Search

Background: Clinical decision support systems based on machine learning (ML) models are emerging within psychiatry. To ensure their successful implementation, healthcare staff needs to trust these systems. Here, we investigated if providing staff with basic information about ML-based clinical decision support systems enhances their trust in them., Methods: We conducted a randomised survey experiment among staff in the Psychiatric Services of the Central Denmark Region. The participants were allocated to one of three arms, receiving different types of information: An intervention arm (receiving information on clinical decision-making supported by an ML model); an active control arm (receiving information on standard clinical decision process without ML support); and a blank control arm (no information). Subsequently, participants responded to various questions regarding their trust/distrust in ML-based clinical decision support systems. The effect of the intervention was assessed by pairwise comparisons between all randomization arms on sum scores of trust and distrust., Results: Among 2838 invitees, 780 completed the survey experiment. The intervention enhanced trust and diminished distrust in ML-based clinical decision support systems compared with the active control arm (Trust: mean difference = 5% [95% confidence interval (CI): 2%; 9%], p value < 0.001; Distrust: mean difference = -4% [-7%; -1%], p value = 0.042) and the blank control arm (Trust: mean difference = 5% [2%; 11%], p value = 0.003; Distrust: mean difference = -3% [-6%; -1%], p value = 0.021)., Conclusion: Providing information on ML-based clinical decision support systems in hospital psychiatry may increase healthcare staff trust in such systems., (© 2025 The Author(s). Acta Psychiatrica Scandinavica published by John Wiley & Sons Ltd.)

Objective: We set forth to build a prediction model of individuals who would develop bipolar disorder (BD) using machine learning techniques in a large birth cohort. Methods: A total of 3748 subjects were studied at birth, 11, 15, 18, and 22 years of age in a community birth cohort. We used the elastic net algorithm with 10‐fold cross‐validation to predict which individuals would develop BD at endpoint (22 years) at each follow‐up visit before diagnosis (from birth up to 18 years). Afterward, we used the best model to calculate the subgroups of subjects at higher and lower risk of developing BD and analyzed the clinical differences among them. Results: A total of 107 (2.8%) individuals within the cohort presented with BD type I, 26 (0.6%) with BD type II, and 87 (2.3%) with BD not otherwise specified. Frequency of female individuals was 58.82% (n = 150) in the BD sample and 53.02% (n = 1868) among the unaffected population. The model with variables assessed at the 18‐year follow‐up visit achieved the best performance: AUC 0.82 (CI 0.75–0.88), balanced accuracy 0.75, sensitivity 0.72, and specificity 0.77. The most important variables to detect BD at the 18‐year follow‐up visit were suicide risk, generalized anxiety disorder, parental physical abuse, and financial problems. Additionally, the high‐risk subgroup of BD showed a high frequency of drug use and depressive symptoms. Conclusions: We developed a risk calculator for BD incorporating both demographic and clinical variables from a 22‐year birth cohort. Our findings support previous studies in high‐risk samples showing the significance of suicide risk and generalized anxiety disorder prior to the onset of BD, and highlight the role of social factors and adverse life events. [ABSTRACT FROM AUTHOR]

Objective: To assess whether estimates of survey structured interview diagnoses of mood and anxiety disorders were concordant with diagnoses of these disorders obtained from health administrative data. Methods: All Ontario respondents to the 2012 Canadian Community Health Survey‐Mental Health (CCHS‐MH) were linked to health administrative databases at ICES (formerly known as the Institute for Clinical Evaluative Sciences). Survey structured interview diagnoses were compared with health administrative data diagnoses obtained using a standardized algorithm. We used modified Poisson regression analyses to assess whether socio‐demographic factors were associated with concordance between the two measures. Results: Of the 4157 Ontarians included in our sample, 20.4% had either a structured interview diagnosis (13.9%) or health administrative diagnosis (10.4%) of a mood or anxiety disorder. There was high discordance between measures, with only 19.4% agreement. Migrant status, age, employment, and income were associated with discordance between measures. Conclusions: Our findings indicate that previous estimates of the 12‐month prevalence of mood and anxiety disorders in Ontario may be underestimating the true prevalence, and that population‐based surveys and health administrative data may be capturing different groups of people. Understanding the limitations of data commonly used in epidemiologic studies is a key foundation for improving population‐based estimates of mental disorders. [ABSTRACT FROM AUTHOR]

Objective: The naturalistic course of major depressive disorder (MDD) and risk indicators for recurrence and chronicity are best studied using a population sample without clear selection bias. However, such studies are scarce. This limits clinical decision‐making concerning monitoring and maintenance treatment. Method: Data were used from the Netherlands Mental Health Survey and Incidence Study‐2, a psychiatric epidemiological cohort study among a representative adult population. Two groups at baseline were selected to study recurrence and chronicity of MDD at follow‐up. Diagnoses were assessed with the Composite International Diagnostic Interview 3.0. Results: Among remitted MDD cases (n = 746), the cumulative recurrence rate was 4.3% at 5 years, 13.4% at 10 years and 27.1% at 20 years. Time to recurrence was predicted by vulnerability characteristics (childhood abuse, negative life events, parental psychopathology), physical health, functioning, clinical characteristics of depression (previous episodes, severity, medication use), psychiatric comorbidity and mental health use. Among current MDD cases (n = 242), 12% developed a chronic depressive episode over 6 years. Chronic course was predicted by similar risk indicators as recurrence, except for vulnerability characteristics and physical health. Conclusion: These risk indicators may help to identify patients requiring monitoring and who could benefit from preventive interventions or maintenance treatment. [ABSTRACT FROM AUTHOR]

Objective Hardly any studies exist on the duration of major depressive disorder ( MDD) and factors that explain variations in episode duration that lack biases. This limits clinical decision-making and leaves patients wondering when they will recover. Method Data were used from the Netherlands Mental Health Survey and Incidence Study-2, a psychiatric epidemiological cohort study among a nationally representative adult population. Respondents with a newly originated depressive episode were selected: 286 MDD and 107 minor depressive disorder (Min DD) cases. DSM- IV diagnoses were assessed with the Composite International Diagnostic Interview 3.0 and episode duration with the Life Chart Interview. Results Among MDD cases, median episode duration was 6 months, mean duration was 10.7 months, and 12% had not recovered at 36 months. Longer duration was associated with comorbid dysthymia, anxiety disorder, psychotropic medication use (i.e. antidepressants or benzodiazepines prescribed by a mental health professional), mental health care use and suicidal behaviour. Better physical and mental functioning before depression onset predicted shorter duration. Among Min DD cases, shorter median duration (3 months) but similar mean duration (8.7 months), risk of chronicity (10% not recovered at 36 months) and risk indicators for episode duration were found. Conclusion As the risk of chronicity was similar for MDD and Min DD, Min DD cannot be dismissed as a merely brief mood state. [ABSTRACT FROM AUTHOR]

Objective Insight on how different missions have impacted rates of mental health service ( MHS) utilization is unexplored. We compared postdeployment MHS utilization in a national cohort of first-time deployed to missions in Balkan, Iraq, and Afghanistan respectively. Methods A prospective national cohort study of 13 246 first-time deployed in the period 1996 through 2012 to missions in Balkan area, Iraq, or Afghanistan respectively. Soldiers ' MHS utilization was also compared with a 5:1 sex-, age-, and calendar year-matched never-deployed background population. Postdeployment utilization of MHS was retrieved from national coverage registers. Using Cox survival analyses, participants were followed and compared with regard to receiving three different types of psychiatric services: (i) admission to psychiatric hospital, (ii) psychiatric outpatient contact, and (iii) prescriptions of psychotropics. Results Utilizing of psychiatric outpatient services and psychotropics was significantly higher in first-time deployed to Iraq and Afghanistan compared with deployed to Balkan. However, the rate of postdeployment admission to psychiatric hospital did not differ between missions. Postdeployment rates of psychiatric admission and psychiatric outpatient treatment were significantly higher in Afghanistan-deployed personnel compared with the background population. Conclusions Utilization of MHS differed significantly between mission areas and was highest after the latest mission to Afghanistan. [ABSTRACT FROM AUTHOR]

Batelaan NM, Smit F, de Graaf R, van Balkom AJLM, Vollebergh WAM, Beekman ATF. Identifying target groups for the prevention of anxiety disorders in the general population. Objective: To avert the public health consequences of anxiety disorders, prevention of their onset and recurrence is necessary. Recent studies have shown that prevention is effective. To maximize the health gain and minimize the effort, preventive strategies should focus on high-risk groups. Method: Using data from a large prospective national survey, high-risk groups were selected for i) the prevention of first ever ( n = 4437) and ii) either first-ever or recurrent incident anxiety disorders ( n = 4886). Indices used were: exposure rate, odds ratio, population attributable fraction and number needed to be treated. Risk indicators included sociodemographic, psychological and illness-related factors. Results: Recognition of a few patient characteristics enables efficient identification of high-risk groups: (subthreshold) panic attacks; an affective disorder; a history of depressed mood; a prior anxiety disorder; chronic somatic illnesses and low mastery. Conclusion: Preventive efforts should be undertaken in the selected high-risk groups. [ABSTRACT FROM AUTHOR]