Identifies drug and chemical names in English clinical and research text
Extract biomedical entitiesDrugs and chemicalsEnglishMedium · 396Mapache-2.0
What it does
This model detects the single entity type 'Chemical or drug' in English clinical notes, research papers, and healthcare documents. It reports an F1 score of 0.953 on the BC5CDR chemicals benchmark, with 396M parameters and support for sequences up to 8192 tokens.
Best for
- Extracting drug names from clinical notes
- Mining chemical compounds in biomedical literature
- Identifying medications in patient records
What it detects (1 labels)
- Chemical or drug
Quality
| Benchmark | BC5CDR (chemicals) · all models on this benchmark |
|---|---|
| F1 | 0.953 |
| Precision | 0.948 |
| Recall | 0.957 |
| Accuracy | 0.987 |
| Source | Reported by the authors (test_results.json in the repository) |
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-ModernClinical-395M", aggregation_strategy="simple")
print(ner("Patient prescribed 10 mg aspirin for hypertension."))Android, browser, CPU (ONNX) build
pip install --upgrade "openmed[onnx-runtime]"
from openmed import OnnxModel
model = OnnxModel.from_pretrained("OpenMed/OpenMed-NER-PharmaDetect-ModernClinical-395M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
print(entity.to_dict())All model information shown here is public and belongs to its authors: use and download it freely under each model’s license. The selection, organization, search design and presentation of this catalog are © 2026 Clinical Corpus. Please link to these pages rather than copy them.