This study explores underlying patterns in suicide risk factors using data mining techniques. Medical records of suicide attempters who were admitted to a teaching hospital in January 2004 - December 2006 were studied. Cluster analysis revealed hidden patterns for repeated and single attempters (n=418). Repeated attempters had a more complex clinical picture. Symptoms of psychotic illness, borderline personality disorder, and psychosomatic complaints of insomnia and headaches, reports of adverse life events such as unemployment, divorce and quarrels, experience of negative feelings, and usage of alcohol were associated with risk of repeated overdoses with benzodiazepines and paracetamol. The findings have implications for suicide assessments and interventions.
Keywords: Borderline personality disorder; Cluster analysis; Data mining; Psychotic illness; Repeated suicide attempts; Risk factors.
Copyright © 2013 Elsevier B.V. All rights reserved.