Code
import edsnlp
nlp = edsnlp.load("raphael-r/bright-eds-dates_outcomes")
doc = nlp("Patient presenting with epileptic seizures...")
for ent in doc.ents:
print(ent.text, "=>", ent.label_)
- Languages
- fr
- Created
- Apr 7, 2026
- Updated
- Apr 7, 2026