1
|
Parsaei M, Arvin A, Taebi M, Seyedmirzaei H, Cattarinussi G, Sambataro F, Pigoni A, Brambilla P, Delvecchio G. Machine Learning for prediction of violent behaviors in schizophrenia spectrum disorders: a systematic review. Front Psychiatry 2024; 15:1384828. [PMID: 38577400 PMCID: PMC10991827 DOI: 10.3389/fpsyt.2024.1384828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/10/2024] [Accepted: 03/08/2024] [Indexed: 04/06/2024] Open
Abstract
Background Schizophrenia spectrum disorders (SSD) can be associated with an increased risk of violent behavior (VB), which can harm patients, others, and properties. Prediction of VB could help reduce the SSD burden on patients and healthcare systems. Some recent studies have used machine learning (ML) algorithms to identify SSD patients at risk of VB. In this article, we aimed to review studies that used ML to predict VB in SSD patients and discuss the most successful ML methods and predictors of VB. Methods We performed a systematic search in PubMed, Web of Sciences, Embase, and PsycINFO on September 30, 2023, to identify studies on the application of ML in predicting VB in SSD patients. Results We included 18 studies with data from 11,733 patients diagnosed with SSD. Different ML models demonstrated mixed performance with an area under the receiver operating characteristic curve of 0.56-0.95 and an accuracy of 50.27-90.67% in predicting violence among SSD patients. Our comparative analysis demonstrated a superior performance for the gradient boosting model, compared to other ML models in predicting VB among SSD patients. Various sociodemographic, clinical, metabolic, and neuroimaging features were associated with VB, with age and olanzapine equivalent dose at the time of discharge being the most frequently identified factors. Conclusion ML models demonstrated varied VB prediction performance in SSD patients, with gradient boosting outperforming. Further research is warranted for clinical applications of ML methods in this field.
Collapse
Affiliation(s)
- Mohammadamin Parsaei
- Maternal, Fetal & Neonatal Research Center, Family Health Research Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Alireza Arvin
- Center for Orthopedic Trans-disciplinary Applied Research (COTAR), Tehran University of Medical Sciences, Tehran, Iran
| | - Morvarid Taebi
- Center for Orthopedic Trans-disciplinary Applied Research (COTAR), Tehran University of Medical Sciences, Tehran, Iran
| | - Homa Seyedmirzaei
- Sports Medicine Research Center, Neuroscience Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Giulia Cattarinussi
- Department of Neuroscience (DNS), Padua Neuroscience Center, University of Padova, Padua, Italy
- Padua Neuroscience Center, University of Padova, Padua, Italy
- Department of Psychological Medicine, Institute of Psychiatry, Psychology and Neuroscience, Kings College London, London, United Kingdom
| | - Fabio Sambataro
- Department of Neuroscience (DNS), Padua Neuroscience Center, University of Padova, Padua, Italy
- Padua Neuroscience Center, University of Padova, Padua, Italy
| | - Alessandro Pigoni
- Social and Affective Neuroscience Group, MoMiLab, Institutions, Markets, Technologies (IMT) School for Advanced Studies Lucca, Lucca, Italy
- Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy
| | - Paolo Brambilla
- Social and Affective Neuroscience Group, MoMiLab, Institutions, Markets, Technologies (IMT) School for Advanced Studies Lucca, Lucca, Italy
- Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy
- Department of Neurosciences and Mental Health, Fondazione Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Ca’ Granda Ospedale Maggiore Policlinico, Milan, Italy
| | - Giuseppe Delvecchio
- Department of Neurosciences and Mental Health, Fondazione Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Ca’ Granda Ospedale Maggiore Policlinico, Milan, Italy
| |
Collapse
|
2
|
Santos MESB, Roza DL, Barros REM, Santos JLF, Razzouk D, Azevedo-Marques JM, Menezes PR, Del-Ben CM. Patient needs four years after first psychiatric hospitalization in a Brazilian cohort. ACTA ACUST UNITED AC 2021; 54:e11447. [PMID: 34320123 PMCID: PMC8302140 DOI: 10.1590/1414-431x2021e11447] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2021] [Accepted: 05/26/2021] [Indexed: 11/22/2022]
Abstract
Knowledge about the needs of psychiatric patients is essential for mental health care planning. However, research on met and unmet needs is still scarce, particularly in low- and middle-income countries. This study aimed to describe the patients' needs (met and unmet) at least four years after their first psychiatric hospitalization and to verify the role of demographic and clinical features as possible predictors of these needs. Patients who had their first psychiatric admission between January 1, 2006 and December 31, 2007 at an inpatient unit in the city of Ribeirão Preto, Brazil, were eligible to participate in the study. Patients were contacted and face-to-face interviews were conducted by psychologists using the Camberwell Assessment of Need. Data were analyzed using zero-inflated negative binomial regression model. Of 933 eligible patients, 333 were interviewed. The highest level of needs was related to welfare benefits (32.4%, unmet=25.5%), followed by household skills (30.3%, unmet=3.0%), psychotic symptoms (29.4%, unmet=9.0%), psychological distress (27.6%, unmet=8.4%), physical health (24.3%, unmet=5.4%), daytime activities (19.5%, unmet=16.5%), and money (16.8%, unmet=9.0%). Fewer years of schooling, living with relatives, and unemployment at the moment of the first admission were significantly associated with a higher number of both met and unmet needs in the follow-up. Unmet needs were also more often reported by patients living alone. In conclusion, socioeconomic indicators were the best predictors of needs. The unmet needs related to welfare benefits point to the need for specific social and health policies.
Collapse
Affiliation(s)
- M E S B Santos
- Departamento de Neurociências e Ciências do Comportamento, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil
| | - D L Roza
- Departamento de Neurociências e Ciências do Comportamento, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil
| | - R E M Barros
- Departamento de Neurociências e Ciências do Comportamento, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil
| | - J L F Santos
- Departamento de Medicina Social, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil
| | - D Razzouk
- Centro de Economia da Saúde Mental, Departamento de Psiquiatria, Universidade Federal de São Paulo, São Paulo, SP, Brasil
| | - J M Azevedo-Marques
- Departamento de Medicina Social, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil
| | - P R Menezes
- Departamento de Medicina Preventiva, Faculdade de Medicina, Universidade de São Paulo, São Paulo, SP, Brasil.,Núcleo de Pesquisa em Saúde Mental Populacional, Universidade de São Paulo, São Paulo, SP, Brasil
| | - C M Del-Ben
- Departamento de Neurociências e Ciências do Comportamento, Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo, Ribeirão Preto, SP, Brasil.,Núcleo de Pesquisa em Saúde Mental Populacional, Universidade de São Paulo, São Paulo, SP, Brasil
| |
Collapse
|
3
|
Neurocognition and social cognition training as treatments for violence and aggression in people with severe mental illness. CNS Spectr 2020; 25:145-153. [PMID: 31248468 DOI: 10.1017/s1092852919001214] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
Abstract
Aggressive and violent behavior, including both verbal and physical aggression, have considerable adverse consequences for people with schizophrenia. There are several potential causes of violent behavior on the part of people with severe mental illness, which include intellectual impairments, cognitive and social-cognitive deficits, skills deficits, substance abuse, antisocial features, and specific psychotic features. This review explores the interventions that have been tested to this date. Computerized Cognitive Training (CCT) or Computerized Social-Cognitive Training (CSCT) have been associated with reductions in violence. Combined CCT and CSCT have been found to improve social cognition and neurocognition, as well as everyday functioning when combined with rehabilitation interventions. These interventions have been shown to reduce violence in schizophrenia patients across multiple environments, including forensic settings. The reductions in violence and aggression have manifested in various ways, including reduced violent thinking and behavior, reduced physical and violent assaults, and reduced disruptive and aggressive behaviors. Effects of cognitive training may be associated with improvements in problem-solving and the increased ability to deploy alternative strategies. The effect of social cognition training on violence reduction appears to be direct, with improvements in violence related to the extent of improvement in social cognition. There are still remaining issues to be addressed in the use of CCT and CSCT, and the benefits should not be overstated; however, the results of these interventions are very promising.
Collapse
|
4
|
Faay MDM, van Os J. Aggressive Behavior, Hostility, and Associated Care Needs in Patients With Psychotic Disorders: A 6-Year Follow-Up Study. Front Psychiatry 2019; 10:934. [PMID: 31998154 PMCID: PMC6961536 DOI: 10.3389/fpsyt.2019.00934] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/09/2019] [Accepted: 11/25/2019] [Indexed: 01/13/2023] Open
Abstract
Background: Hostility and aggressive behavior in patients with psychotic disorders are associated with demographic and clinical risk factors, as well as with childhood adversity and neglect. Care needs are an essential concept in clinical practice; care needs in the domain of safety for others reflect the actual problem the patient has. Hostility, aggressive behavior, and associated care needs, however, are often studied in retrospect. Method: In a sample of 1,119 patients with non-affective psychotic disorders, who were interviewed three times over a period of 6 years, we calculated the incidence of hostility, self-reported maltreatment to others and care needs associated with safety for other people (safety-to-others). Regression analysis was used to analyze the association between these outcomes and risk factors. The population attributable fraction (PAF) was used to calculate the proportion of the outcome that could potentially be prevented if previous expressions of adverse behavior were eliminated. Results: The yearly incidence of hostility was 2.8%, for safety-to-others 0.8% and for maltreatment this was 1.8%. Safety-to-others was associated with previous hostility and vice versa, but, assuming causality, only 18% of the safety-to-others needs was attributable to previous hostility while 26% was attributable to impulsivity. Hostility, maltreatment and safety-to-others were all associated with number of unmet needs, suicidal ideation and male sex. Hostility and maltreatment, but not safety-to-others, were associated with childhood adversity. Neither safety-to-others, maltreatment nor hostility were associated with premorbid adjustment problems. Conclusion: The incidence of hostility, self-reported aggressive behaviors, and associated care needs is low and linked to childhood adversity. Known risk factors for prevalence also apply to incidence and for care needs associated with safety for other people. Clinical symptoms can index aggressive behaviors years later, providing clinicians with some opportunity for preventing future incidents.
Collapse
Affiliation(s)
- Margo D M Faay
- Department of Psychiatry, University Medical Center Utrecht, Utrecht, Netherlands
| | - Jim van Os
- Department of Psychiatry, University Medical Center Utrecht, Utrecht, Netherlands.,Department of Psychosis Studies, Institute of Psychiatry, King's College London, King's Health Partners, London, United Kingdom
| | | |
Collapse
|
5
|
Ritsner MS, Farkash H, Rauchberger B, Amrami-Weizman A, Zendjidjian XY. Assessment of health needs, satisfaction with care, and quality of life in compulsorily admitted patients with severe mental disorders. Psychiatry Res 2018; 267:541-550. [PMID: 29980135 DOI: 10.1016/j.psychres.2018.05.030] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/04/2018] [Revised: 04/20/2018] [Accepted: 05/11/2018] [Indexed: 11/17/2022]
Abstract
This cross-sectional study compared the levels of needs, care satisfaction, quality of life, and social support of compulsory admitted patients with severe mental disorders to a comparable group of voluntary admitted patients. One hundred and twenty-five patients with schizophrenia and schizoaffective disorder were admitted to a hospital by district psychiatrist order (DPO), court observation order (COO), or voluntary (VA). Participants were assessed before discharge using questionnaires, and psychiatric rating scales. A linear discriminant analysis revealed eight variables that best differentiated the three groups. COO patients were significantly discriminated from the two other groups (DPO and VA) by severe negative symptoms, better satisfaction with both nursing staff and family support. COO subjects had more non-illness unmet needs, while reported better hedonic capacity for social and interpersonal pleasure - compared to VA patients. DPO patients were significantly indicated by poorer awareness to illness, but better satisfaction with subjective feelings. VA subjects were significantly discriminated from compulsory admitted patients by higher illness severity scores. Assessment of unmet needs, satisfaction with care, quality of life, hedonic capacity, and social support constitute the factors that differentiate compulsory admitted patients and could be targets for interventions aimed to reduce the negative effects of compulsory admissions.
Collapse
Affiliation(s)
- Michael S Ritsner
- Shaar Menashe Mental Health Center, Israel; National Insurance Institute in Israel, Haifa, Israel.
| | | | | | | | - Xavier Y Zendjidjian
- Aix-Marseille University, EA 3279 - Public Health, Chronic Diseases and Quality of Life - Research Unit, Marseille, France.
| |
Collapse
|
6
|
Pinna F, Tusconi M, Dessì C, Pittaluga G, Fiorillo A, Carpiniello B. Violence and mental disorders. A retrospective study of people in charge of a community mental health center. INTERNATIONAL JOURNAL OF LAW AND PSYCHIATRY 2016; 47:122-128. [PMID: 27180213 DOI: 10.1016/j.ijlp.2016.02.015] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
BACKGROUND Numerous studies conducted in inpatient settings have highlighted how mental disorders are associated with an increased risk of violence, particularly during acute phases. However, to date a more limited number of studies have been performed to assess the risk of violence in outpatients, particularly in Italy. The present study aims to evaluate the prevalence of violent events in a sample of patients in charge of a community mental health center in Italy. METHODS Based on data obtained from standardized clinical records, a retrospective study was undertaken to investigate acts of violence (physical aggression only) in a total of 678 patients (Males=308, 45.4%) in charge of a university mental health center; patients were mainly affected by anxiety disorders (30.7%), depressive disorder (17.2%), bipolar disorder (18.3%) and schizophrenia or other psychotic disorders (25.0%). RESULTS 27.6% of the sample had committed at least one act of violence during their lifetime, 10.5% over the previous year. 56.7% of those who committed violence acts had acted violently twice or more during their lifetime. A significant association of lifetime violence was found with gender (male), younger age, low education, unemployment, living with parents. With regard to diagnosis, a significant association was found with schizophrenia and other psychotic disorders, personality disorders, mental retardation, and comorbidity between two or more psychiatric disorders. Violence was moreover associated with early age at onset and at first psychiatric treatment, longer duration of the disorder, previous hospital admissions, previous violent events. CONCLUSION Violent behavior is relatively common among outpatients.
Collapse
Affiliation(s)
- Federica Pinna
- Department of Public Health, Clinical and Molecular Medicine, Unit of Psychiatry, University of Cagliari, Italy
| | - Massimo Tusconi
- Department of Public Health, Clinical and Molecular Medicine, Unit of Psychiatry, University of Cagliari, Italy
| | - Claudio Dessì
- Department of Public Health, Clinical and Molecular Medicine, Unit of Psychiatry, University of Cagliari, Italy
| | - Giuseppe Pittaluga
- Department of Public Health, Clinical and Molecular Medicine, Unit of Psychiatry, University of Cagliari, Italy
| | - Andrea Fiorillo
- Department of Psychiatry, Second University of Naples (SUN), Italy
| | - Bernardo Carpiniello
- Department of Public Health, Clinical and Molecular Medicine, Unit of Psychiatry, University of Cagliari, Italy.
| |
Collapse
|
7
|
A cross sectional study of prevalence and correlates of current and past risks in schizophrenia. Asian J Psychiatr 2015; 14:36-41. [PMID: 25703039 PMCID: PMC4450129 DOI: 10.1016/j.ajp.2015.01.005] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2014] [Revised: 12/22/2014] [Accepted: 01/27/2015] [Indexed: 11/21/2022]
Abstract
BACKGROUND The growing burden of chronic often untreated mental illness has increased the importance of risk assessment in people suffering from major mental disorders. AIMS The present study was undertaken to obtain prevalence of various risks and predictive factors for self-harm, violence and various other risks among randomly recruited schizophrenia subjects (N=270) on the basis of past history of their disorder. METHOD Using a rigorous translation, back translation and acceptability process, a specially constructed semi-structured assessment interview, based on a prior NHS Trust risk assessment interview along with the Diagnostic Interview for Genetic Studies (DIGS), detailed information was obtained for various risks. RESULTS Risk of violence (historical) was reported among 65.55%, and risk of self-neglect among 53.33%, risk to others (47.41%), risk of coming to harm (24.07%), self-harm (22.59%), risk from others (11.85%), fire risk (2.96%). Risk of violence (historical) and risk to others was related to 'ever' having emotions related to harm and self-harm, 'current' emotions related to violence and poor compliance to treatment. CONCLUSION Regular risk assessment is essential to assess emotions related to violence and non-adherence to treatment. Assessment of risk helps clinicians predict the risks involved in management and in timely intervention.
Collapse
|
8
|
Torres-González F, Ibanez-Casas I, Saldivia S, Ballester D, Grandón P, Moreno-Küstner B, Xavier M, Gómez-Beneyto M. Unmet needs in the management of schizophrenia. Neuropsychiatr Dis Treat 2014; 10:97-110. [PMID: 24476630 PMCID: PMC3897352 DOI: 10.2147/ndt.s41063] [Citation(s) in RCA: 35] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/11/2022] Open
Abstract
Studies on unmet needs during the last decades have played a significant role in the development and dissemination of evidence-based community practices for persistent schizophrenia and other severe mental disorders. This review has thoroughly considered several blocks of unmet needs, which are frequently related to schizophrenic disorders. Those related to health have been the first block to be considered, in which authors have examined the frequent complications and comorbidities found in schizophrenia, such as substance abuse and dual diagnosis. A second block has been devoted to psychosocial and economic needs, especially within the field of recovery of the persistently mentally ill. Within this block, the effects of the current economic difficulties shown in recent literature have been considered as well. Because no patient is static, a third block has reviewed evolving needs according to the clinical staging model. The fourth block has been dedicated to integrated evidence-based interventions to improve the quality of life of persons with schizophrenia. Consideration of community care for those reluctant to maintain contact with mental health services has constituted the fifth block. Finally, authors have aggregated their own reflections regarding future trends. The number of psychosocial unmet needs is extensive. Vast research efforts will be needed to find appropriate ways to meet them, particularly regarding so-called existential needs, but many needs could be met only by applying existing evidence-based interventions. Reinforcing research on the implementation strategies and capacity building of professionals working in community settings might address this problem. The final aim should be based on the collaborative model of care, which rests on the performance of a case manager responsible for monitoring patient progress, providing assertive follow-up, teaching self-help strategies, and facilitating communication among the patient, family doctor, mental health specialist, and other specialists.
Collapse
Affiliation(s)
- Francisco Torres-González
- Centro de Investigación Biomédica en Red de Salud Mental, University of Granada, Spain ; Maristán Network, University of Granada, Granada, Spain
| | - Inmaculada Ibanez-Casas
- Centro de Investigación Biomédica en Red de Salud Mental, University of Granada, Spain ; Maristán Network, University of Granada, Granada, Spain
| | - Sandra Saldivia
- Department of Psychiatry and Mental Health, Faculty of Medicine, University of Concepcion, Chile ; Maristán Network, University of Granada, Granada, Spain
| | - Dinarte Ballester
- Sistema de Saúde Mãe de Deus, Escola Superior de Saúde, Universidade do Vale do Rio dos Sinos, Brazil ; Maristán Network, University of Granada, Granada, Spain
| | - Pamela Grandón
- Department of Psychology, Faculty of Social Sciences, University of Concepcion, Chile ; Maristán Network, University of Granada, Granada, Spain
| | - Berta Moreno-Küstner
- Andalusian Psychosocial Research Group and Department of Personality, Assessment and Psychological Treatment, Faculty of Psychology, University of Malaga, Spain ; Maristán Network, University of Granada, Granada, Spain
| | - Miguel Xavier
- Department of Mental Health, NOVA Medical School, Universidade Nova de Lisboa, Lisbon, Portugal ; Maristán Network, University of Granada, Granada, Spain
| | - Manuel Gómez-Beneyto
- Centro de Investigación Biomédica en Red de Salud Mental, University of Valencia, Spain ; Maristán Network, University of Granada, Granada, Spain
| |
Collapse
|