The same but different too: Depression profiles in young adults without a history of psychiatric treatment identified using Bayesian and partial correlation networks.

Depression is a heterogenous diagnostic construct; however, dynamic interactions between specific depressive symptoms across their qualitatively different profiles remain largely unknown. The study aimed to recognize the most prevalent profiles of depressive symptoms and assess their dynamics in young adults without a history of psychiatric treatment. Depressive symptoms were recorded using the Patient Health Questionnaire-9 (PHQ-9). The data were assessed for all theoretical and empirical combinations of depressive symptoms in participants with a positive screening for depression. The profiles identified in the majority of participants were analyzed using partial correlation and Bayesian networks. Data from 3583 individuals with a positive screening for depression were analyzed. Out of 382 theoretical profiles, 150 profiles (39.3%) were present in this dataset. The majority of participants (56.8%) showed 4 profiles of depressive symptoms including the profile with all depressive symptoms present, the profile without suicidal ideation, the profile without psychomotor impairment, and the profile without both psychomotor impairment and suicidal ideation. The profiles differed largely in terms of their dynamics and symptoms that are necessary to activate the whole network. The network characteristics within specific profiles did not differ significantly across the level of difficulties attributable to depressive symptoms. Our findings indicate that depression emerging in young adults shows a limited number of symptom profiles. However, dynamics of depressive symptoms differs largely between specific profiles regardless of functional impairment indicating the need to personalize therapeutic approaches. Future studies should further disentangle the heterogeneity of depressive symptoms, e.g., by dissecting the symptoms that are combined together by single PHQ-9 items (i.e., hypersomnia and insomnia; psychomotor agitation and retardation).

[Diagnosis and admission center : Establishment and evaluation of an integrated translational infrastructure for clinical psychiatric research]. / Diagnose- und Aufnahmezentrum : Etablierung und Evaluation einer integrierten translationalen Infrastruktur für die klinisch-psychiatrische Forschung.

The routine in-depth characterization of patients with methods of clinical and scale-based examination, neuropsychology, based on biomaterials, and sensor-based information opens up transformative possibilities on the way to personalized diagnostics, treatment and prevention in psychiatry, psychotherapy, and psychosomatics. Effective integration of the additional temporal and logistical effort into everyday care as well as the acceptance by patients are critical to the success of such an approach but there is little evidence on this to date. We report here on the establishment of the Diagnosis and Admission Center (DAZ) at the Central Institute of Mental Health (ZI) in Mannheim. The DAZ is an outpatient unit upstream of other care structures for clinical and scientific phenotyping across diagnoses as a starting point for data-driven, individualized pathways to further treatment, diagnostics or research. We describe the functions, goals, and implementation of the newly created clinical scientific translational structure, provide an overview of the patient populations it has reached, and provide data on its acceptance. In this context, the close integration with downstream clinical processes enables a better coordinated and demand-oriented allocation. In addition, DAZ enables a faster start of disorder-specific diagnostics and treatment. Since its launch in April 2021 up to the end of 2022, 1021 patients underwent psychiatric evaluation at DAZ during a pilot phase. The patient sample corresponded to a representative sample from standard care and the newly established processes were regarded as helpful by patients. In summary, the DAZ uniquely combines the interests and needs of patient with the collection of scientifically relevant data.

The role of pharmacogenomics in precision psychiatry.

The field of psychiatry is facing an important paradigm shift in the provision of clinical care and mental health service organization toward personalization and integration of multimodal data science. This approach, termed precision psychiatry, aims at identifying subgroups of patients more prone to the development of a certain phenotype, such as symptoms or severe mental disorders (risk detection), and/or to guide treatment selection. Pharmacogenomics and computational psychiatry are two fundamental tools of precision psychiatry, which have seen increasing levels of integration in clinical settings. Here we present a brief overview of these two applications of precision psychiatry in clinical settings.

Genetic Predictors of Antipsychotic Efflux Impairment via Blood-Brain Barrier: Role of Transport Proteins.

Antipsychotic (AP)-induced adverse drug reactions (ADRs) are a current problem of biological and clinical psychiatry. Despite the development of new generations of APs, the problem of AP-induced ADRs has not been solved and continues to be actively studied. One of the important mechanisms for the development of AP-induced ADRs is a genetically-determined impairment of AP efflux across the blood-brain barrier (BBB). We present a narrative review of publications in databases (PubMed, Springer, Scopus, Web of Science E-Library) and online resources: The Human Protein Atlas; GeneCards: The Human Gene Database; US National Library of Medicine; SNPedia; OMIM Online Mendelian Inheritance in Man; The PharmGKB. The role of 15 transport proteins involved in the efflux of drugs and other xenobiotics across cell membranes (P-gp, TAP1, TAP2, MDR3, BSEP, MRP1, MRP2, MRP3, MRP4, MRP5, MRP6, MRP7, MRP8, MRP9, BCRP) was analyzed. The important role of three transporter proteins (P-gp, BCRP, MRP1) in the efflux of APs through the BBB was shown, as well as the association of the functional activity and expression of these transport proteins with low-functional and non-functional single nucleotide variants (SNVs)/polymorphisms of the ABCB1, ABCG2, ABCC1 genes, encoding these transport proteins, respectively, in patients with schizophrenia spectrum disorders (SSDs). The authors propose a new pharmacogenetic panel "Transporter protein (PT)-Antipsychotic (AP) Pharmacogenetic test (PGx)" (PTAP-PGx), which allows the evaluation of the cumulative contribution of the studied genetic biomarkers of the impairment of AP efflux through the BBB. The authors also propose a riskometer for PTAP-PGx and a decision-making algorithm for psychiatrists. Conclusions: Understanding the role of the transportation of impaired APs across the BBB and the use of genetic biomarkers for its disruption may make it possible to reduce the frequency and severity of AP-induced ADRs, since this risk can be partially modified by the personalized selection of APs and their dosing rates, taking into account the genetic predisposition of the patient with SSD.

The Progress and Pitfalls of Pharmacogenetics-Based Precision Medicine in Schizophrenia Spectrum Disorders: A Systematic Review and Meta-Analysis.

The inadequate efficacy and adverse effects of antipsychotics severely affect the recovery of patients with schizophrenia spectrum disorders (SSD). We report the evidence for associations between pharmacogenetic (PGx) variants and antipsychotics outcomes, including antipsychotic response, antipsychotic-induced weight/BMI gain, metabolic syndrome, antipsychotic-related prolactin levels, antipsychotic-induced tardive dyskinesia (TD), clozapine-induced agranulocytosis (CLA), and drug concentration level (pharmacokinetics) in SSD patients. Through an in-depth systematic search in 2010-2022, we identified 501 records. We included 29 meta-analyses constituting pooled data from 298 original studies over 69 PGx variants across 39 genes, 4 metabolizing phenotypes of CYP2D9, and 3 of CYP2C19. We observed weak unadjusted nominal significant (p < 0.05) additive effects of PGx variants of DRD1, DRD2, DRD3, HTR1A, HTR2A, HTR3A, and COMT (10 variants) on antipsychotic response; DRD2, HTR2C, BDNF, ADRA2A, ADRB3, GNB3, INSIG2, LEP, MC4R, and SNAP25 (14 variants) on weight gain; HTR2C (one variant) on metabolic syndrome; DRD2 (one variant) on prolactin levels; COMT and BDNF (two variants) on TD; HLA-DRB1 (one variant) on CLA; CYP2D6 (four phenotypes) and CYP2C19 (two phenotypes) on antipsychotics plasma levels. In the future, well-designed longitudinal naturalistic multi-center PGx studies are needed to validate the effectiveness of PGx variants in antipsychotic outcomes before establishing any reproducible PGx passport in clinical practice.

Multimodal predictions of treatment outcome in major depression: A comparison of data-driven predictors with importance ratings by clinicians.

BACKGROUND: Reliable prediction models of treatment outcome in Major Depressive Disorder (MDD) are currently lacking in clinical practice. Data-driven outcome definitions, combining data from multiple modalities and incorporating clinician expertise might improve predictions. METHODS: We used unsupervised machine learning to identify treatment outcome classes in 1060 MDD inpatients. Subsequently, classification models were created on clinical and biological baseline information to predict treatment outcome classes and compared to the performance of two widely used classical outcome definitions. We also related the findings to results from an online survey that assessed which information clinicians use for outcome prognosis. RESULTS: Three and four outcome classes were identified by unsupervised learning. However, data-driven outcome classes did not result in more accurate prediction models. The best prediction model was targeting treatment response in its standard definition and reached accuracies of 63.9 % in the test sample, and 59.5 % and 56.9 % in the validation samples. Top predictors included sociodemographic and clinical characteristics, while biological parameters did not improve prediction accuracies. Treatment history, personality factors, prior course of the disorder, and patient attitude towards treatment were ranked as most important indicators by clinicians. LIMITATIONS: Missing data limited the power to identify biological predictors of treatment outcome from certain modalities. CONCLUSIONS: So far, the inclusion of available biological measures in addition to psychometric and clinical information did not improve predictive value of the models, which was overall low. Optimized biomarkers, stratified predictions and the inclusion of clinical expertise may improve future prediction models.

Interpersonal attunement in social interactions: from collective psychophysiology to inter-personalized psychiatry and beyond.

In this article, we analyse social interactions, drawing on diverse points of views, ranging from dialectics, second-person neuroscience and enactivism to dynamical systems, active inference and machine learning. To this end, we define interpersonal attunement as a set of multi-scale processes of building up and materializing social expectations-put simply, anticipating and interacting with others and ourselves. While cultivating and negotiating common ground, via communication and culture-building activities, are indispensable for the survival of the individual, the relevant multi-scale mechanisms have been largely considered in isolation. Here, collective psychophysiology, we argue, can lend itself to the fine-tuned analysis of social interactions, without neglecting the individual. On the other hand, an interpersonal mismatch of expectations can lead to a breakdown of communication and social isolation known to negatively affect mental health. In this regard, we review psychopathology in terms of interpersonal misattunement, conceptualizing psychiatric disorders as disorders of social interaction, to describe how individual mental health is inextricably linked to social interaction. By doing so, we foresee avenues for an inter-personalized psychiatry, which moves from a static spectrum of disorders to a dynamic relational space, focusing on how the multi-faceted processes of social interaction can help to promote mental health. This article is part of the theme issue 'Concepts in interaction: social engagement and inner experiences'.

Transitions in depression: if, how, and when depressive symptoms return during and after discontinuing antidepressants.

PURPOSE: The aim of the current study is to provide insight into if, how, and when meaningful changes occur in individual patients who discontinue antidepressant medication. Agreement between macro-level quantitative symptom data, qualitative ratings, and micro-level Ecological Momentary Assessments is examined. METHODS: During and shortly after antidepressant discontinuation, depressive symptoms and 'feeling down' were measured in 56 participants, using the SCL-90 depression subscale weekly (macro-level) for 6 months, and 5 Ecological Momentary Assessments daily (micro-level) for 4 months (30.404 quantitative measurements in total). Qualitative information was also obtained, providing additional information to verify that changes were clinically meaningful. RESULTS: At the macro-level, an increase in depressive symptoms was found in 58.9% of participants that (a) was statistically reliable, (b) persisted for 3 weeks and/or required intervention, and (c) was clinically meaningful to patients. Of these increases, 30.3% happened suddenly, 42.4% gradually, and for 27.3% criteria were inconclusive. Quantitative and qualitative criteria showed a very high agreement (Cohen's κ = 0.85) regarding if a participant experienced a recurrence of depression, but a moderate agreement (Cohen's κ = 0.49) regarding how that change occurred. At the micro-level, 41.1% of participants experienced only sudden increases in depressed mood, 12.5% only gradual, 30.4% experienced both types of increase, and 16.1% neither. CONCLUSION: Meaningful change is common in patients discontinuing antidepressants, and there is substantial heterogeneity in how and when these changes occur. Depressive symptom change at the macro-level is not the same as depressive symptom change at the micro-level.

The ANKK1/DRD2 gene TaqIA polymorphism (rs1800497) is associated with the severity of extrapyramidal side effects of haloperidol treatment in CYP2D6 extensive metabolizers with schizophrenia spectrum disorders.

OBJECTIVES: Extrapyramidal symptoms (EPS) are one of the most prominent side effects of haloperidol. Variability of EPS severity may be associated with the genetic factors, affecting both haloperidol pharmacokinetics (e.g., CYP2D6) and pharmacodynamics (e.g., DRD2, ANKK1). We conducted a 3-week prospective study to investigate the associations of ANKK1/DRD2 TaqIA (rs1800497), DRD2 -141C Ins/Del (rs1799732) polymorphisms and CYP2D6 metabolic phenotype on the efficacy of haloperidol treatment and severity of EPS in patients with schizophrenia spectrum disorders. METHODS: In total, 57 inpatients with schizophrenia spectrum disorders (24 (42.1%)) females; age -46.7 (11.8) years (M(SD)) of European ancestry were enrolled. BARS and SAS scales were used to assess EPS. PANSS and CGI scales - to assess the efficacy of haloperidol treatment. Genotyping was performed by real-time PCR. CYP2D6 metabolic phenotype was predicted by the CYP2D6 *3, *4, *5, *6, *9, *10, *41 and xN genotypes. RESULTS: Minor C allele of TaqIA was associated with higher scores of BARS (p=0.029) and SAS (p=0.024) on day 21 and minor Del allele of -141C Ins/Del - with more prominent clinical improvement by CGI scale (p=0.007) but not by PANSS. These differences were observed only in extensive CYP2D6 metabolizers, although no associations with the metabolic type itself were found. General linear model showed that the combination of TaqIA genotype and metabolic type was significantly associated with BARS score on day 21 (p=0.013). CONCLUSIONS: Our results highlight the importance of using both pharmacokinetic and pharmacodynamic genetic markers for predicting haloperidol treatment response to personalize schizophrenia spectrum disorders treatment.

Challenges in Identifying Individualized Brain Biomarkers of Late Life Depression.

Research into neuroimaging biomarkers for Late Life Depression (LLD) has identified neural correlates of LLD including increased white matter hyperintensities and reduced hippocampal volume. However, studies into neuroimaging biomarkers for LLD largely fail to converge. This lack of replicability is potentially due to challenges linked to construct variability, etiological heterogeneity, and experimental rigor. We discuss suggestions to help address these challenges, including improved construct standardization, increased sample sizes, multimodal approaches to parse heterogeneity, and the use of individualized analytical models.

Practitioner and researcher perspectives on the utility of ecological momentary assessment in mental health care: A survey study.

Background: Ecological momentary assessment (EMA) is a scientific self-monitoring method to capture individuals' daily life experiences. Early on, EMA has been suggested to have the potential to improve mental health care. However, it remains unclear if and how EMA should be implemented. This requires an in-depth investigation of how practitioners and researchers view the implementation of EMA. Objective: Explore the perspectives of mental health practitioners and EMA researchers on the utility of EMA for mental health care. Methods: Practitioners (n = 89; psychiatrists, psychologists, psychiatric nurses) and EMA researchers (n = 62) completed a survey about EMA in clinical practice. This survey addressed EMA goals for practitioner and patient, requirements regarding clinical use of EMA, and (dis)advantages of EMA compared to treatment-as-usual. t-Tests were used to determine agreement with each statement and whether practitioners' and researchers' views differed significantly. Linear regression was used to explore predictors of goals and preferences (e.g., EMA experience). Results: Practitioners and researchers considered EMA to be a useful clinical tool for diverse stages of care. They indicated EMA to be most useful for gaining insight into the context specificity of symptoms (55.0 %), whereas receiving alerts when symptoms increase was rated the least useful (11.3 %, alerts is in 95 % of bootstrap iterations between rank 8 and 10). Compared to treatment-as-usual, EMA was considered easier to use (M = 4.87, t = 5.30, p < .001) and interpret (M = 4.52, t = 3.61, p < .001), but also more burdensome for the patient (M = 4.48, t = 3.17, p < .001). Although participants preferred personalization of the EMA diary, they also suggested that EMA should cost practitioners and patients limited time. The preference for creating personalized EMA was related to the level of experience with EMA. Finally, they highlighted the need for practitioner training and patient full-time access to the EMA feedback. Conclusions: This survey study demonstrated that practitioners and researchers expect EMA to have added value for mental health care. Concrete recommendations for implementation of EMA are formulated. This may inform the development of specific clinical applications and user-friendly EMA software.

Psychiatric diagnosis and treatment in the 21st century: paradigm shifts versus incremental integration.

Psychiatry has always been characterized by a range of different models of and approaches to mental disorder, which have sometimes brought progress in clinical practice, but have often also been accompanied by critique from within and without the field. Psychiatric nosology has been a particular focus of debate in recent decades; successive editions of the DSM and ICD have strongly influenced both psychiatric practice and research, but have also led to assertions that psychiatry is in crisis, and to advocacy for entirely new paradigms for diagnosis and assessment. When thinking about etiology, many researchers currently refer to a biopsychosocial model, but this approach has received significant critique, being considered by some observers overly eclectic and vague. Despite the development of a range of evidence-based pharmacotherapies and psychotherapies, current evidence points to both a treatment gap and a research-practice gap in mental health. In this paper, after considering current clinical practice, we discuss some proposed novel perspectives that have recently achieved particular prominence and may significantly impact psychiatric practice and research in the future: clinical neuroscience and personalized pharmacotherapy; novel statistical approaches to psychiatric nosology, assessment and research; deinstitutionalization and community mental health care; the scale-up of evidence-based psychotherapy; digital phenotyping and digital therapies; and global mental health and task-sharing approaches. We consider the extent to which proposed transitions from current practices to novel approaches reflect hype or hope. Our review indicates that each of the novel perspectives contributes important insights that allow hope for the future, but also that each provides only a partial view, and that any promise of a paradigm shift for the field is not well grounded. We conclude that there have been crucial advances in psychiatric diagnosis and treatment in recent decades; that, despite this important progress, there is considerable need for further improvements in assessment and intervention; and that such improvements will likely not be achieved by any specific paradigm shifts in psychiatric practice and research, but rather by incremental progress and iterative integration.

Human-Induced Pluripotent Stem Cell Technology: Toward the Future of Personalized Psychiatry.

The polygenic and multifactorial nature of many psychiatric disorders has hampered implementation of the personalized medicine approach in clinical practice. However, induced pluripotent stem cell (iPSC) technology has emerged as an innovative tool for patient-specific disease modeling to expand the pathophysiology knowledge and treatment perspectives in the last decade. Current technologies enable adult human somatic cell reprogramming into iPSCs to generate neural cells and direct neural cell conversion to model organisms that exhibit phenotypes close to human diseases, thereby effectively representing relevant aspects of neuropsychiatric disorders. In this regard, iPSCs reflect patient pathophysiology and pharmacological responsiveness, particularly when cultured under conditions that emulate spatial tissue organization in brain organoids. Recently, the application of iPSCs has been frequently associated with gene editing that targets the disease-causing gene to deepen the illness pathophysiology and to conduct drug screening. Moreover, gene editing has provided a unique opportunity to repair the putative causative genetic lesions in patient-derived cells. Here, we review the use of iPSC technology to model and potentially treat neuropsychiatric disorders by illustrating the key studies on a series of mental disorders, including schizophrenia, major depressive disorder, bipolar disorder, and autism spectrum disorder. Future perspectives will involve the development of organ-on-a-chip platforms that control the microenvironmental conditions so as to reflect individual pathophysiological by adjusting physiochemical parameters according to personal health data. This strategy could open new ways by which to build a disease model that considers individual variability and tailors personalized treatments.

Blood and Urinary Biomarkers of Antipsychotic-Induced Metabolic Syndrome.

Metabolic syndrome (MetS) is a clustering of at least three of the following five medical conditions: abdominal obesity, high blood pressure, high blood sugar, high serum triglycerides, and low serum high-density lipoprotein (HDL). Antipsychotic (AP)-induced MetS (AIMetS) is the most common adverse drug reaction (ADR) of psychiatric pharmacotherapy. Herein, we review the results of studies of blood (serum and plasma) and urinary biomarkers as predictors of AIMetS in patients with schizophrenia (Sch). We reviewed 1440 studies examining 38 blood and 19 urinary metabolic biomarkers, including urinary indicators involved in the development of AIMetS. Among the results, only positive associations were revealed. However, at present, it should be recognized that there is no consensus on the role of any particular urinary biomarker of AIMetS. Evaluation of urinary biomarkers of the development of MetS and AIMetS, as one of the most common concomitant pathological conditions in the treatment of patients with psychiatric disorders, may provide a key to the development of strategies for personalized prevention and treatment of the condition, which is considered a complication of AP therapy for Sch in clinical practice.

A Web-Based Application for Personalized Ecological Momentary Assessment in Psychiatric Care: User-Centered Development of the PETRA Application.

BACKGROUND: Smartphone self-monitoring of mood, symptoms, and contextual factors through ecological momentary assessment (EMA) provides insights into the daily lives of people undergoing psychiatric treatment. Therefore, EMA has the potential to improve their care. To integrate EMA into treatment, a clinical tool that helps clients and clinicians create personalized EMA diaries and interpret the gathered data is needed. OBJECTIVE: This study aimed to develop a web-based application for personalized EMA in specialized psychiatric care in close collaboration with all stakeholders (ie, clients, clinicians, researchers, and software developers). METHODS: The participants were 52 clients with mood, anxiety, and psychotic disorders and 45 clinicians (psychiatrists, psychologists, and psychiatric nurses). We engaged them in interviews, focus groups, and usability sessions to determine the requirements for an EMA web application and repeatedly obtained feedback on iteratively improved high-fidelity EMA web application prototypes. We used human-centered design principles to determine important requirements for the web application and designed high-fidelity prototypes that were continuously re-evaluated and adapted. RESULTS: The iterative development process resulted in Personalized Treatment by Real-time Assessment (PETRA), which is a scientifically grounded web application for the integration of personalized EMA in Dutch clinical care. PETRA includes a decision aid to support clients and clinicians with constructing personalized EMA diaries, an EMA diary item repository, an SMS text message-based diary delivery system, and a feedback module for visualizing the gathered EMA data. PETRA is integrated into electronic health record systems to ensure ease of use and sustainable integration in clinical care and adheres to privacy regulations. CONCLUSIONS: PETRA was built to fulfill the needs of clients and clinicians for a user-friendly and personalized EMA tool embedded in routine psychiatric care. PETRA is unique in this codevelopment process, its extensive but user-friendly personalization options, its integration into electronic health record systems, its transdiagnostic focus, and its strong scientific foundation in the design of EMA diaries and feedback. The clinical effectiveness of integrating personalized diaries via PETRA into care requires further research. As such, PETRA paves the way for a systematic investigation of the utility of personalized EMA for routine mental health care.

Investigation of Psychoactive Medications: Challenges and a Practical and Scalable New Path.

In the last two decades the validity of clinical trials in psychiatry has been subject to discussion. The most accepted clinical study method in the medical area, randomized controlled trial (RCT), faces significant problems when applied to the psychiatric world. One of the causes for this scenario is the strict participant inclusion and exclusion criteria that may not represent the real world. The inconsistency of the different endpoint parameters that are used in the field is another cause. We think that psychiatric RCTs' challenges, together with the underlying complexity of psychiatry, lead to a problematic clinical practice. Today, psychoactive drugs are routinely tested not in an official clinical trial setting. Off-label psychoactive drugs are commonly prescribed, and other substances, such as herbal remedies, are also regularly consumed. Learning from those real-life experiments can teach us useful lessons. Real-world data (RWD) includes information about heterogeneous patient populations, and it can be measured with standardized parameters. Collecting RWD can also address the need for systematically documenting and sharing case reports' outcomes. We suggest using digital tools to capture objective and continuous behavioral data from patients passively. New conclusions will be constantly drawn, possibly allowing more personalized treatment outcomes. The relevant next-generation decision support tools are already available.

A New Characterization of Mental Health Disorders Using Digital Behavioral Data: Evidence from Major Depressive Disorder.

Mental health disorders are ambiguously defined and diagnosed. The established diagnosis technique, which is based on structured interviews, questionnaires and data subjectively reported by the patients themselves, leaves the mental health field behind other medical areas. We support these statements with examples from major depressive disorder (MDD). The National Institute of Mental Health (NIMH) launched the Research Domain Criteria (RDoC) project in 2009 as a new framework to investigate psychiatric pathologies from a multidisciplinary point of view. This is a good step in the right direction. Contemporary psychiatry considers mental illnesses as diseases that manifest in the mind and arise from the brain, expressed as a behavioral condition; therefore, we claim that these syndromes should be characterized primarily using behavioral characteristics. We suggest the use of smartphones and wearable devices to passively collect quantified behavioral data from patients by utilizing digital biomarkers of mental disorder symptoms. Various digital biomarkers of MDD symptoms have already been detected, and apps for collecting this longitudinal behavioral data have already been developed. This quantified data can be used to determine a patient's diagnosis and personalized treatment, and thereby minimize the diagnosis rate of comorbidities. As there is a wide spectrum of human behavior, such a fluidic and personalized approach is essential.

Predicting offenses among individuals with psychiatric disorders - A machine learning approach.

BACKGROUND: Actuarial risk estimates are considered the gold-standard way to assess whether psychiatric patients are likely to commit prospective criminal offenses. However, these risk estimates cannot individually predict the type of criminal offense a patient will subsequently commit, and often simply assess the general likelihood of crime occurring in a group sample. In order to advance the predictive utility of risk assessments, better statistical strategies are required. AIM: To develop a machine learning model to predict the type of criminal offense committed in a large transdiagnostic sample of psychiatry patients, at an individual level. METHOD: Machine learning algorithms (Random Forest, Elastic Net, SVM), were applied to a representative and diverse sample of 1240 patients in the forensic mental health system. Clinical, historical, and sociodemographic variables were considered as potential predictors and assessed in a data-driven way. Separate models were created for each type of criminal offense, and feature selection methods were used to improve the interpretability and generalizability of our findings. RESULTS: Sexual offenses can be predicted from nonviolent and violent offenses at an individual level with a sensitivity of 82.44% and specificity of 60.00%, using only 36 variables. Furthermore, in a binary classification model, sexual and violent offenses can be predicted at an individual level with 83.26% sensitivity and 77.42% specificity using only 20 clinical variables. Likewise, non-violent and sexual offenses can be individually predicted with 74.60% sensitivity and 80.65% specificity using 30 clinical variables. CONCLUSION: The current results suggest that machine learning models can show greater accuracy than gold-standard risk assessment tools (AUCs 0.70-0.80). However, unlike existing risk tools, this approach allows for the prediction of cases at an individual level, which is more clinically useful. Despite this, it is important to note that a large subset of patients in the sample were involved in the criminal system in the past, prior to an official diagnosis. Therefore, many of the variables that predict offenses may be derived from the issues of prior offenses. Irrespective of this, the accuracy of prospective models is expected to only improve with further refinement.