Research Alert

Premature birth is a major global health challenge and the leading cause of death in children under 5. In order to predict premature birth, it necessary to know the gestational age of a baby, which isn’t easy. Even if a woman knows the exact date of conception, babies conceived at the same time grow at different rates and can be born weeks apart.

Now, an international group of researchers led by the University of Wisconsin-Milwaukee and the University of Oxford have applied a machine learning technique they developed to substantially reduce the uncertainty in gestational age estimates. The paper is being published in the U.S. Monday, June 22, in the medical journal The Lancet Digital Health.