[Preventing violence in schizophrenia with cognitive remediation]

Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia

Objective

To establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.

Methods

The cluster sampling method was used to select patients with schizophrenia who were hospitalized in our hospital from July 2019 to August 2021 as the survey objects, and they were divided into an aggressive behavior group (611 cases) and a non-aggressive behavior group (1,426 cases) according to whether they experienced obvious aggressive behaviors during hospitalization. Self-administered General Condition Questionnaire, Insight and Treatment Attitude Questionnaire (ITAQ), Family APGAR (Adaptation, Partnership, Growth, Affection, Resolve) Questionnaire (APGAR), Social Support Rating Scale Questionnaire (SSRS) and Family Burden Scale of Disease Questionnaire (FBS) were used for the survey. The Multi-layer Perceptron, Lasso, Support Vector Machine and Random Forest algorithms were used to build a predictive model for the occurrence of aggressive behaviors from hospitalized patients with schizophrenia and to evaluate its predictive effect. Nomogram was used to build a clinical application tool.

Results

The area under the receiver operating characteristic curve (AUC) values of the Multi-Layer Perceptron, Lasso, Support Vector Machine, and Random Forest were 0.904 (95% CI: 0.877-0.926), 0.901 (95% CI: 0.874-0.923), 0.902 (95% CI: 0.876-0.924), and 0.955 (95% CI: 0.935-0.970), where the AUCs of the Random Forest and the remaining three models were statistically different (p < 0.0001), and the remaining three models were not statistically different in pair comparisons (p > 0.5).

Conclusion

Machine learning models can fairly predict aggressive behaviors in hospitalized patients with schizophrenia, among which Random Forest has the best predictive effect and has some value in clinical application.

Substance Abuse Associated with Aggressive/Violent Behaviors in Psychiatric Outpatients and Related Psychotropic Prescription

Psychiatric disorders with substance abuse are considered the leading causes of most violent and aggressive behaviors in the general population. This study was aimed to assess the impact of substance abuse and the therapeutic approaches adopted by psychiatrists in aggressive vs non-aggressive outpatients (n = 400) attending community-based psychiatric services and recruited over a 3-year period. Clinical and therapeutic variables were collected from medical records and the Modified Overt Aggression Scale (MOAS) was used to assess any aggressive/violent behavior. Violent behaviors were significantly higher in alcohol and substance abusers compared to non-abusers (p < 0.01), except for heroin abusers. Mean weighted MOAS score was significantly higher in patients taking antipsychotics (p < 0.005). The administration of Haloperidol, Zuclopenthixol, and Clozapine was more frequent in aggressive than in non-aggressive patients. The most frequently administered drug in these patients was Haloperidol (23.91%), with a higher mean daily dosage in violent vs non-violent patients. Our results confirm the well-established relationship between substance abuse and violent behaviors in psychiatric inpatients also within outpatient community services. Observed rates of most frequently prescribed antipsychotics to aggressive patients did not show any preference for newer generation compounds, with clinicians operating in the community setting likely being in need for further evidence and specific training to support their treatment choice.

The neural basis of hostility-related dimensions in schizophrenia

Hostility and related dimensions like anger, urgency, impulsivity and aggressiveness have been described in non-clinical populations and various serious mental illnesses including schizophrenia. Although representing a mental healthcare challenge, the investigation of such constructs is often limited by the presence of complex and multi-factorial causes and lack of agreement in their conceptualisation and measurement. In this review, we aim to clarify the anatomical basis of hostility-related dimensions in schizophrenia. Imaging studies suggest malfunctioning of a neural circuitry including amygdala, striatum, prefrontal cortex, anterior cingulate cortex, insula and hippocampus to modulate hostile thoughts and behaviours, at least in the subgroup of patients with schizophrenia who exhibit high levels of urgency, impulsivity and aggressiveness.