Publications by authors named "Johannes Kirchebner"
Article Synopsis
- Advances in medical data and computer technology are enabling new research opportunities through machine learning (ML), which leverages complex algorithms to find patterns in large datasets.
- ML is particularly useful for studying multifactorial issues, such as mental health and forensic psychiatry, allowing researchers to quantify the effectiveness of their statistical models.
- The study analyzed 48 sociodemographic variables in 370 offender and 370 non-offender schizophrenia patients, using gradient boosting as the best algorithm, but found the ability to discriminate between the two groups based on these variables was limited, with an AUC of 0.65 indicating poor statistical discrimination.
Background: While several studies in cerebral amyloid angiopathy (CAA) focus on cognitive function, data on neuropsychiatric symptoms (NPS) and lifelong mental activities in these patients are scarce. Since NPS are associated with functional impairment, faster cognitive decline and faster progression to death, replication studies in more diverse settings and samples are warranted.
Methods: We prospectively recruited n = 69 CAA patients and n = 18 cognitively normal controls (NC).
The purpose of this study was to investigate the difference between offender female patients (OFS) and non-offender female patients (NOFS) with schizophrenia spectrum disorder (SSD).The patients in this study were admitted to the university psychiatry in Zurich Switzerland between 1982 and 2016. Demography, psychopathology, comorbidity, and treatment differences were analyzed using binary statistics to compare 31 OFS and 29 matching NOFS with SSD.
View Article and Find Full Text PDFInferior frontal sulcal hyperintensities (IFSHs) on fluid-attenuated inversion recovery (FLAIR) sequences have been proposed to be indicative of glymphatic dysfunction. Replication studies in large and diverse samples are nonetheless needed to confirm them as an imaging biomarker. We investigated whether IFSHs were tied to Alzheimer's disease (AD) pathology and cognitive performance.
View Article and Find Full Text PDFDelusions and Delinquencies: A Comparison of Violent and Non-Violent Offenders With Schizophrenia Spectrum Disorders.
Int J Offender Ther Comp Criminol
May 2024
The relationship between schizophrenia spectrum disorders (SSD) and violent offending has long been the subject of research. The present study attempts to identify the content of delusions, an understudied factor in this regard, that differentiates between violent and non-violent offenses. Limitations, clinical relevance, and future directions are discussed.
View Article and Find Full Text PDFArticle Synopsis
- Comorbid substance use disorder (SUD) increases violence risk in patients with schizophrenia spectrum disorder (SSD), prompting a study to identify key differences between offending and non-offending individuals.
- A total of 269 offender patients and 184 non-offender patients were analyzed using supervised machine learning, showing that rule violations during temporary leaves and medication non-compliance were significant distinguishing factors.
- The study highlights treatment-related differences as critical risk factors, suggesting that improving access and maintenance of treatment could benefit this population, and calls for further exploration of the connection between social isolation and delinquency.
Article Synopsis
- International cancer treatment guidelines suggest that nurses should routinely screen for patient distress to provide psycho-oncological support.
- This study uses machine learning to analyze data from 4,064 patients to identify factors predicting the decline of psycho-oncological support among patients.
- The findings indicate that older patients and those with lower distress scores are more likely to refuse support, highlighting the need for improved nurse training and time to address patient misconceptions about such assistance.
Background: Suffering from schizophrenia spectrum disorder (SSD) has been well-established as a risk factor for offending. However, the majority of patients with an SSD do not show aggressive or criminal behavior. Yet, there is little research on clinical key features distinguishing offender from non-offender patients.
View Article and Find Full Text PDFArticle Synopsis
- The study focuses on individuals with schizophrenia spectrum disorders (SSD) who have committed sex offenses, aiming to distinguish them from those with SSD who committed violent non-sex offenses.
- It analyzed patient records of 296 men admitted to a specialized center in Zurich, utilizing machine learning to assess 461 different variables to identify distinguishing features between the two groups.
- The findings revealed a machine learning model that successfully differentiated offenders with 71.5% accuracy, highlighting the importance of sexual behaviors, psychopathological symptoms, and typical offense characteristics in risk assessment and treatment strategies.
Article Synopsis
- Individuals with schizophrenia spectrum disorders have a higher risk of aggressive behavior, particularly when comorbid with substance use disorders.
- The study aimed to identify and compare risk factors related to aggressive behavior in offender vs. non-offender patients using machine learning algorithms on a dataset of 740 individuals with SSD.
- Gradient boosting was the most effective machine learning model, achieving high accuracy in distinguishing between the two groups based on key predictor variables like medication dosage, temporary leave failures, and education level, rather than psychopathology factors.
Article Synopsis
- Social isolation negatively impacts both physical and mental health, and is linked to increased criminal behavior, affecting individuals and society.
- Forensic psychiatric patients with schizophrenia spectrum disorders (SSD) are particularly vulnerable to social isolation due to their mental health issues and interactions with the criminal justice system.
- A study using machine learning analyzed 370 patients and identified five key factors contributing to social isolation, revealing that illness-related factors, rather than the nature of their crimes, are more significant in influencing their social integration.
Article Synopsis
- Forensic psychiatric settings tend to prescribe higher doses of antipsychotic medications and use polypharmacy more frequently than acute or community settings.
- A lack of research exists on offender patients with schizophrenia spectrum disorders (SSD), despite their significant presence in forensic settings.
- This study uniquely compares prescription patterns of antipsychotics and other medications between offender and non-offender patients with SSD, revealing that offenders receive higher doses, while non-offenders are more often prescribed polypharmacy and additional medications like antidepressants and benzodiazepines.
Article Synopsis
- The study highlights the critical role of social capital in helping offenders rehabilitate, particularly focusing on those with severe mental disorders like schizophrenia.
- Through machine learning analysis of 369 offenders, it identified key factors contributing to successful social reintegration after release, emphasizing social integration, insight into their condition, and treatment engagement.
- Surprisingly, the nature of the offense or the severity of mental illness had little impact on establishing social connections post-discharge, underscoring the potential for therapeutic interventions to enhance social support networks.
Today's extensive availability of medical data enables the development of predictive models, but this requires suitable statistical methods, such as machine learning (ML). Especially in forensic psychiatry, a complex and cost-intensive field with risk assessments and predictions of treatment outcomes as central tasks, there is a need for such predictive tools, for example, to anticipate complex treatment courses and to be able to offer appropriate therapy on an individualized basis. This study aimed to develop a first basic model for the anticipation of adverse treatment courses based on prior compulsory admission and/or conviction as simple and easily objectifiable parameters in offender patients with a schizophrenia spectrum disorder (SSD).
View Article and Find Full Text PDFExploring Characteristics of Homicide Offenders With Schizophrenia Spectrum Disorders Via Machine Learning.
Int J Offender Ther Comp Criminol
May 2024
The link between schizophrenia and homicide has long been the subject of research with significant impact on mental health policy, clinical practice, and public perception of people with psychiatric disorders. The present study investigates factors contributing to completed homicides committed by offenders diagnosed with schizophrenia referred to a Swiss forensic institution, using machine learning algorithms. Data were collected from 370 inpatients at the Centre for Inpatient Forensic Therapy at the Zurich University Hospital of Psychiatry.
View Article and Find Full Text PDFArticle Synopsis
- Rule-violating behavior related to substance misuse has been mostly studied in prisons, with less focus on forensic psychiatric settings.
- The study aimed to identify factors associated with substance misuse among patients with schizophrenia or similar disorders in a Swiss forensic psychiatric unit, using data from 1982 to 2016.
- Results showed that substance misuse during hospitalization was uncommon (14%), with prior substance use disorders being a significant factor, while other associated factors included younger age, nature of offending, and previous treatment complications.
Article Synopsis
- Patients with both cancer and severe mental illness (SMI) face a higher likelihood of late-stage cancer diagnosis and have worse survival rates compared to those with cancer alone.
- The study shows that patients with SMI are often less screened for psychological distress and less informed about available psycho-oncological support services.
- A clear disparity exists in the level of support offered, particularly indicating that psychosocial support is often overlooked unless patients are diagnosed with advanced cancer, contrary to existing literature.
Objective: In routine oncological treatment settings, psychological distress, including mental disorders, is overlooked in 30% to 50% of patients. High workload and a constant need to optimise time and costs require a quick and easy method to identify patients likely to miss out on psychological support.
Methods: Using machine learning, factors associated with no consultation with a clinical psychologist or psychiatrist were identified between 2011 and 2019 in 7,318 oncological patients in a large cancer treatment centre.
Article Synopsis
- The study investigates the prevalence of self-injury among patients with schizophrenia spectrum disorders (SSD) in forensic psychiatry, utilizing a sample of 356 inmates from a Swiss facility.
- Using machine learning to analyze 512 potential predictors, the research identified ten key variables that effectively distinguished self-injuring patients from those who did not, achieving balanced accuracy of 68%.
- Findings indicate that younger patients with SSD who self-injured displayed more severe symptoms of depression and anxiety upon admission, suggesting these symptoms could be critical targets for future prevention efforts.
Uncovering Barriers to Screening for Distress in Patients With Cancer via Machine Learning.
J Acad Consult Liaison Psychiatry
March 2022
Background: Psychologic distress and manifest mental disorders are overlooked in 30-50% of patients with cancer. Accordingly, international cancer treatment guidelines recommend routine screening for distress in order to provide psychologic support to those in need. Yet, institutional and patient-related factors continue to hinder implementation.
View Article and Find Full Text PDFBackground And Aims: Recent research has identified higher prevalence of offending behavior in patients with comorbid schizophrenia spectrum disorder (SSD) and substance use disorder (SUD) compared to patients with SSD only and to the general population. However, findings on the subgroup of patients with SUD, SSD and offending behavior in forensic psychiatric care are scarce and inconsistent. The present study used machine learning to uncover more detailed characteristics of offender patients in forensic psychiatric care with comorbid SSD and SUD.
View Article and Find Full Text PDFObjectives: The link between schizophrenia and violent offending has long been the subject of research with significant impact on mental health policy, clinical practice and public perception of the dangerousness of people with psychiatric disorders. The present study attempts to identify factors that differentiate between violent and non-violent offenders based on a unique sample of 370 forensic offender patients with schizophrenia spectrum disorder by employing machine learning algorithms and an extensive set of variables.
Methods: Using machine learning algorithms, 519 variables were explored in order to differentiate violent and non-violent offenders.
Background: There is limited research with inconsistent findings on differences between female and male offender patients with a schizophrenia spectrum disorder (SSD), who behave aggressively towards others. This study aimed to analyse inhomogeneities in the dataset and to explore, if gender can account for those.
Methods: Latent class analysis was used to analyse a mixed forensic dataset consisting of 31 female and 329 male offender patients with SSD, who were accused or convicted of a criminal offence and were admitted to forensic psychiatric inpatient treatment between 1982 and 2016 in Switzerland.