metadata
license: apache-2.0
language:
- en
base_model:
- distilbert/distilbert-base-uncased
tags:
- medical
- NER
Model Description
distilbert-clinical-ner is a fine-tuned DistilBERT model for biomedical and clinical NER tasks.
It is trained to identify and classify entities such as diseases, medications, lab values, procedures, and other biomedical concepts in text.
This model is intended for research and learning purposes
Intended Use
- Extract biomedical entities from clinical notes, research papers, or other health-related texts.
- Educational purposes: experiment with NER pipelines, token classification, and fine-tuning pre-trained transformers.
Not Intended For
- Production-level clinical decision making.
- Use in real-world medical diagnosis or treatment recommendations.
Metrics
The model was evaluated on a biomedical NER dataset (BioMedical NER, [your dataset reference]) using standard token-level metrics:
| Metric | Score |
|---|---|
| Accuracy | 0.65 |
| Precision | 0.65 |
| Recall | 0.65 |
| F1-score | 0.65 |
These metrics reflect experimental performance and are intended for learning and demonstration purposes.
Citation
If you use this model for research or portfolio demonstrations, you can cite:
@misc{rakesh-mohan-2025-distilbertclinicalner,
title={distilbert-clinical-ner: A Biomedical NER Model},
author={Rakesh Mohan},
year={2025},
howpublished={\url{https://huggingface.co/rm0013/distilbert-clinical-ner}}
}