Advantages of Machine Learning in Forensic Psychiatric Research—Uncovering the Complexities of Aggressive Behavior in Schizophrenia

Linear statistical methods may not be suited to the understanding of psychiatric phenomena such as aggression due to their complexity and multifactorial origins. Here, the application of machine learning (ML) algorithms offers the possibility of analyzing a large number of influencing factors and their interactions. This study aimed to explore inpatient aggression in offender patients with schizophrenia spectrum disorders (SSDs) using a suitable ML model on a dataset of 370 patients. With a balanced accuracy of 77.6% and an AUC of 0.87, support vector machines (SVM) outperformed all the other ML algorithms. Negative behavior toward other patients, the breaking of ward rules, the PANSS score at admission as well as poor impulse control and impulsivity emerged as the most predictive variables in distinguishing aggressive from non-aggressive patients. The present study serves as an example of the practical use of ML in forensic psychiatric research regarding the complex interplay between the factors contributing to aggressive behavior in SSD. Through its application, it could be shown that mental illness and the antisocial behavior associated with it outweighed other predictors. The fact that SSD is also highly associated with antisocial behavior emphasizes the importance of early detection and sufficient treatment.

Testing the Reliability and Construct Validity of Short-Term Assessment of Risk and Treatability (START) in Non-Western Forensic Psychiatric Inpatients

The Short-Term Assessment of Risk and Treatability (START) is deemed the most appropriate instrument for assessing violence risks and management because of its balanced approach between dynamic risk and protective factors. Although several facets of reliability and predictive validity of this tool were strong, its inter-rater reliability, construct validity, and implementation in Asian population were under-investigated. The objective of this research was to examine the inter-rater reliability and construct validity of the START: Thai version within forensic psychiatric inpatients. The participants consisted of 118 forensic psychiatric inpatients hospitalized at Galya Rajanagarindra Institute in Thailand. Trained mental health professionals (i.e., psychiatrists, forensic nurses, clinical psychologists, social workers, and occupational therapists) assessed each participant across twenty domains of the Thai START. The inter-rater reliability was examined using the intraclass correlation coefficient and a confirmatory factor analysis for ordinal data was used to test the construct validity of the scale. The main finding showed a good-to-excellent inter-rater reliability and supported two relational constructs (i.e., strength vs vulnerability subscales) of the Thai START. The Thai START is a promising tool for using in Thai forensic psychiatric setting but some items were not significant in contributing to the scale. This study also provides the guideline for implementing the tool in non-Western forensic psychiatric populations.

The Reconvictions of Mentally Disordered Offenders - How, When, and Where?

Background Little is known about the recidivism of mentally disordered offenders after discharge from forensic psychiatric services. This is problematic because such knowledge could (i) help professionals who come into contact with this group to better plan interventions to prevent recidivism and (ii) clarify the effectiveness of forensic psychiatric care. The aim of this study was to investigate the new crimes of mentally disordered offenders who had been reconvicted after discharge from forensic psychiatric care. Methods Included in this study were all individuals who had been discharged from forensic psychiatric care in Sweden during 2009-2018, were included in the Swedish National Forensic Psychiatric Register, and had been reconvicted in a criminal court within the follow-up period of 2009-2018 (n=157). Retrospective registry data along with coded data from criminal judgments (n=210) were used to create a database. Descriptive statistical analysis was performed. Results 75% of included individuals were reconvicted for at least one violent crime, but only 9 individuals were reconvicted for a serious violent crime, which can be compared to the 44 individuals with serious violent index crimes. The most common crime was “Other violent”. The most common sentence was probation. The offender’s most common relationship to the victim was having no known relationship, followed by the victim being a person of authority. The most common circumstance of the crime leading to the reconviction was that it occurred without apparent provocation; other common circumstances were related to the exercise of public authority. The most common crime scene was a public place. Conclusions Even though the reconvictions of this group included many violent crimes, there were very few serious violent crimes. The finding that the victims of the crimes of mentally disordered offenders are most commonly either unknown to the perpetrator or persons of authority, and that the crimes are often perpetrated without apparent provocation or reason, is important information for all professionals who come into contact with this group and should be taken into consideration in order to assess risk more accurately.

Crimes and sentences in individuals with intellectual disability in a forensic psychiatric context: a register-based study

Aims To study associations between intellectual disability (ID) and sexual and violent offending among individuals subject to pre-trial forensic psychiatric assessment. To investigate sentences following pre-trial forensic psychiatric assessment in offenders with and without ID. Methods A population-based observational study using data from pre-trial forensic psychiatric assessments in Sweden (1997–2013), the Swedish National Crime Register and several other Swedish national registers. The study population consisted of 7450 offenders (87% men, 13% women) who were subject to forensic psychiatric assessment in 1997–2013, of whom 481 (6.5%) were clinically assessed as having ID. Results ID offenders were more likely than non-ID offenders to have a sexual crime as an index crime [26.2 v. 11.5%, adjusted odds ratio (OR) 2.7, 95% confidence interval (CI) 2.02–3.58] as well as previous convictions regarding sexual offending (10.4 v. 5.6%, adj OR 2.3, 95% CI 1.70–3.12). These associations were restricted to male offenders; sexual offending was uncommon among women. Comorbid attention-deficit hyperactivity disorder reduced the association between ID and sexual offending (adj OR 2.7 v. 3.1, p = 0.017), while comorbid autism spectrum disorder had no significant influence on the association (adj OR 2.7 v. 3.0, p = 0.059). Violent crime was equally common among ID and non-ID offenders. Offenders with ID were more likely than non-ID offenders to be sentenced to forensic psychiatric care or community sanctions and measures (such as probation, conditional sentences or fines) than to prison; however, 15% of individuals who received an ID diagnosis during the forensic psychiatric assessment were sentenced to prison. Previous criminal convictions, concurrent antisocial personality disorders and substance use disorders were associated with a higher probability of a prison sentence among offenders with ID. Conclusions Sexual crime is overrepresented among offenders with ID compared to offenders with other mental disorders than ID in forensic psychiatric contexts. ID offenders become subject to forensic psychiatric care and forensic psychiatric services need evidence-based treatment programmes for offenders with ID. In addition, there is a need for early intervention strategies suitable for disability services and special education schools, in order to address the complex needs of individuals with ID and prevent sexual and violent offending.

Is a Forensic Cohabitation Program Recovery-Oriented? A Logic Model Analysis

Background. Recovery orientation is a movement in mental health practice. Although general mental health services have taken the lead in promoting recovery, forensic psychiatric systems have lagged behind because of the need to reconcile recovery principles with the complexities of legal mandates. Advocating recovery and making systemic changes can be challenging because they require seeking a balance between the competing duties to the patient and the public. This paper used a logic model framework to demonstrate a cohabitation program that placed a woman and her newborn infant in a secure forensic rehabilitation unit, and analyzed the key assumptions of recovery upon which it was based. Methods. This was a qualitative program evaluation. Data collection involved individual interviews with the woman, the infant’s father, five primary healthcare providers, and five system administrators, and 11 focus groups with unit staff and other patients. Content analysis was used to guide the data analysis and develop the critical components of the program logic model. Results. A logic model that consists of input (team building, program planning, staff and patient preparation, resource management), output (logistic activities, risk management, mental healthcare, staff/other patient support, discharge preparation), and outcome (individual, provider, system, and society) components was developed. Conclusions. This study demonstrates a recovery-oriented program for a woman cohabitating with her baby in a secure forensic psychiatric rehabilitation unit. The logic model provided a comprehensive understanding of the way the recovery principles, such as shared decision-making, positive risk-taking, informed choices, and relational security, were implemented.

Self-Harm Among Forensic Psychiatric Inpatients With Schizophrenia Spectrum Disorders: An Explorative Analysis

The burden of self-injury among offenders undergoing inpatient treatment in forensic psychiatry is substantial. This exploratory study aims to add to the previously sparse literature on the correlates of self-injury in inpatient forensic patients with schizophrenia spectrum disorders (SSD). Employing a sample of 356 inpatients with SSD treated in a Swiss forensic psychiatry hospital, patient data on 512 potential predictor variables were retrospectively collected via file analysis. The dataset was examined using supervised machine learning to distinguish between patients who had engaged in self-injurious behavior during forensic hospitalization and those who had not. Based on a combination of ten variables, including psychiatric history, criminal history, psychopathology, and pharmacotherapy, the final machine learning model was able to discriminate between self-injury and no self-injury with a balanced accuracy of 68% and a predictive power of AUC = 71%. Results suggest that forensic psychiatric patients with SSD who self-injured were younger both at the time of onset and at the time of first entry into the federal criminal record. They exhibited more severe psychopathological symptoms at the time of admission, including higher levels of depression and anxiety and greater difficulty with abstract reasoning. Of all the predictors identified, symptoms of depression and anxiety may be the most promising treatment targets for the prevention of self-injury in inpatient forensic patients with SSD due to their modifiability and should be further substantiated in future studies.

Nachsorge unter erschwerten Vorzeichen – Erfahrungen forensischer Nachsorgeambulanzen mit Sexualstraftätern, die nach der Novelle der Verhältnismäßigkeitsregelung entlassen wurden

A major amendment of the German Criminal Code concerning treatment in forensic psychiatric hospitals (Secs. 63, 67 StGB) became effective in August 2016 and has led to an increasing number of discharges of sex offenders. In addition to inpatient treatment practice, this also poses great challenges for forensic aftercare. After a brief overview of the amendment, this article examines how it affects the release practice and legal probation. Based on the analysis of the post-inpatient development of ten sex offenders from North Rhine-Westphalia who were released for disproportionate reasons, the far-reaching consequences of the amendment forensic aftercare have to deal with are illustrated. Finally, attention is drawn to the great need for action and alternative solutions to reduce the length of stay and strengthens the patients fundamental right to freedom are proposed.