Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,58 @@ base_model:
|
|
| 7 |
tags:
|
| 8 |
- medical
|
| 9 |
- NER
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
|
|
|
| 7 |
tags:
|
| 8 |
- medical
|
| 9 |
- NER
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
## Model Description
|
| 13 |
+
|
| 14 |
+
`distilbert-clinical-ner` is a fine-tuned DistilBERT model for **biomedical and clinical NER tasks**.
|
| 15 |
+
It is trained to identify and classify entities such as **diseases, medications, lab values, procedures, and other biomedical concepts** in text.
|
| 16 |
+
|
| 17 |
+
This model is intended for **research and learning purposes**
|
| 18 |
+
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
## Intended Use
|
| 22 |
+
|
| 23 |
+
- Extract biomedical entities from clinical notes, research papers, or other health-related texts.
|
| 24 |
+
- Educational purposes: experiment with NER pipelines, token classification, and fine-tuning pre-trained transformers.
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
## Not Intended For
|
| 29 |
+
|
| 30 |
+
- Production-level clinical decision making.
|
| 31 |
+
- Use in real-world medical diagnosis or treatment recommendations.
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
## Metrics
|
| 36 |
+
|
| 37 |
+
The model was evaluated on a biomedical NER dataset (BioMedical NER, [your dataset reference]) using standard token-level metrics:
|
| 38 |
+
|
| 39 |
+
| Metric | Score |
|
| 40 |
+
|-----------|-------|
|
| 41 |
+
| Accuracy | 0.65 |
|
| 42 |
+
| Precision | 0.65 |
|
| 43 |
+
| Recall | 0.65 |
|
| 44 |
+
| F1-score | 0.65 |
|
| 45 |
+
|
| 46 |
+
> These metrics reflect experimental performance and are intended for learning and demonstration purposes.
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## Citation
|
| 51 |
+
|
| 52 |
+
If you use this model for research or portfolio demonstrations, you can cite:
|
| 53 |
+
|
| 54 |
+
```
|
| 55 |
+
@misc{rakesh-mohan-2025-distilbertclinicalner,
|
| 56 |
+
title={distilbert-clinical-ner: A Biomedical NER Model},
|
| 57 |
+
author={Rakesh Mohan},
|
| 58 |
+
year={2025},
|
| 59 |
+
howpublished={\url{https://huggingface.co/rm0013/distilbert-clinical-ner}}
|
| 60 |
+
}
|
| 61 |
+
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
---
|