OpenMed-NER-DiseaseDetect-ElectraMed-109M

What it does

This model identifies disease entities in English clinical notes and biomedical literature, using a BERT-based architecture fine-tuned on the BC5CDR dataset. It reports an F1 score of 0.866 on the BC5CDR test set, with a maximum sequence length of 512 tokens and 109 million parameters.

Best for

• Clinical text mining for disease mentions
• Biomedical literature screening for conditions
• Patient record analysis for disease coding

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-ElectraMed-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-DiseaseDetect-ElectraMed-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-DiseaseDetect-ElectraMed-109M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)