Automated Peer Review Quality Prediction: Can ML Identify Accept/Reject Outcomes Before Submission?

Key Points

• The aim is to explore whether machine learning can accurately predict the outcomes of peer review processes before article submission.
• Utilized machine learning algorithms to analyze prior peer review outcomes.
• Developed a predictive model to assess accept/reject outcomes based on submission data.
• Tested the model with previously reviewed articles for validation.
• The model successfully predicted accept/reject outcomes with an accuracy of 85%.
• Sensitivity for accept predictions was 78%, and specificity for reject predictions was 82%.
• The findings suggest that using machine learning could streamline peer review processes.