Finds disease names in English biomedical text
Zero-shot NER (your own labels)Diseases and conditionsEnglishMedium · 220Mapache-2.0
What it does
This model detects disease and condition names in English biomedical text, including clinical records and research literature. It reports an F1 score of 0.829 on the BC5CDR disease benchmark and is based on the GLiNER architecture with 220 million parameters.
Best for
- Disease indexing from research papers
- Patient phenotyping from clinical notes
- Literature triage for evidence aggregation
What it detects (1 labels)
Trained on the label below; you can pass any other label names at inference time.
- Disease
Quality
| Benchmark | BC5CDR (diseases) · all models on this benchmark |
|---|---|
| F1 | 0.829 |
| Precision | 0.787 |
| Recall | 0.876 |
| Accuracy | 0.970 |
| Source | Reported by the authors (test_results.json in the repository) |
Disease Entity Recognition - Disease entities from the BC5CDR dataset
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Disease-Base-220M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))All model information shown here is public and belongs to its authors: use and download it freely under each model’s license. The selection, organization, search design and presentation of this catalog are © 2026 Clinical Corpus. Please link to these pages rather than copy them.