Youth Depression Screening with Parent and Self-Reports: Assessing Current and Prospective Depression Risk

Investigating the neurodevelopmental correlates of early adolescent-onset emotional problems

BACKGROUND

Emotional problems (EPs) increase sharply after mid-adolescence. Earlier EPs are associated with poorer long-term outcomes, and their underlying mechanisms may differ to later-onset EPs. Given an established relationship between ADHD, autism, and later depression, we aimed to examine associations between neurodevelopmental conditions and correlates and early adolescent-onset EPs.

METHODS

Adolescents in two UK population cohorts, Avon Longitudinal Study of Parents and Children (ALSPAC) and Millennium Cohort Study (MCS), were included. Individuals scoring >6 on the Strengths and Difficulties Questionnaire (SDQ) emotional problems subscale between ages 11-14 were defined as having early adolescent-onset EP, whilst those scoring >6 for the first time at 16-25 were defined as having later-onset EP. We tested associations between early adolescent-onset EP (total cases = 887, controls = 19,582) and ICD-10/DSM-5 neurodevelopmental conditions and known correlates, including: sex, birth complications, low cognitive ability, special educational needs (SEND), and epilepsy. Analyses were conducted separately in ALSPAC and MCS then meta-analysed.

RESULTS

In the meta-analysis of both cohorts, early adolescent-onset EPs were associated with female sex and greater likelihood of low cognitive ability, SEND, autism, ADHD, and reading difficulties. Compared to later-onset EP, early adolescent-onset EPs were associated with male sex, low cognitive ability, SEND, epilepsy, ASD, ADHD, and reading difficulties.

LIMITATIONS

A clinical definition of depression/anxiety was available only in ALSPAC, instead we primarily defined EP via questionnaires, which capture a broader phenotype.

CONCLUSIONS

Individuals with early adolescent-onset EP are likely to have a co-occurring neurodevelopmental condition. Clinicians should consider assessing for neurodevelopmental conditions in young adolescents with EPs.

What CBT Modules Work Best for Whom? Identifying Subgroups of Depressed Youths by Their Differential Response to Specific Modules

Prior research suggests that the effects of specific cognitive-behavioral therapy (CBT) modules on symptom outcomes can be estimated. We conducted a study utilizing idiographic and nomothetic methods to clarify which CBT modules are most effective for youth depression, and for whom they are most effective. Thirty-five youths received modular CBT for depression. Interrupted time series models estimated whether the introduction of each module was associated with changes in internalizing symptoms, whereby significant symptom reduction would suggest a therapeutic response to the module. Regression models were used to explore whether participant characteristics predicted subgroups of youths based on their estimated response to certain types (e.g., cognitive) of modules, and whether group membership was associated with posttreatment outcomes. Thirty youths (86%) had at least one module associated with a significant change in internalizing symptoms from premodule delivery to postmodule delivery. The specific modules associated with these changes varied across youths. Behavioral activation was most frequently associated with symptom decreases (34% of youths). No participant characteristics predicted estimated response to module type, and group membership was not significantly associated with posttreatment outcomes. Youths display highly heterogeneous responses to treatment modules, indicating multiple pathways to symptom improvement for depressed youths.

Deep transcranial magnetic stimulation for adolescents with treatment-resistant depression: A preliminary dose-finding study exploring safety and clinical effectiveness

BACKGROUND

Transcranial magnetic stimulation (TMS) is an intervention for treatment-resistant depression (TRD) that modulates neural activity. Deep TMS (dTMS) can target not only cortical but also deeper limbic structures implicated in depression. Although TMS has demonstrated safety in adolescents, dTMS has yet to be applied to adolescent TRD.

OBJECTIVE/HYPOTHESIS

This pilot study evaluated the safety, tolerability, and clinical effects of dTMS in adolescents with TRD. We hypothesized dTMS would be safe, tolerable, and efficacious for adolescent TRD.

METHODS

15 adolescents with TRD (Age, years: M = 16.4, SD = 1.42) completed a six-week daily dTMS protocol targeting the left dorsolateral prefrontal cortex (BrainsWay H1 coil, 30 sessions, 10 Hz, 3.6 s train duration, 20s inter-train interval, 55 trains; 1980 total pulses per session, 80 % to 120 % of motor threshold). Participants completed clinical, safety, and neurocognitive assessments before and after treatment. The primary outcome was depression symptom severity measured by the Children's Depression Rating Scale-Revised (CDRS-R).

RESULTS

14 out of 15 participants completed the dTMS treatments. One participant experienced a convulsive syncope; the other participants only experienced mild side effects (e.g., headaches). There were no serious adverse events and minimal to no change in cognitive performance. Depression symptom severity significantly improved pre- to post-treatment and decreased to a clinically significant degree after 10 treatment sessions. Six participants met criteria for treatment response.

LIMITATIONS

Main limitations include a small sample size and open-label design.

CONCLUSIONS

These findings provide preliminary evidence that dTMS may be tolerable and associated with clinical improvement in adolescent TRD.

Mental health among children with and without reading difficulties

This study explored the relationship between mental health, i.e., depression and anxiety, and reading difficulties (RD) in Chinese elementary school children. Participants were 1535 grades 3, 4, and 5 students from three elementary schools in Xi'an, China. Children with and without RD were compared to their depression and anxiety. Additionally, children's self-ratings, parents' ratings, and teachers' ratings of depression and anxiety were compared to better understand mental health issues of Chinese children with RD. The findings showed that Chinese children with RD experienced more depression but not anxiety compared to their typically developing peers across all three grade levels. Reports from all three informants consistently reflected that children with RD experienced more depression. However, some inconsistencies were found between self-reported levels of depression and anxiety and the observations made by parents and teachers. Children reported experiencing more depression than their parents and teachers observed but less anxiety than their parents reported. This study emphasizes the importance of understanding the links between RD and mental health and the need for appropriate intervention programs to help children with RD cope with the mental health challenges.

The p factor outweighs the specific internalizing factor in predicting recurrences of adolescent depression

BACKGROUND

The early prediction of adolescent depression recurrence poses a significant challenge in the field. This study aims to investigate and compare the abilities of the general psychopathology factor (p) and the specific internalizing factor, in predicting depression recurrence over a 2-year course, as well as identifying remitted depressed adolescents from healthy adolescents. Longitudinal changes of these two factors in different trajectory groups were also tracked to examine their sensitivity to sustained remission and relapse.

METHODS

We included 255 baseline-remitted depressed adolescents and a healthy control group (n = 255) matched in age, sex, and race, sourced from the Adolescent Brain Cognitive Development Study. The linear mixed model was employed for the statistical analysis.

RESULTS

The p factor not only effectively discriminated between remitted depressed adolescents and healthy controls but also robustly predicted the depression recurrence over a subsequent 2-year course. The specific internalizing factor could only differentiate remitted depressed adolescents from healthy controls. Additionally, a noteworthy longitudinal decline of the p factor in the sustained-remission group was observed.

CONCLUSIONS

Psychopathology factors serve as the inherent and enduring measurement of long-term mental health aberrations. Longitudinal results indicate that the p factor is more sensitive to respond to sustained remission than the internalizing factor. The ability of the overall p factor to anticipate depression relapse, unlike the specific internalizing factor, suggests the clinical interventions should monitor and mitigate the coincident symptoms across all dimensions to preempt relapse of adolescent depression, rather than an exclusive focus on internalizing symptoms.

Identify adolescents' help-seeking intention on suicide through self- and caregiver's assessments of psychobehavioral problems: deep clustering of the Tokyo TEEN Cohort study

Background

Psychopathological and behavioral problems in adolescence are highly comorbid, making their developmental trajectories complex and unclear partly due to technical limitations. We aimed to classify these trajectories using deep learning and identify predictors of cluster membership.

Methods

We conducted a population-based cohort study on 3171 adolescents from three Tokyo municipalities, with 2344 pairs of adolescents and caregivers participating at all four timepoints (ages 10, 12, 14, and 16) from 2012 to 2021. Adolescent psychopathological and behavioral problems were assessed by using self-report questionnaires. Both adolescents and caregivers assessed depression/anxiety and psychotic-like experiences. Caregivers assessed obsession/compulsion, dissociation, sociality problem, hyperactivity/inattention, conduct problem, somatic symptom, and withdrawal. Adolescents assessed desire for slimness, self-harm, and suicidal ideation. These trajectories were clustered with variational deep embedding with recurrence, and predictors were explored using multinomial logistic regression.

Findings

Five clusters were identified: unaffected (60.5%), minimal problems; internalizing (16.2%), persistent or worsening internalizing problems; discrepant (9.9%), subjective problems overlooked by caregivers; externalizing (9.6%), persistent externalizing problems; and severe (3.9%), chronic severe problems across symptoms. Stronger autistic traits and experience of bullying victimization commonly predicted the four "affected" clusters. The discrepant cluster, showing the highest risks for self-harm and suicidal ideation, was predicted by avoiding help-seeking for depression. The severe cluster predictors included maternal smoking during pregnancy, not bullying others, caregiver's psychological distress, and adolescent's dissatisfaction with family.

Interpretation

Approximately 40% of adolescents were classified as "affected" clusters. Proactive societal attention is warranted toward adolescents in the discrepant cluster whose suicidality is overlooked and who have difficulty seeking help.

Funding

Japan Ministry of Health, Labor and Welfare, Japan Agency for Medical Research and Development, and Japan Science and Technology Agency.

Assessment of Depression in Adults and Youth

This article selectively reviews the key issues and measures for the assessment of depressive disorders and symptoms in youth and adults. The first portion of the article addresses the nature and conceptualization of depression and some key issues that must be considered in its assessment. Next, the diagnostic interview and clinician- and self-administered rating scales that are most widely used to diagnose, screen for, and assess the severity of depression in adults and youth are selectively reviewed. In addition, the assessment of three transdiagnostic clinical features (anhedonia, irritability, and suicidality) that are frequently associated with both depression and other forms of psychopathology is discussed. The article concludes with some broad recommendations for assessing depression in research and clinical practice and suggestions for future research.

Examining the relationship between genetic risk for depression and youth episodic stress exposure

BACKGROUND

Offspring of depressed mothers have elevated risk of developing depression because they are exposed to greater stress. While generally assumed that youth's increased exposure to stress is due to the environmental effects of living with a depressed parent, youth's genes may influence stress exposure through gene-environment correlations (rGEs). To understand the relationship between risk for depression and stress, we examined the effects of polygenic risk for depression on youth stress exposure.

METHODS

We examined the relations of a polygenic risk score (PRS) for depression (DEP-PRS), as well as PRSs for 5 other disorders, with youth stress exposure. Data were from a longitudinal study of a community sample of youth and their parents (n = 377) focusing on data collected at youth's aged 12 and 15 assessments.

RESULTS

Elevated youth DEP-PRS was robustly associated with increased dependent stress, particularly interpersonal events. Exploratory analyses indicated that findings were driven by major stress and were not moderated by maternal nor paternal history of depression, and of the 5 additional PRSs tested, only elevated genetic liability for bipolar I was associated with increased dependent stress-particularly non-interpersonal events.

LIMITATIONS

Like other PRS studies, we focused on those of European ancestry thus, generalizability of findings is limited.

CONCLUSION

Polygenic risk contributes to youth experiencing stressful life events which are dependent on their behavior. This rGE appears to be specific to genetic risk for mood disorders.

The Influence of Emotional Regulation and Cognitive Flexibility on Sleep Habits in Spanish Children and Adolescents through the Lens of Parents

BACKGROUND

Previous research studies have suggested the importance of studying the relationship between emotional regulation and sleep habits. Some investigations have especially focused on how emotional regulation could impact sleep habits in children and adolescents. Therefore, these researchers have stated there exists a two-way direction in this relationship.

OBJECTIVE

This study aimed to analyze the influence of emotional regulation on sleep habits in Spanish children and adolescents and the mediating role of anxiety in this relationship.

METHOD

Participants were 953 Spanish parents who completed the assessment protocol according to their children and adolescents' information.

RESULTS

The results revealed moderate-strong correlations between emotional regulation problems and sleep habit disturbances (r = 0.375, p < 0.001), trait (r = 0.488, p < 0.001) anxiety, and state (r = 0.589, p < 0.001) anxiety. Additionally, emotional regulation showed a direct impact on sleep habits (β = 0.011, p = 0.005). Trait and state anxiety demonstrated a significant mediating role in the relationship between emotional regulation and sleep habits.

CONCLUSIONS

Emotional regulation may have an impact on sleep habits during childhood and adolescence, suggesting the importance of early intervention focused on the emotions management and the prevention of sleep habit disturbances.

Depression in middle childhood: secure base script as a cognitive diathesis in the relationship between daily stress and depressive symptoms

A better understanding of protective factors against childhood depression may allow for the mitigation of severe and chronic symptoms and the timely implementation of intervention strategies. This study investigated the protective effect of having a secure base script on depressive symptoms when children face daily stressors. To test this hypothesis, moderation analyses were performed in a cross-sectional study with 378 children (48.5% boys, 51.5%) aged 8-12 years (M = 10.20; SD = 0.57). The results provided some support for the moderation effect when secure base script knowledge was investigated as a categorical variable in middle childhood. However, the results did not support the moderation effect when investigating secure base script as a continuous variable. Therefore, future investigations may need to address whether a categorical approach could better elucidate the protective role of secure base script knowledge in childhood depression.

Psychiatric Diagnoses and Treatment in Nine- to Ten-Year-Old Participants in the ABCD Study

Objective

Psychiatric disorders commonly emerge prior to adulthood. Identification and intervention may vary significantly across populations. We leveraged a large population-based study to estimate the prevalence of psychiatric disorders and treatments, and evaluate predictors of treatment, in children ages 9-10 in the United States.

Method

We analyzed cross-sectional data from the Adolescent Brain Cognitive Developmental (ABCD) Study. The Computerized Kiddie Schedule for Affective Disorders and Schizophrenia (KSADS-COMP) was used to estimate clinical diagnoses, and the Child Behavior Checklist (CBCL) was used to assess internalizing and externalizing psychopathology. Parents reported on prescription medications and other mental health interventions. Prevalence rates of KSADS diagnoses and treatments were calculated. Logistic regression analyses estimated associations between clinical and sociodemographic predictors (sex at birth, race, ethnicity, income, education, urbanicity) and treatments.

Results

The most common KSADS diagnoses were anxiety disorders, followed by attention deficit/hyperactivity disorder (ADHD) and oppositional defiant disorder. ADHD and depression diagnoses predicted stimulant and antidepressant medication use, respectively. Bipolar and ADHD diagnoses also predicted antidepressant medications, outpatient treatment and psychotherapy. The odds of reporting specific treatments varied by sex, ethnic and racial identities, urbanicity, and income.

Conclusion

Expected rates of KSADS-based psychiatric symptoms are present in the ABCD sample at ages 9-10, with treatment patterns broadly mapping onto psychopathology in expected ways. However, we observed important variations in reported treatment utilization across sociodemographic groups, likely reflecting societal and cultural influences. Findings are considered in the context of potential mental health disparities in U.S. children.

Suicidal ideation and its relationship with mental health reported by different informants among children aged 6-12

BACKGROUND

Suicidal ideation in children has received less attention than in adolescents. This study aimed to explore the self-reported prevalence of suicidal ideation among children aged 6-12 and to identify the relationship between self-reported suicidal ideation and children's mental health reported by different informants in Chinese setting.

METHOD

The study sample was 1479 children aged 6-12 from three elementary schools in Tianjin. Children completed the Dominic Interactive to report their mental health and suicidal ideation. Parents and teachers completed the Socio-Demographic Questionnaire and the Strengths and Difficulties Questionnaire (SDQ).

RESULTS

The prevalence of suicidal thoughts and death thoughts was 18.05 % and 16.90 %, respectively. Parent reported emotional symptoms, ADHD and externalized problems were associated with death thoughts, and ADHD was associated with suicidal thoughts. For teacher's reports, emotional symptoms, and impact were associated with death thoughts, and ADHD, peer problems, internalized problems, and internalized and externalized comorbidity were associated with suicidal thoughts. All of the children's self-reported mental health problems were associated with suicidal thoughts and death thoughts.

LIMITATIONS

Causality cannot be inferred in a cross-sectional study.

CONCLUSION

Suicidal ideation is not uncommon in Chinese children. The relationships between mental health problems and suicidal ideation varied in different informants. Suicide prevention in young children should be enhanced, and screening for suicidal ideation is recommended at the onset of different informants who reported specific mental health problems.

Identifying and responding to depression in adolescents in primary care: A quality improvement response

The American Academy of Pediatrics (AAP) recommends adolescent depression screening and subsequent follow-up for those scoring at-risk. The current study assessed the outcomes of a Quality Improvement (QI) project that implemented these guidelines during annual well-child visits in a network of pediatric practices. This project used a two-stage screening process. First, adolescents were screened with the Pediatric Symptom Checklist (PSC-17). Second, adolescents who screened at-risk on the PSC-17 were asked to complete the Patient Health Questionnaire (PHQ-9). QI-participating providers received training on how to categorize the severity of their patient's depression based on PHQ-9 cut-off scores and clinical interview, and to implement and document appropriate options for follow-up. Patients in the QI group were significantly more likely to be screened with both the PSC-17 (93.8% vs. 89.1%, p < .001) and the PHQ-9 (54.8% vs. 16.4%, p < .001) compared to those in the non-QI group. Of the 80 adolescents in the QI group at-risk on the PSC-17 and with a completed PHQ-9, 65 (81.3%) received at least one type of referral for mental health, ranging from behavioral health services to lifestyle interventions. Findings support the feasibility of adolescent depression screening and referrals within pediatric primary care.

Brain signatures in children who contemplate suicide: learning from the large-scale ABCD study

BACKGROUND

Suicide is the second-leading cause of death in youth. Understanding the neural correlates of suicide ideation (SI) in children is crucial to ongoing efforts to understand and prevent youth suicide. This study characterized key neural networks during rest and emotion task conditions in an epidemiologically informed sample of children who report current, past, or no SI.

METHODS

Data are from the adolescent brain cognitive development study, including 8248 children (ages 9-10; mean age = 119.2 months; 49.2% female) recruited from the community. Resting-state functional connectivity (RSFC) and activation to emotional stimuli in the salience (SN) and default mode (DMN) networks were measured through fMRI. Self-reported SI and clinical profiles were gathered. We examined the replicability of our model results through repeated sub-sample reliability analyses.

RESULTS

Children with current SI (2.0%), compared to those without any past SI, showed lower DMN RSFC (B = -0.267, p < 0.001) and lower DMN activation in response to negative as compared to neutral faces (B = -0.204, p = 0.010). These results were robust to the effects of MDD, ADHD, and medication use. Sub-sample analysis further supported the robustness of these results. We did not find support for differences in SN RSFC or in SN activation to positive or negative stimuli for children with or without SI.

CONCLUSIONS

Results from a large brain imaging study using robust statistical approaches suggest aberrant DMN functioning in children with current suicide ideation. Findings suggest potential mechanisms that may be targeted in suicide prevention efforts.

Analyzing User-Generated Web-Based Posts of Adolescents' Emotional, Behavioral, and Symptom Responses to Beliefs About Depression: Qualitative Thematic Analysis

BACKGROUND

Depression is common during adolescence. Early intervention can prevent it from developing into more progressive mental disorders. Combining information technology and clinical psychoeducation is a promising way to intervene at an earlier stage. However, data-driven research on the cognitive response to health information targeting adolescents with symptoms of depression is lacking.

OBJECTIVE

This study aimed to fill this knowledge gap through a new understanding of adolescents' cognitive response to health information about depression. This knowledge can help to develop population-specific information technology, such as chatbots, in addition to clinical therapeutic tools for use in general practice.

METHODS

The data set consists of 1870 depression-related questions posted by adolescents on a public web-based information service. Most of the posts contain descriptions of events that lead to depression. On a sample of 100 posts, we conducted a qualitative thematic analysis based on cognitive behavioral theory investigating behavioral, emotional, and symptom responses to beliefs associated with depression.

RESULTS

Results were organized into four themes. (1) Hopelessness, appearing as a set of negative beliefs about the future, possibly results from erroneous beliefs about the causal link between risk factors and the course of depression. We found beliefs about establishing a sturdy therapy alliance as a responsibility resting on the patient. (2) Therapy hesitancy seemed to be associated with negative beliefs about therapy prognosis and doubts about confidentiality. (3) Social shame appeared as a consequence of impaired daily function when the cause is not acknowledged. (4) Failing to attain social interaction appeared to be associated with a negative symptom response. In contrast, actively obtaining social support reduces symptoms and suicidal thoughts.

CONCLUSIONS

These results could be used to meet the clinical aims stated by earlier psychoeducation development, such as instilling hope through direct reattribution of beliefs about the future; challenging causal attributions, thereby lowering therapy hesitancy; reducing shame through the mechanisms of externalization by providing a tentative diagnosis despite the risk of stigmatizing; and providing initial symptom relief by giving advice on how to open up and reveal themselves to friends and family and balance the message of self-management to fit coping capabilities. An active counseling style advises the patient to approach the social environment, demonstrating an attitude toward self-action.

Is ACEs Screening for Adolescent Mental Health Accurate and Fair?

Increasingly, adversity-focused assessment tools are being introduced into preventive mental health screening protocols. However, few studies have explicitly examined whether use of these instruments serves as equitable, clinically useful measures of mental health risk in adolescents. In response, the present study examined whether an adverse childhood experiences (ACEs) measure was accurate and fair as an index of environmental risk for adolescent mental health diagnoses. Secondary data analyses were conducted on the National Comorbidity Survey-Adolescent Supplement. Adolescents (N = 10,148; Age_Mean = 15.20; 51.3% male; 65.6% White, 15.1% Black, and 14.4% Hispanic) answered ten questions concerning childhood adversities and completed diagnostic interviews for PTSD, depression, and externalizing disorders. In the overall sample, ACEs showed some clinical utility (e.g., area under the curve (AUCs) ≥ 0.64), diagnostic likelihood ratios (DLRs) > 4.0) and acceptable calibration (i.e., expected/observed indices' confidence intervals included 1) across diagnoses. Within subpopulations, however, predictive validity varied. The AUCs were lower for multiple diagnoses in Black male and Hispanic female adolescents and DLRs suggested greater clinical utility for indexing mental health in White, female adolescents. Finally, models were not well-calibrated between adolescent subpopulations, suggesting recommended ACEs screening can potentially produce biased results when used to inform mental health policy and prevention. Reasons for why results from ACEs screening may vary across adolescent subpopulations and the importance of testing statistical fairness for preventive mental health screening are discussed.

Large-Scale Textual Datasets and Deep Learning for the Prediction of Depressed Symptoms

Millions of people worldwide suffer from depression. Assessing, treating, and preventing recurrence requires early detection of depressive symptoms as depression-related datasets expand and machine learning improves, intelligent approaches to detect depression in written material may emerge. This study provides an effective method for identifying texts describing self-perceived depressive symptoms by using long short-term memory (LSTM) based recurrent neural networks (RNN). On a huge dataset of a suicide and depression detection dataset taken from Kaggle with 233337 datasets, this information channel featured text-based teen questions. Then, using a one-hot technique, medical and psychiatric practitioners extract strong features from probably depressed symptoms. The characteristics outperform the usual techniques, which rely on word frequencies rather than symptoms to explain the underlying events in text messages. Depression symptoms can be distinguished from nondepression signals by using a deep learning system (nondepression posts). Eventually, depression is predicted by the RNN. In the suggested technique, the frequency of depressive symptoms outweighs their specificity. With correct annotations and symptom-based feature extraction, the method may be applied to different depression datasets. Because of this, chatbots and depression prediction can work together.

Reliability and Validity of the Korean Version of Children's Depression Inventory 2 Short Version as a Screening Tool: A Comparison With the Standard 28-Item Version

OBJECTIVE

To investigate the reliability and validity of the Korean version of Children's Depression Inventory 2 Short Version (CDI 2:S) in comparison with its full-length version (CDI 2) as a screening tool for depressive youth.

METHODS

A total of 714 children from the community and 62 psychiatric patients were enrolled in this study. The Korean version of the Kiddie Schedule for Affective Disorders and Schizophrenia Present and Lifetime Version (K-SADS-PL-K) served as the reference standard for computing receiver operating characteristic (ROC) curves. To evaluate the ability of the CDI 2 and CDI 2:S to discriminate major depressive disorders, areas under the curves (AUCs) were compared. To investigate psychometric properties of the CDI 2:S, internal consistency was calculated and confirmatory factor analysis was conducted.

RESULTS

For the CDI 2, the cutoff at 20 yielded the best balance between sensitivity (83%) and specificity (91%). For the CDI 2:S, the cutoff point of 10 resulted in high sensitivity (82%) and high specificity (93%). The short form was proven to be as sensitive and specific as the CDI 2. Further analyses confirmed that the CDI 2:S also had good reliability and validity.

CONCLUSION

The CDI 2:S, a sensitive and brief form of the CDI 2, may serve as a better option in time-constrained psychiatric settings.

Deep learning for prediction of depressive symptoms in a large textual dataset

Depression is a common illness worldwide with potentially severe implications. Early identification of depressive symptoms is a crucial first step towards assessment, intervention, and relapse prevention. With an increase in data sets with relevance for depression, and the advancement of machine learning, there is a potential to develop intelligent systems to detect symptoms of depression in written material. This work proposes an efficient approach using Long Short-Term Memory (LSTM)-based Recurrent Neural Network (RNN) to identify texts describing self-perceived symptoms of depression. The approach is applied on a large dataset from a public online information channel for young people in Norway. The dataset consists of youth’s own text-based questions on this information channel. Features are then provided from a one-hot process on robust features extracted from the reflection of possible symptoms of depression pre-defined by medical and psychological experts. The features are better than conventional approaches, which are mostly based on the word frequencies (i.e., some topmost frequent words are chosen as features from the whole text dataset and applied to model the underlying events in any text message) rather than symptoms. Then, a deep learning approach is applied (i.e., RNN) to train the time-sequential features discriminating texts describing depression symptoms from posts with no such descriptions (non-depression posts). Finally, the trained RNN is used to automatically predict depression posts. The system is compared against conventional approaches where it achieved superior performance than others. The linear discriminant space clearly reveals the robustness of the features by generating better clustering than other traditional features. Besides, since the features are based on the possible symptoms of depression, the system may generate meaningful explanations of the decision from machine learning models using an explainable Artificial Intelligence (XAI) algorithm called Local Interpretable Model-Agnostic Explanations (LIME). The proposed depression symptom feature-based approach shows superior performance compared to the traditional general word frequency-based approaches where frequency of the features gets more importance than the specific symptoms of depression. Although the proposed approach is applied on a Norwegian dataset, a similar robust approach can be applied on other depression datasets developed in other languages with proper annotations and symptom-based feature extraction. Thus, the depression prediction approach can be adopted to contribute to develop better mental health care technologies such as intelligent chatbots.

Psychometric properties of the Dutch-Flemish PROMIS® pediatric item banks Anxiety and Depressive Symptoms in a general population

PURPOSE

This study aims to validate the Dutch-Flemish PROMIS pediatric item banks v2.0 Anxiety and Depressive Symptoms, the short forms 8a, and computerized adaptive tests (CATs) in a general Dutch population and to provide reference data.

METHODS

Participants (N = 2,893, aged 8-18), recruited by two internet survey providers, completed both item banks. These item banks were assessed on unidimensionality, local independence, monotonicity, Graded Response Model (GRM) item fit, and differential item functioning (DIF) for gender, age group, region, ethnicity, and language. The short forms and CATs were assessed on reliability and construct validity compared to the Revised Child Anxiety and Depression Scale short version (RCADS-22) subscales. Reference scores were calculated.

RESULTS

Both item banks showed sufficient unidimensionality, local independence, monotonicity, and GRM item fit, except for three Depressive Symptoms items that showed insufficient GRM item fit. No DIF was found when using ordinal regression analyses, except for two Depressive Symptoms items that showed DIF for language; all items showed DIF for language when using IRT PRO, except for one Anxiety item. Both short forms and CATs revealed sufficient reliability for moderate and severe levels of anxiety and depression, as well as high positive correlations with corresponding RCADS-22 subscales and slightly lower correlations with non-corresponding RCADS-22 subscales.

CONCLUSION

The Dutch-Flemish PROMIS pediatric item banks v2.0 Anxiety and Depressive Symptoms, the short forms 8a and CATs are useful to assess and monitor anxiety and depression in a general population. Reference data are presented.

Girls' brain structural connectivity in late adolescence relates to history of depression symptoms

BACKGROUND

Girls' depressive symptoms typically increase in adolescence, with individual differences in course and severity being key risk factors for impaired emotional functioning in young adulthood. Given the continued brain white matter (WM) maturation that occurs in adolescence, the present study tested whether structural connectivity patterns in late adolescence are associated with variation in the course of depression symptom severity throughout adolescence.

METHOD

Participants were girls (N = 115) enrolled in a multiyear prospective cohort study of risk for depression. Initial depression severity (intercept) at age 10 and change in severity (linear slope) across ages 10-19 were examined in relation to WM tractography collected at age 19. Network-based statistic analyses were used to identify clusters showing variation in structural connectivity in association with depressive symptom intercept, slope, and their interaction.

RESULTS

Higher initial depressive severity and steeper positive slope (separately) were associated with greater structural connectivity between temporal, subcortical socioaffective, and occipital regions. Intercept showed more connectivity associations than slope. The interaction effect indicated that higher initial symptom severity and a steeper negative slope (i.e., alleviating symptoms) were related to greater connectivity between cognitive control regions. Moderately severe symptoms that worsened over time were followed by greater connectivity between self-referential and cognitive regions (e.g., posterior cingulate and frontal gyrus).

CONCLUSIONS

Higher depressive symptom severity in early adolescence and increasing symptom severity over time may forecast structural connectivity differences in late adolescence, particularly in pathways involving cognitive and emotion-processing regions. Understanding how clinical course relates to neurobiological correlates may inform new treatment approaches to adolescent depression.

Randomized control trial testing the effectiveness of implemented depression prevention in high-risk adolescents

BACKGROUND

Adolescent depression is a global mental health concern. Identification and effective prevention in an early stage are necessary. The present randomized, controlled trial aimed to examine the effectiveness of Cognitive Behavioral Therapy (CBT)-based depression prevention in adolescents with elevated depressive symptoms. This prevention approach is implemented in school communities, which allows to examine effects under real-life circumstances.

METHODS

A total of 5222 adolescents were screened for elevated depressive symptoms in the second grade of secondary schools; 130 adolescents aged between 12 and 16 years old (M = 13.59; SD = 0.68; 63.8% girls) were randomly assigned to the experimental (OVK 2.0) or control condition (psycho-education). Self- and parent-reported depressive symptoms were assessed at pretest and post intervention, as well as 6- and 12-months follow-up. Clinical assessment of depression was assessed at pretest and 6-months follow-up.

RESULTS

Intent-to-treat analyses revealed that the decrease in adolescent-rated depressive symptoms was significantly larger in the intervention condition than in the control condition. There was no significant difference in decrease of parent-rated depressive symptoms between both conditions.

CONCLUSIONS

Based on the findings, we recommend the implementation of screening and prevention in schools, according the basics of this study design. Since this is a new step forward, we discuss the clinical impact and challenges, as well possibilities for future research.

TRIAL REGISTRATION

The study is registered in the Dutch Trial Register for RCT's ( NTR5725 ). Date registered: 11 March 2016.