Finds anatomical structures and body parts in English clinical text
What it does
This zero-shot model detects the entity type Anatomy, covering organs, tissues, and substructures, in English clinical narratives and biomedical literature, with labels supplied by the user at inference. It reports an F1 score of 0.561 on the AnatEM benchmark, with 60M parameters and a GLiNER backbone.
Best for
- Radiology and surgical note parsing
- Site-of-disease extraction from reports
- Anatomy-aware analytics in healthcare
What it detects (1 labels)
Trained on the label below; you can pass any other label names at inference time.
- Anatomy
Quality
| Benchmark | AnatEM · all models on this benchmark |
|---|---|
| F1 | 0.561 |
| Precision | 0.524 |
| Recall | 0.604 |
| Accuracy | 0.917 |
| Source | Reported by the authors (test_results.json in the repository) |
Anatomical Entity Recognition - Anatomical structures and body parts
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Anatomy-Tiny-60M")
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.