Photo Credit: Evgeniy Shkolenko
The following is a summary of “When do drugs trigger criminal behavior? a machine learning analysis of offenders and non-offenders with schizophrenia and comorbid substance use disorder,” published in the March 2024 issue of Psychiatry by Bender et al.
People with both substance use disorder (SUD) and schizophrenia spectrum disorder (SSD) increase the risk of violence.
Researchers started a retrospective study using supervised machine learning to identify factors differentiating patients with SSD and SUD who commit crimes from those who don’t.
They assessed a total of 269 patients who were offenders and 184 patients who were non-offenders, all diagnosed with SSD and SUD, using supervised machine learning algorithms.
The results showed that failures during opening, referring to rule violations during a permitted temporary leave from an inpatient ward or during the opening of an otherwise closed ward, emerged as the most influential distinguishing factor, closely followed by non-compliance with medication (in the psychiatric history). Subsequently, social isolation in the past, absence of prescribed antipsychotics (in the psychiatric history), and lack of outpatient psychiatric treatments before the current hospitalization followed in succession.
Investigators concluded that treatment engagement was a key factor distinguishing violent and non-violent patients with SSD and SUD, suggesting a need for improved treatment access and adherence for this population.
Source: frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2024.1356843/full