OpenMed-NER-BloodCancerDetect-ModernClinical-395M

What it does

This model detects cell line names in English clinical text, using a fixed label set. It reports an F1 score of 0.718 on the CLL corpus, which contains 2,156 documents, and is built on the ModernBERT architecture with 396M parameters.

Best for

• Extracting cell lines from oncology notes
• Annotating cell line mentions in research papers
• Identifying cell lines in clinical trial records

Note on the model card. Cell line name recognition in clinical text (CLL corpus, 2,156 documents; label CL = cell line). The model card's 'chronic lymphocytic leukemia' wording is a misreading of the corpus name; see the OpenMed paper, Table 1.

What it detects (1 labels)

• Cell line

Quality

Cell line name recognition in clinical text (CLL corpus, 2,156 documents; label CL = cell line). The model card's 'chronic lymphocytic leukemia' wording is a misreading of the corpus name; see the OpenMed paper, Table 1.

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-BloodCancerDetect-ModernClinical-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-BloodCancerDetect-ModernClinical-395M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())