Using automation to produce a ‘living map’ of the COVID-19 research literature

Abstract

The COVID-19 pandemic has disrupted life worldwide and presented unique challenges in the health evidence
synthesis space. The urgent nature of the pandemic required extreme rapidity for keeping track of research, and
this presented a unique opportunity for long-proposed automation systems to be deployed and evaluated. We
compared the use of novel automation technologies with conventional manual screening; and Microsoft Academic
Graph (MAG) with the MEDLINE and Embase databases locating the emerging research evidence. We found
that a new workflow involving machine learning to identify relevant research in MAG achieved a much higher
recall with lower manual effort than using conventional approaches.