RoBIn: A Transformer-based model for risk of bias inference with machine reading comprehension.

Journal: Journal of biomedical informatics
Published Date:

Abstract

OBJECTIVE: Scientific publications are essential for uncovering insights, testing new drugs, and informing healthcare policies. Evaluating the quality of these publications often involves assessing their Risk of Bias (RoB), a task traditionally performed by human reviewers. The goal of this work is to create a dataset and develop models that allow automated RoB assessment in clinical trials.

Authors

  • Abel Corrêa Dias
    Instituto de Informatica, Av. Bento Goncalves 9500 - Caixa Postal 15064, Porto Alegre, 91501-970, Rio Grande do Sul, Brazil.
  • Viviane Pereira Moreira
    Instituto de Informatica, Av. Bento Goncalves 9500 - Caixa Postal 15064, Porto Alegre, 91501-970, Rio Grande do Sul, Brazil.
  • João Luiz Dihl Comba
    Instituto de Informatica, Av. Bento Goncalves 9500 - Caixa Postal 15064, Porto Alegre, 91501-970, Rio Grande do Sul, Brazil. Electronic address: joao.comba@gmail.com.