An Explainable Artificial Intelligence Text Classifier for Suicidality Prediction in Youth Crisis Text Line Users: Development and Validation Study.

Journal: JMIR public health and surveillance
PMID: 39879608

Abstract

BACKGROUND: Suicide represents a critical public health concern, and machine learning (ML) models offer the potential for identifying at-risk individuals. Recent studies using benchmark datasets and real-world social media data have demonstrated the capability of pretrained large language models in predicting suicidal ideation and behaviors (SIB) in speech and text.

Authors

  • Julia Thomas
    Division of Clinical Psychology and Epidemiology, Faculty of Psychology, University of Basel, Basel, Switzerland.
  • Antonia Lucht
    Department of Research, Analytics and Development, krisenchat gGmbH, Berlin, Germany.
  • Jacob Segler
    Division of Child and Adolescent Psychiatry/Psychotherapy, Universitätsklinikum Ulm, Ulm, Germany.
  • Richard Wundrack
    Department of Research, Analytics and Development, krisenchat gGmbH, Berlin, Germany.
  • Marcel Miché
    University of Basel, Department of Psychology, Division of Clinical Psychology and Epidemiology, Basel, Switzerland.
  • Roselind Lieb
    University of Basel, Department of Psychology, Division of Clinical Psychology and Epidemiology, Basel, Switzerland. Electronic address: roselind.lieb@unibas.ch.
  • Lars Kuchinke
    Division of Methods and Statistics, International Psychoanalytic University Berlin, Berlin, Germany.
  • Gunther Meinlschmidt
    Division of Clinical Psychology and Cognitive Behavioural Therapy, International Psychoanalytic University (IPU) Berlin, Berlin, Germany. meinlschmidt@uni-trier.de.

Keywords

External Resources

Popular Topics
Recent Journals