Vande Voort, Jennifer L.

Background The treatment of depression in children and adolescents is a substantial public health challenge. This study examined artificial intelligence tools for the prediction of early outcomes in depressed children and adolescents treated with fluoxetine, duloxetine, or placebo. Methods The study samples included training datasets ( N = 271) from patients with major depressive disorder (MDD) treated with fluoxetine and testing datasets from patients with MDD treated with duloxetine ( N = 255) or placebo ( N = 265). Treatment trajectories were generated using probabilistic graphical models (PGMs). Unsupervised machine learning identified specific depressive symptom profiles and related thresholds of improvement during acute treatment. Results Variation in six depressive symptoms (difficulty having fun, social withdrawal, excessive fatigue, irritability, low self‐esteem, and depressed feelings) assessed with the Children’s Depression Rating Scale‐Revised at 4–6 weeks predicted treatment outcomes with fluoxetine at 10–12 weeks with an average accuracy of 73% in the training dataset. The same six symptoms predicted 10–12 week outcomes at 4–6 weeks in (a) duloxetine testing datasets with an average accuracy of 76% and (b) placebo‐treated patients with accuracies of 67%. In placebo‐treated patients, the accuracies of predicting response and remission were similar to antidepressants. Accuracies for predicting nonresponse to placebo treatment were significantly lower than antidepressants. Conclusions PGMs provided clinically meaningful predictions in samples of depressed children and adolescents treated with fluoxetine or duloxetine. Future work should augment PGMs with biological data for refined predictions to guide the selection of pharmacological and psychotherapeutic treatment in children and adolescents with depression.

Abstract Objective The aim of this study was to evaluate the efficacy and safety of the dopaminergic‐enhancing agent modafinil/armodafinil (MoArm) as adjunctive treatment for bipolar depression. Methods A comprehensive search of major electronic databases was conducted to identify randomized controlled trials (RCTs) of adjunctive MoArm that included patients with bipolar I (BP‐I) or bipolar II (BP‐II) depression. Data for response/remission and all‐cause discontinuation were analyzed. Effect size was summarized by relative risk (RR) using a random effect model. Results Of 58 studies, five RCTs (N = 795 drug, N = 792 placebo) met inclusion criteria. Four armodafinil studies included only BP‐I patients and one modafinil study included both bipolar subtypes with limited heterogeneity ( I 2 = 34%, P = .19; I 2 = 18%, P = .30). Compared to placebo, augmentation with MoArm was associated with significantly greater rates of treatment response (RR, 1.18; 95% CI, 1.01‐1.37; P = .03) and remission (RR, 1.38; 95% CI, 1.10‐1.73; P = .005). All‐cause discontinuation was not different than placebo (RR, 1.08; 95% CI, 0.89‐1.30; P = .45) with no evidence of increased risk of mood switch or suicide attempts with MoArm (RR, 0.99; 95% CI, 0.39‐2.5; P = .98; RR, 1.02; 95% CI, 0.37‐2.85; P = .97). Conclusion This narrower scope meta‐analysis of one drug for one disease suggests that adjunctive MoArm may represent a novel therapeutic intervention. Further studies delineating the subtypes of bipolar depression responsive to these novel dopaminergic‐enhancing agents are encouraged.

This study aimed to understand prescribing practices during acute psychiatric hospitalization in a large cohort of patients (N = 569) with borderline personality disorder (BPD) at a tertiary care psychiatry unit from January 1, 2013, through January 1, 2015. The mean number of hospitalizations per patient was 1.5 (range, 1–7). The odds of being prescribed antidepressants, antipsychotics, mood stabilizers, hypnotics, or anxiolytics were higher at discharge than at admission. The rate of psychotropic prescriptions was also higher at discharge than at admission (incidence rate ratio, 1.9). This pattern was true for the combined psychotropic and nonpsychotropic (“medical”) prescriptions. Further guidelines are needed regarding optimal psychosocial, medical, and psychopharmacological care of patients with BPD during acute psychiatric hospitalizations.

Objectives: The Patient Health Questionnaire-9 Modified (PHQ-9M) is a self-report tool used to assess the presence and severity of depressive symptoms in teenagers. Despite widespread use in primary care clinics and psychiatric settings, the PHQ-9M has not been validated nor are its psychometric properties adequately understood for the adolescent population. This study sought to examine the psychometrics of the PHQ-9M in treatment-seeking, depressed adolescents at a psychiatric psychopharmacology clinic who were concurrently assessed with the Children's Depression Rating Scale Revised (CDRS-R) and Quick Inventory of Depressive Symptomatology-Adolescent (17-item) Self-Report (QIDS-A17-SR). Methods: Adolescents ( N = 160) aged 13 through 18 years with a diagnosis of major depressive disorder, determined on the basis of a clinical interview and semi-structured interview using the Kiddie Schedule for Affective Disorders and Schizophrenia—Present and Lifetime Version, were assessed for severity of depressive symptoms with the PHQ-9M, CDRS-R (adolescent interview only), and QIDS-A17-SR assessments at baseline, 4, and 8 weeks. Classical test theory analysis was used to evaluate the internal consistency and dimensionality of the PHQ-9M. Convergent validity was evaluated via intraclass correlations of the PHQ-9M with the CDRS-R and QIDS-A17-SR. Sensitivity to treatment response was also evaluated. Results: The internal consistency (Cronbach's coefficient α) at baseline, 4, and 8 weeks was 0.879, 0.859, and 0.827 for the PHQ-9M; 0.739, 0.835, and 0.867 for CDRS-R; and 0.712, 0.777, and 0.804 for QIDS-A17-SR, respectively. The PHQ-9M had moderate convergent validity with the CDRS-R but good convergent validity with the QIDS-A17-SR. The PHQ-9M was less sensitive to changes in symptom severity than the CDRS-R and QIDS-A17-SR. Conclusions: The PHQ-9M appears to be a valid and reliable assessment tool for the severity of depressive symptoms in a psychiatric clinic setting. However, its utility as a treatment outcome measure may be limited compared with other available rating scales.