System RCT Classifier
Description
This is a BERT-based model intended for identifying Randomized-Controlled Trials based on title and abstract. It is fine-tuned based on https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract, with an additional binary classifier layer.
Model Performance
F1 Score
In out-of-sample testing, the model exhibits an F1 score of 0.93 on a sample of 500 abstracts from PubMed.
Confusion Matrix
![](https://cdn-uploads.huggingface.co/production/uploads/6489f259cc46206353925a71/12vCXtlTJtt01o6dP8ee7.png)
Use
This model is made available under the Open RAIL-M license.
![](https://cdn-uploads.huggingface.co/production/uploads/6489f259cc46206353925a71/EHWzmLDJf9jvqoe0Hks-V.png)
- Downloads last month
- 0