22 May 2019

Can a computer model accurately identify kids at risk of abuse?

From Nine To Noon, 9:42 am on 22 May 2019
No caption

Photo: 123RF

Kathryn speaks with Stanford University Associate Professor of Medicine, Jeremy Goldhaber-Fiebert, who has evaluated the effectiveness of a predictive risk assessment tool developed by a New Zealand researcher and implemented for two years in the United States. 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, Pensylvania began using it in 2016, and commissioned Stanford University researchers to evaluate it.