Prediction of the trajectories of depressive symptoms among children in the adolescent brain cognitive development (ABCD) study using machine learning approach

The Dynamic Interplay Between Puberty and Structural Brain Development as a Predictor of Mental Health Difficulties in Adolescence: A Systematic Review

Puberty is a time of intense reorganization of brain structure and a high-risk period for the onset of mental health problems, with variations in pubertal timing and tempo intensifying this risk. We conducted 2 systematic reviews of articles published up to February 1, 2024, focusing on 1) the role of brain structure in the relationship between puberty and mental health, and 2) precision psychiatry research evaluating the utility of puberty in making individualized predictions of mental health outcomes in young people. The first review provides inconsistent evidence about whether and how pubertal and psychopathological processes may interact in relation to brain development. While most studies found an association between early puberty and mental health difficulties in adolescents, evidence on whether brain structure mediates this relationship is mixed. The pituitary gland was found to be associated with mental health status during this time, possibly through its central role in regulating puberty and its function in the hypothalamic-pituitary-gonadal and hypothalamic-pituitary-adrenal axes. In the second review, the design of studies that have explored puberty in predictive models did not allow for a quantification of its predictive power. However, when puberty was evaluated through physically observable characteristics rather than hormonal measures, it was more commonly identified as a predictor of depression, anxiety, and suicidality in adolescence. Social processes may be more relevant than biological ones to the link between puberty and mental health problems and represent an important target for educational strategies.

Individual Trajectories of Depressive Symptoms Within Racially-Ethnically Diverse Youth: Associations with Polygenic Risk for Depression and Substance Use Intent and Perceived Harm

There are distinct individual trajectories of depressive symptoms across adolescence which are most often differentiated into low, moderate/stable, and high/increasing groups. Research has found genetic predisposition for depression associated with trajectories characterized by greater depressive symptoms. However, the majority of this research has been conducted in White youth. Moreover, a separate literature indicates that trajectories with elevated depressive symptoms can result in substance use. It is critical to identify depressive symptom trajectories, genetic predictors, and substance use outcomes in diverse samples in early adolescence to understand distinct processes and convey equitable benefits from research. Using data from the Adolescent Cognitive Brain Development Study (ABCD), we examined parent-reported depressive symptom trajectories within Black/African American (AA, n = 1783), White/European American (EA, n = 6179), and Hispanic/Latinx (LX, n = 2410) youth across four annual assessments in early adolescence (age 9-10 to 12-13). We examined racially/ethnically aligned polygenic scores (Dep-PGS) as predictors of trajectories as well as substance use intent and perceived substance use harm as outcomes at age 12-13. Differential trajectories were found in AA, EA, and LX youth but low and high trajectories were represented within each group. In EA youth, greater Dep-PGS were broadly associated with membership in trajectories with greater depressive symptoms. Genetic effects were not significant in AA and LX youth. In AA youth, membership in the low trajectory was associated with greater substance use intent. In EA youth, membership in trajectories with higher depressive symptoms was associated with greater substance use intent and less perceived harm. There were no associations between trajectories and substance use intent and perceived harm in LX youth. These findings indicate that there are distinct depressive symptom trajectories in AA, EA, and LX youth, accompanied by unique associations with genetic predisposition for depressive symptoms and substance use outcomes.

Predicting new onset thought disorder in early adolescence with optimized deep learning implicates environmental-putamen interactions

Background

Thought disorder (TD) is a sensitive and specific marker of risk for schizophrenia onset. Specifying factors that predict TD onset in adolescence is important to early identification of youth at risk. However, there is a paucity of studies prospectively predicting TD onset in unstratified youth populations.

Study Design

We used deep learning optimized with artificial intelligence (AI) to analyze 5,777 multimodal features obtained at 9-10 years from youth and their parents in the ABCD study, including 5,014 neural metrics, to prospectively predict new onset TD cases at 11-12 years. The design was replicated for all prevailing TD cases at 11-12 years.

Study Results

Optimizing performance with AI, we were able to achieve 92% accuracy and F1 and 0.96 AUROC in prospectively predicting the onset of TD in early adolescence. Structural differences in the left putamen, sleep disturbances and the level of parental externalizing behaviors were specific predictors of new onset TD at 11-12 yrs, interacting with low youth prosociality, the total parental behavioral problems and parent-child conflict and whether the youth had already come to clinical attention. More important predictors showed greater inter-individual variability.

Conclusions

This study provides robust person-level, multivariable signatures of early adolescent TD which suggest that structural differences in the left putamen in late childhood are a candidate biomarker that interacts with psychosocial stressors to increase risk for TD onset. Our work also suggests that interventions to promote improved sleep and lessen parent-child psychosocial stressors are worthy of further exploration to modulate risk for TD onset.

Longitudinal trajectories of sickness absence among young adults with a history of depression and anxiety symptoms in Sweden

BACKGROUND

Depression and anxiety are associated with increased risk of sickness absence (SA), yet the developmental patterns of SA remain unclear. We aimed to identify trajectories of SA in young adults with depression and/or anxiety, accounting for sociodemographic and occupational factors.

METHODS

Longitudinal study of 1445 twin individuals with elevated depressive/anxiety symptoms in late adolescence or young adulthood (age range: 19-30), assessed in Swedish surveys completed in 2005. Through linkage to nationwide registries, individuals were prospectively followed from 2006 to 2018. The outcome included consecutive annual days of SA, which were analyzed using group-based trajectory modeling. Multinomial logistic regression estimating odds ratios (OR) with 95 % confidence intervals (CI) was used to examine associations of age, sex, and educational level with the resulting SA trajectories.

RESULTS

Four distinct SA trajectories were identified in the total sample: 'high-increasing' (6 %), 'low-increasing' (12 %), 'high-decreasing' (13 %), and 'low-constant' (69 %). Increasing age was associated with higher odds of belonging to the low-increasing trajectory (OR = 1.07, 95 % CI = 1.02-1.12). Women had higher odds of belonging to the low-increasing trajectory (OR = 1.67, 95 % CI = 1.10-2.53), compared with men. Higher education was associated with lower odds of belonging to high-increasing (OR = 0.34, 95 % CI = 0.22-0.54) and high-decreasing (OR = 0.59, 95 % CI = 0.43-0.81) trajectories, compared with lower education. Few differences were observed in analyses stratified by occupational sector.

LIMITATIONS

Information on potential confounders (e.g., psychiatric comorbidity, work-environment factors) was not available.

CONCLUSIONS

Among young adults with prior depression/anxiety, close to every fifth showed rising SA trajectories over time. This calls for targeted strategies to improve public mental health already at young ages.

Predicting individual cases of major adolescent psychiatric conditions with artificial intelligence

Three-quarters of lifetime mental illness occurs by the age of 24, but relatively little is known about how to robustly identify youth at risk to target intervention efforts known to improve outcomes. Barriers to knowledge have included obtaining robust predictions while simultaneously analyzing large numbers of different types of candidate predictors. In a new, large, transdiagnostic youth sample and multidomain high-dimension data, we used 160 candidate predictors encompassing neural, prenatal, developmental, physiologic, sociocultural, environmental, emotional and cognitive features and leveraged three different machine learning algorithms optimized with a novel artificial intelligence meta-learning technique to predict individual cases of anxiety, depression, attention deficit, disruptive behaviors and post-traumatic stress. Our models tested well in unseen, held-out data (AUC ≥ 0.94). By utilizing a large-scale design and advanced computational approaches, we were able to compare the relative predictive ability of neural versus psychosocial features in a principled manner and found that psychosocial features consistently outperformed neural metrics in their relative ability to deliver robust predictions of individual cases. We found that deep learning with artificial neural networks and tree-based learning with XGBoost outperformed logistic regression with ElasticNet, supporting the conceptualization of mental illnesses as multifactorial disease processes with non-linear relationships among predictors that can be robustly modeled with computational psychiatry techniques. To our knowledge, this is the first study to test the relative predictive ability of these gold-standard algorithms from different classes across multiple mental health conditions in youth within the same study design in multidomain data utilizing >100 candidate predictors. Further research is suggested to explore these findings in longitudinal data and validate results in an external dataset.