Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🤖 RoBERTa ADR Severity Classifier
|
| 2 |
|
| 3 |
This is a fine-tuned [RoBERTa](https://huggingface.co/roberta-base) model that detects **Adverse Drug Reactions (ADRs)** and classifies them as either **severe** (`1`) or **not severe** (`0`). It is trained on annotated ADR text data and is part of a broader NLP pipeline that extracts symptoms, diseases, and medications from biomedical reports.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- roberta
|
| 5 |
+
- text-classification
|
| 6 |
+
- healthcare
|
| 7 |
+
- biomedical
|
| 8 |
+
- adverse-drug-reaction
|
| 9 |
+
- nlp
|
| 10 |
+
datasets:
|
| 11 |
+
- custom
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
model-index:
|
| 15 |
+
- name: RoBERTa ADR Severity Classifier
|
| 16 |
+
results:
|
| 17 |
+
- task:
|
| 18 |
+
name: Text Classification
|
| 19 |
+
type: text-classification
|
| 20 |
+
metrics:
|
| 21 |
+
- type: accuracy
|
| 22 |
+
value: 0.891
|
| 23 |
+
- type: f1
|
| 24 |
+
value: 0.891
|
| 25 |
+
- type: auc
|
| 26 |
+
value: 0.956
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
# 🤖 RoBERTa ADR Severity Classifier
|
| 30 |
|
| 31 |
This is a fine-tuned [RoBERTa](https://huggingface.co/roberta-base) model that detects **Adverse Drug Reactions (ADRs)** and classifies them as either **severe** (`1`) or **not severe** (`0`). It is trained on annotated ADR text data and is part of a broader NLP pipeline that extracts symptoms, diseases, and medications from biomedical reports.
|