Exploring substance use as rule-violating behaviour during inpatient treatment of offender patients with schizophrenia

Offence Paralleling Schema Modes in Institutional Violence

This study explored emotional patterns in relation to the Offence Paralleling Behavior and the schema mode frameworks. The study retrospectively assesses schema modes in the events prior and during criminal and institutional violent behavior. It draws upon observer-ratings of schema modes by 42 male patients who received mandated clinical care in a forensic hospital in the Netherlands. Wilcoxon Signed Ranked tests showed no differences between events prior crimes and incidents with regard to schema modes that relate to universal childhood needs with the exception of impulsive child mode. States of intoxication were more prevalent prior and during the crimes than during the incidents. Furthermore, modes tended to be less activated during incidents, particularly low self-control, conning and manipulating, and self-aggrandizer modes. It is hoped that criminal justice institutions and their staff would benefit from being more aware of schema mode in order to prevent and deal with incidental violence.

Correlates of Social Isolation in Forensic Psychiatric Patients with Schizophrenia Spectrum Disorders: An Explorative Analysis Using Machine Learning

The detrimental effects of social isolation on physical and mental health are well known. Social isolation is also known to be associated with criminal behavior, thus burdening not only the affected individual but society in general. Forensic psychiatric patients with schizophrenia spectrum disorders (SSD) are at a particularly high risk for lacking social integration and support due to their involvement with the criminal justice system and their severe mental illness. The present study aims to exploratively evaluate factors associated with social isolation in a unique sample of forensic psychiatric patients with SSD using supervised machine learning (ML) in a sample of 370 inpatients. Out of >500 possible predictor variables, 5 emerged as most influential in the ML model: attention disorder, alogia, crime motivated by ego disturbances, total PANSS score, and a history of negative symptoms. With a balanced accuracy of 69% and an AUC of 0.74, the model showed a substantial performance in differentiating between patients with and without social isolation. The findings show that social isolation in forensic psychiatric patients with SSD is mainly influenced by factors related to illness and psychopathology instead of factors related to the committed offences, e.g., the severity of the crime.

Model Building in Forensic Psychiatry: A Machine Learning Approach to Screening Offender Patients with SSD

Today’s extensive availability of medical data enables the development of predictive models, but this requires suitable statistical methods, such as machine learning (ML). Especially in forensic psychiatry, a complex and cost-intensive field with risk assessments and predictions of treatment outcomes as central tasks, there is a need for such predictive tools, for example, to anticipate complex treatment courses and to be able to offer appropriate therapy on an individualized basis. This study aimed to develop a first basic model for the anticipation of adverse treatment courses based on prior compulsory admission and/or conviction as simple and easily objectifiable parameters in offender patients with a schizophrenia spectrum disorder (SSD). With a balanced accuracy of 67% and an AUC of 0.72, gradient boosting proved to be the optimal ML algorithm. Antisocial behavior, physical violence against staff, rule breaking, hyperactivity, delusions of grandeur, fewer feelings of guilt, the need for compulsory isolation, cannabis abuse/dependence, a higher dose of antipsychotics (measured by the olanzapine half-life) and an unfavorable legal prognosis emerged as the ten most influential variables out of a dataset with 209 parameters. Our findings could demonstrate an example of the use of ML in the development of an easy-to-use predictive model based on few objectifiable factors.