OpenMed-NER-OncologyDetect-ModernClinical-149M

What it does

This model detects 16 cancer-related entity types, including Cancer, Gene or gene product, and Simple chemical, in English clinical and research documents. It reports an F1 score of 0.774 on the BioNLP 2013 Cancer Genetics benchmark, with a 150M-parameter ModernBERT backbone.

Best for

• Entity extraction from oncology literature
• Mining genetic entities in clinical notes
• Identifying chemical compounds in research papers

What it detects (16 labels)

• Amino acid
• Anatomical system
• Cancer
• Cell
• Cellular component
• Developing anatomical structure
• Gene or gene product
• Immaterial anatomical entity
• Multi-tissue structure
• Organ
• Organism
• Organism subdivision
• Organism substance
• Pathological formation
• Simple chemical
• Tissue

Quality

Cancer Genetics - Cancer-related genetic entities

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-OncologyDetect-ModernClinical-149M", 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-OncologyDetect-ModernClinical-149M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())