A predictive risk assessment tool that can identify children at risk of abuse, developed by a New Zealand researcher and implemented for two years in the United States, has been found to improve the accuracy of referral screening decisions. The Ministry of Social development originally commissioned Professor Rhema Vaithianathan, Co-Director of the Centre for Social Data Analytics at AUT to develop the model. It uses data about children and their families to identify those at risk of physical, sexual or emotional abuse before the age of two. MSD stopped short of implementing the tool, but Allegheny County in Pittsburg, Pennsylvania began using it in 2016, and commissioned Stanford University researchers to evaluate its effectiveness. Kathryn talks and Rhema Vaithianathan.