Detects chemical and drug names in English biomedical text
Extract biomedical entitiesDrugs and chemicalsEnglishMedium · 396Mapache-2.0
What it does
This model identifies chemical or drug entities in English clinical texts and research papers. It reports an F1 score of 0.949 on the BC5CDR chemicals benchmark, with 396M parameters and a maximum sequence length of 8192 tokens.
Best for
- Medication extraction from patient records
- Literature mining for drug discovery
- Adverse event monitoring in clinical notes
What it detects (1 labels)
- Chemical or drug
Quality
| Benchmark | BC5CDR (chemicals) · all models on this benchmark |
|---|---|
| F1 | 0.949 |
| Precision | 0.939 |
| Recall | 0.959 |
| Accuracy | 0.986 |
| 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-ModernMed-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-ModernMed-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.