When do drugs trigger criminal behavior? a machine learning analysis of offenders and non-offenders with schizophrenia and comorbid substance use disorder

Aug 6, 2026

Comorbid substance use disorder is linked to elevated violence risk in patients with schizophrenia spectrum disorder. This study uses supervised machine learning to identify the most distinguishing factors between offending and non-offending patients sharing SSD and comorbid substance use disorder. In a sample of 269 offenders and 184 non-offenders, failures during opening events and non-compliance with medication history emerged as leading discriminators. Findings highlight treatment-related differences and support improving access and continuity of care in this population.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Violence risk in schizophrenia spectrum disorder

Role of substance use disorder and ongoing debate

Methods

Study design and supervised machine learning approach

Results

Key differentiating factors between groups

Discussion

Implications for treatment access and future research

Zurich Open Repository and Archive University of Zurich University Library Strickhofstrasse 39 CH-8057 Zurich [www.zora.uzh.ch](www.zora.uzh.ch) Year: 2024 When do drugs trigger criminal behavior? a machine learning analysis of offenders and non-offenders with schizophrenia and comorbid substance use disorder Bender, Ewa-Maria ; Machetanz, Lena ; von Känel, Roland ; Euler, Sebastian ; Kirchebner, Johannes ; Günther, Moritz Philipp DOI: [https://doi.org/10.3389/fpsyt.2024.1356843](https://doi.org/10.3389/fpsyt.2024.1356843) Posted at the Zurich Open Repository and Archive, University of Zurich ZORA URL: [https://doi.org/10.5167/uzh-265543](https://doi.org/10.5167/uzh-265543) Journal Article Published Version The following work is licensed under a Creative Commons: Attribution 4.0 International (CC BY 4.0) License. Originally published at: Bender, Ewa-Maria; Machetanz, Lena; von Känel, Roland; Euler, Sebastian; Kirchebner, Johannes; Günther, Moritz Philipp (2024) . When do drugs trigger criminal behavior? a machine learning analysis of offenders and non-offenders with schizophrenia and comorbid substance use disorder. Frontiers in Psychiatry, 15:1356843 . DOI: [https://doi.org/10.3389/fpsyt.2024.1356843](https://doi.org/10.3389/fpsyt.2024.1356843) TYPE Original Research PUBLISHED 07 March 2024 DOI 10.3389/fpsyt.2024.1356843 OPEN ACCESS EDITED BY Giovanna Parmigiani, Sapienza University of Rome, Italy REVIEWED BY Valentin Matei, Carol Davila University of Medicine and Pharmacy, Romania Marta Bosia, Vita-Salute San Raffaele University, Italy *CORRESPONDENCE Lena Machetanz lena. machetanz@pukzh. ch Johannes Kirchebner johannes. kirchebner@pukzh. ch Moritz Philipp Günther [moritzphilipp.guenther@usz.ch](moritzphilipp.guenther@usz.ch) RECEIVED 16 December 2023 ACCEPTED 14 February 2024 PUBLISHED 07 March 2024 CITATION Bender E-M, Machetanz L, von Känel R, Euler S, Kirchebner J and Günther MP (2024) When do drugs trigger criminal behavior? a machine learning analysis of offenders and non-offenders with schizophrenia and comorbid substance use disorder. Front. Psychiatry 15:1356843 . doi: 10.3389/fpsyt.2024.1356843 COPYRIGHT © 2024 Bender, Machetanz, von Känel, Euler, Kirchebner and Günther. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. When do drugs trigger criminal behavior? a machine learning analysis of offenders and nonoffenders with schizophrenia and comorbid substance use disorder Ewa-Maria Bender 1, Lena Machetanz 2*, Roland von Känel 1, Sebastian Euler 1, Johannes Kirchebner 2* and Moritz Philipp Günther 1,3* 1 Department of Consultation-Liaison Psychiatry and Psychosomatic Medicine, University Hospital Zurich, University of Zürich, Zurich, Switzerland, 2 Department of Forensic Psychiatry, University Hospital of Psychiatry Zurich, Zurich, Switzerland, 3 Privatklinik Meiringen, Willigen, Meiringen, Switzerland Introduction: Comorbid substance use disorder (SUD) is linked to a higher risk of violence in patients with schizophrenia spectrum disorder (SSD) . The objective of this study is to explore the most distinguishing factors between offending and non-offending patients diagnosed with SSD and comorbid SUD using supervised machine learning. Methods: A total of 269 offender patients and 184 non-offender patients, all diagnosed with SSD and SUD, were assessed using supervised machine learning algorithms. Results: Failures during opening, referring to rule violations during a permitted temporary leave from an inpatient ward or during the open

FAQs

What is the main objective of the study?

To explore the most distinguishing factors between offending and non-offending patients diagnosed with schizophrenia spectrum disorder with comorbid substance use disorder, using supervised machine learning.

How many patients were included and how were groups defined?

The study assessed 269 offender patients and 184 non-offender patients, all diagnosed with SSD and comorbid substance use disorder.

Which factors most strongly differentiated offenders from non-offenders?

Failures during opening related to rule violations during temporary leave or ward opening were the most influential factor, followed closely by non-compliance with medication in the psychiatric history.

What does the discussion conclude and what future research is suggested?

The results emphasize treatment-related differences and indicate potential improvements in access and maintenance of treatment. Further research is warranted to explore the relationship between social isolation and delinquency in this population.

Aug 6, 2026

Upload by Emma Wilson