Skip to Main Content

Long before the pace of scientific publishing about Covid-19 broke land speed records, researchers were struggling to keep tabs on new studies in their fields. And to lighten the load, they’re increasingly turning to tools powered by artificial intelligence.

Researchers at Utrecht University in the Netherlands have built one such tool for a particularly labor-intensive step in the scientific process: sifting through many thousands of papers to find the ones most relevant to researchers conducting systematic reviews. Their open-source program, ASReview, is described in a new paper published Monday in Nature Machine Intelligence.

Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!