OpenMed-NER-PharmaDetect-BioMed-109M

What it does

This model identifies mentions of drugs and chemicals in English clinical notes, research papers, and healthcare documents, labeling them as 'Chemical or drug'. It reports an F1 score of 0.948 on the BC5CDR chemicals benchmark and is built on a 109M-parameter BiomedELECTRA backbone.

Best for

• Medication extraction from patient records
• Literature mining for drug discovery
• Chemical entity recognition in research papers

What it detects (1 labels)

• Chemical or drug

Quality

Chemical Entity Recognition - Chemical entities from the BC5CDR dataset

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-PharmaDetect-BioMed-109M", 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-PharmaDetect-BioMed-109M-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-PharmaDetect-BioMed-109M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)