Psychosocial function, legal involvement and violence in mental disorder

Predictors of psychosocial functioning in people diagnosed with schizophrenia spectrum disorders that committed violent offences and in those that did not: Results of the Recoviwel study

Psychosocial functioning represents a core treatment target of Schizophrenia Spectrum Disorders (SSD), and several clinical and cognitive factors contribute to its impairment. However, determinants of psychosocial functioning in people living with SSD that committed violent offences remain to be more thoroughly explored. This study aims to separately assess and compare predictors of psychosocial functioning in people with SSD that did and that did not commit violent offences considering several clinical, cognitive and violence-related parameters. Fifty inmates convicted for violent crimes in a forensic psychiatry setting diagnosed with SSD (OP group) and fifty participants matched for age, gender, education, and diagnosis (Non-OP group) were included in the study. A higher risk of violent relapse as measured by HCR-20 clinical subscale scores (p < 0.002) and greater global clinical severity as measured by CGI-S scores (p = 0.023) emerged as individual predictors of worse psychosocial functioning, as measured by PSP scores, in the OP group. Greater global clinical severity (p < 0.001), worse performance in the processing speed domain as measured by the BACS Symbol Coding (p = 0.002) and TMT-A tests (p = 0.016) and higher levels of non-planning impulsivity as measured by BIS-11 scores (p < 0.001) emerged as individual predictors of worse psychosocial functioning in the Non-OP group. These results confirm that clinical severity impacts psychosocial functioning in all individuals diagnosed with SSD and suggest that while cognitive impairment clearly represents a determinant of worse functional outcomes in most patients, the risk of violent relapse is a specific predictor of worse psychosocial functioning in people with SSD that committed criminal offences.

The Prediction and Influential Factors of Violence in Male Schizophrenia Patients With Machine Learning Algorithms

BACKGROUND

Early to identify male schizophrenia patients with violence is important for the performance of targeted measures and closer monitoring, but it is difficult to use conventional risk factors. This study is aimed to employ machine learning (ML) algorithms combined with routine data to predict violent behavior among male schizophrenia patients. Moreover, the identified best model might be utilized to calculate the probability of an individual committing violence.

METHOD

We enrolled a total of 397 male schizophrenia patients and randomly stratified them into the training set and the testing set, in a 7:3 ratio. We used eight ML algorithms to develop the predictive models. The main variables as input features selected by the least absolute shrinkage and selection operator (LASSO) and logistic regression (LR) were integrated into prediction models for violence among male schizophrenia patients. In the training set, 10 × 10-fold cross-validation was conducted to adjust the parameters. In the testing set, we evaluated and compared the predictive performance of eight ML algorithms in terms of area under the curve (AUC) for the receiver operating characteristic curve.

RESULT

Our results showed the prevalence of violence among male schizophrenia patients was 36.8%. The LASSO and LR identified main risk factors for violent behavior in patients with schizophrenia integrated into the predictive models, including lower education level [0.556 (0.378-0.816)], having cigarette smoking [2.121 (1.191-3.779)], higher positive syndrome [1.016 (1.002-1.031)] and higher social disability screening schedule (SDSS) [1.081 (1.026-1.139)]. The Neural Net (nnet) with an AUC of 0.6673 (0.5599-0.7748) had better prediction ability than that of other algorithms.

CONCLUSION

ML algorithms are useful in early identifying male schizophrenia patients with violence and helping clinicians take preventive measures.