Finds disease mentions in English biomedical literature
Zero-shot NER (your own labels)Diseases and conditionsEnglishMedium · 220Mapache-2.0
What it does
This zero-shot model detects disease entities in English clinical and research text, with users supplying the entity label at inference time. It reports an F1 score of 0.856 on the NCBI Disease benchmark, based on a 220M-parameter GLiNER backbone.
Best for
- Disease mention extraction from research articles
- Cohort discovery in clinical notes
- Knowledge graph construction from biomedical text
What it detects (1 labels)
Trained on the label below; you can pass any other label names at inference time.
- Disease
Quality
| Benchmark | NCBI Disease · all models on this benchmark |
|---|---|
| F1 | 0.856 |
| Precision | 0.828 |
| Recall | 0.885 |
| Accuracy | 0.968 |
| Source | Reported by the authors (test_results.json in the repository) |
Disease Entity Recognition - Disease entities from the NCBI dataset
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Pathology-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.