Prospective prediction of suicide attempts in community adolescents and young adults, using regression methods and machine learning.

Journal: Journal of affective disorders
PMID: 31786028

Abstract

BACKGROUND: The use of machine learning (ML) algorithms to study suicidality has recently been recommended. Our aim was to explore whether ML approaches have the potential to improve the prediction of suicide attempt (SA) risk. Using the epidemiological multiwave prospective-longitudinal Early Developmental Stages of Psychopathology (EDSP) data set, we compared four algorithms-logistic regression, lasso, ridge, and random forest-in predicting a future SA in a community sample of adolescents and young adults.

Authors

  • Marcel Miché
    University of Basel, Department of Psychology, Division of Clinical Psychology and Epidemiology, Basel, Switzerland.
  • Erich Studerus
    a University of Basel Psychiatric Clinics, Center for Gender Research and Early Detection , Basel , Switzerland.
  • Andrea Hans Meyer
    University of Basel, Department of Psychology, Division of Clinical Psychology and Epidemiology, Basel, Switzerland.
  • Andrew Thomas Gloster
    University of Basel, Department of Psychology, Division of Clinical Psychology and Intervention Science, Basel, Switzerland.
  • Katja Beesdo-Baum
    Institute of Clinical Psychology and Psychotherapy Technische Universität Dresden Dresden Germany; Behavioral Epidemiology Technische Universität Dresden Dresden Germany; Department of Psychology Neuroimaging CenterTechnische Universität Dresden Dresden Germany.
  • Hans-Ulrich Wittchen
  • Roselind Lieb
    University of Basel, Department of Psychology, Division of Clinical Psychology and Epidemiology, Basel, Switzerland. Electronic address: roselind.lieb@unibas.ch.

Keywords

External Resources

Popular Topics
Recent Journals