|
|
--- |
|
|
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}} |
|
|
} |
|
|
|
|
|
``` |
|
|
|
|
|
--- |
