Predicting criminal offence in adolescents who exhibit antisocial behaviour: a machine learning study using data from a large randomised controlled trial of multisystemic therapy.

Journal: European child & adolescent psychiatry
Published Date:

Abstract

INTRODUCTION: Accurate prediction of short-term offending in young people exhibiting antisocial behaviour could support targeted interventions. Here we develop a set of machine learning (ML) models that predict offending status with good accuracy; furthermore, we show interpretable ML analyses can complement models to inform clinical decision-making.

Authors

  • Jae Won Suh
    CORE Data Lab, Centre for Outcomes Research and Effectiveness, Research Department of Clinical, Educational and Health Psychology, University College London, London, UK. j.suh@ucl.ac.uk.
  • Rob Saunders
    CORE Data Lab, Centre for Outcomes Research and Effectiveness, Research Department of Clinical, Educational and Health Psychology, University College London, London, UK.
  • Elizabeth Simes
    Research Department of Clinical, Educational and Health Psychology, University College London, London, UK.
  • Henry Delamain
    CORE Data Lab, Centre for Outcomes Research and Effectiveness, Research Department of Clinical, Educational and Health Psychology, University College London, London, UK.
  • Stephen Butler
    Research Department of Clinical, Educational and Health Psychology, University College London, London, UK.
  • David Cottrell
    Leeds Institute of Health Sciences, University of Leeds, Leeds, UK.
  • Abdullah Kraam
    University of Leeds, Leeds, UK.
  • Stephen Scott
  • Ian M Goodyer
    Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; Cambridgeshire and Peterborough NHS Foundation Trust, Cambridge, United Kingdom.
  • James Wason
    Population Health Sciences Institute, Newcastle University, Newcastle upon Tyne, UK.
  • Stephen Pilling
    CORE Data Lab, Centre for Outcomes Research and Effectiveness, Research Department of Clinical, Educational and Health Psychology, University College London, London, UK.
  • Peter Fonagy
    Research Department of Clinical, Educational, and Health Psychology, University College London, London, United Kingdom.