Paper #1236 presented at #husITa14 in Melbourne, Australia, July, 2014.
Rhema Vaithianathan (AUT University, New Zealand).
In the complex field of child protection many maltreated children do not receive help early enough to prevent serious harm. Professionals know that they may either overlook signs that children are unsafe or over-react when children actually are safe. In 2012, New Zealand’s Ministry of Social Development (MSD) commissioned a study to find out whether it is possible to use administrative data to identify children at risk of maltreatment. A research team, based at the University of Auckland’s Centre for Applied Research in Economics, used a data set linking administrative records held by MSD to develop a predictive risk modeling (PRM) tool with significant capacity to ascertain and stratify children’s risk of experiencing maltreatment in the future. The study found that although PRM cannot replace more-comprehensive clinical assessments, this approach could provide a simple and cost-effective method of targeting early prevention services. The use of the PRM tool is currently under consideration for inclusion in initiatives that are part of the New Zealand Children’s Action Plan.
In this joint presentation, the Principal Investigator, Associate Professor Rhema Vaithianathan, will describe how the tool was developed using stepwise probit modeling and show how PRM can be used to generate risk scores for substantiated maltreatment. Associate Professor Tim Dare will discuss ethical implications of using PRM, including predictable false positives; possible stigmatization of already vulnerable populations; probable use of data without consent; resource allocation issues; and difficulties in designing and implementing effective interventions. Dr Irene de Haan will discuss challenges and opportunities presented by use of PRM as part a public health approach to child maltreatment encompassing proportionate universalism. The question at the heart of the use of PRM is how it can be used to enhance well-being and prevent maltreatment.
Please use the reply section below to comment on and discuss this paper.
Back to programme