Enhanced early prediction of clinically relevant neonatal hyperbilirubinemia with machine learning

Almost 10% of newborn infants develop significant hyperbilirubinemia, and many require phototherapy treatment. This is costly and can increase the likelihood of patients developing allergic diseases. However the costs of not treating neonatal jaundice can be more severe as it can cause lifelong disability. Precise patient monitoring and deliberate treatment assignment are therefore essential for at-risk neonates. In this episode, we meet Sven Wellman, then of the University of Basel's Children Hospital in Switzerland. He and his team developed an online tool that uses machine learning methods to accurately predict neonates at risk of developing clinically relevant hyperbilirubinemia. Related article: https://www.nature.com/articles/s41390-019-0384-x