Comparison between clinician and machine learning prediction in a randomized controlled trial for nonsuicidal self-injury.

Journal: BMC psychiatry
PMID:

Abstract

BACKGROUND: Nonsuicidal self-injury is a common health problem in adolescents and associated with future suicidal behavior. Predicting who will benefit from treatment is an urgent and a critical first step towards personalized treatment approaches. Machine-learning algorithms have been proposed as techniques that might outperform clinicians' judgment. The aim of this study was to explore clinician predictions of which adolescents would abstain from nonsuicidal self-injury after treatment as well as how these predictions match machine-learning algorithm predictions.

Authors

  • Moa Pontén
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden. moa.ponten@ki.se.
  • Oskar Flygare
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Karolinska University Hospital, Karolinska Institutet, M46, SE-141 86, Huddinge, Sweden. oskar.flygare@ki.se.
  • Martin Bellander
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.
  • Moa Karemyr
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.
  • Jannike Nilbrink
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.
  • Clara Hellner
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.
  • Olivia Ojala
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.
  • Johan Bjureberg
    Centre for Psychiatry Research, Department of Clinical Neuroscience, Stockholm, Karolinska Institutet, Sweden & Stockholm Health Care Services, Region Stockholm, Norra Stationsgatan 69, 113 64, Stockholm, Sweden.