OpenMed-NER-DiseaseDetect-ModernClinical-395M

What it does

This model detects disease entities in English clinical notes and biomedical literature, labeling them as 'Disease'. It reports an F1 score of 0.884 on the BC5CDR benchmark, with a 396M-parameter ModernBERT backbone supporting sequences up to 8192 tokens.

Best for

• Disease mentions in clinical notes
• Disease extraction from research papers
• Disease tagging for biomedical databases

What it detects (1 labels)

• Disease

Quality

Disease Entity Recognition - Disease entities from the BC5CDR dataset

Use it

pip install transformers torch

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