system-technologies
/

BiomedNLP-BiomedBERT-abstract-RCT-classifier-public

Text Classification

Inference Endpoints

Model card Files Files and versions Community

Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

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

Use

This model is made available under the Open RAIL-M license.

For more information on System, visit https://about.system.com

Downloads last month: 3