OpenMed-NER-AnatomyDetect-ModernMed-395M

What it does

This model detects the single entity type Anatomy, covering anatomical structures and body parts, in English clinical notes and biomedical literature. It reports an F1 score of 0.871 on the AnatEM benchmark with a 396M-parameter ModernBERT-large backbone.

Best for

• Extracting anatomy mentions from clinical notes
• Mining anatomical structures in research papers
• Building biomedical knowledge graphs

What it detects (1 labels)

• Anatomy

Quality

Anatomical Entity Recognition - Anatomical structures and body parts

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-AnatomyDetect-ModernMed-395M", aggregation_strategy="simple")
print(ner("Patient prescribed 10 mg aspirin for hypertension."))

pip install --upgrade "openmed[onnx-runtime]"

from openmed import OnnxModel
model = OnnxModel.from_pretrained("OpenMed/OpenMed-NER-AnatomyDetect-ModernMed-395M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())