Artificial Intelligence and Machine Learning Could Enhance Scientific Peer Review of COVID-19 Papers

In some cases, poorly validated research has massively influenced public policy, as when a French team reported COVID patients were cured by a combination of hydroxychloroquine and azithromycin. The claim was widely publicized, and soon US patients were prescribed these drugs under an emergency use authorization. However, further research involving larger numbers of patients cast serious doubts on these claims.

Tudor Oprea, MD, PhD, professor of Medicine and Pharmaceutical Sciences and chief of the Division of Translational Informatics at the University of New Mexico (Albuquerque, NM, USA), notes that the sense of urgency to develop a vaccine and devise effective treatments for the coronavirus has led many scientists to bypass the traditional peer review process by publishing “preprints” - preliminary versions of their work - online. While that enables rapid dissemination of new findings, bad information may lead scientists and clinicians to waste time and money chasing blind leads.

In a commentary published in Nature Biotechnology, Oprea and his colleagues, many of whom work at AI companies, have suggested that AI and ML can harness massive computing power to check many of the claims that are being made in a research paper. Since the COVID epidemic took hold, Oprea himself has used advanced computational methods to help identify existing drugs with potential antiviral activity, culled from a library of thousands of candidates.

“I think there is tremendous potential there,” said Oprea. “I think we are on the cusp of developing tools that will assist with the peer review process.”

Although the tools are not fully developed, “We’re getting really, really close to enabling automated systems to digest tons of publications and look for discrepancies,” he says. “I am not aware of any such system that is currently in place, but we’re suggesting with adequate funding this can become available.”

Text mining, in which a computer combs through millions of pages of text looking for specified patterns, has already been “tremendously helpful,” added Oprea. “We’re making progress in that.”

“We’re not saying we have a cure for peer review deficiency, but we are saying that that a cure is within reach, and we can improve the way the system is currently implemented,” he says. “As soon as next year we may be able to process a lot of these data and serve as additional resources to support the peer review process.”

Related Links:
University of New Mexico