OpenMed-ZeroShot-NER-Pathology-Medium-209M

What it does

This model performs zero-shot named-entity recognition for disease mentions in English biomedical and clinical text, with users supplying the entity label at inference. It reports an F1 score of 0.894 on the NCBI Disease benchmark, with 209M parameters and a GLiNER backbone.

Best for

• Disease mentions from research literature
• 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

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-Medium-209M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))

pip install "openmed[mlx]"

from openmed import analyze_text
from openmed.core.config import OpenMedConfig
result = analyze_text("Patient started imatinib in March.", model_name="OpenMed/OpenMed-ZeroShot-NER-Pathology-Medium-209M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)