OpenMed-NER-AnatomyDetect-ElectraMed-560M

What it does

This model performs named-entity recognition to identify anatomical structures and body parts in English clinical texts, research papers, and healthcare documents. It reports an F1 score of 0.906 on the AnatEM benchmark, with 559M parameters and a maximum sequence length of 514 tokens.

Best for

• Anatomy extraction from clinical notes
• Literature mining for anatomical entities
• Biomedical knowledge graph construction

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-ElectraMed-560M", 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-ElectraMed-560M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())

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-NER-AnatomyDetect-ElectraMed-560M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)