Using Decision Trees to Examine Environmental and Behavioural Factors Associated with Youth Anxiety, Depression, and Flourishing

Using random forest to identify correlates of depression symptoms among adolescents

PURPOSE

Adolescent depression is a significant public health concern, and studying its multifaceted factors using traditional methods possess challenges. This study employs random forest (RF) algorithms to determine factors predicting adolescent depression scores.

METHODS

This study utilized self-reported survey data from 56,008 Canadian students (grades 7-12) attending 182 schools during the 2021/22 academic year. RF algorithms were applied to identify the correlates of (i) depression scores (CESD-R-10) and (ii) presence of clinically relevant depression (CESD-R-10 ≥ 10).

RESULTS

RF achieved a 71% explained variance, accurately predicting depression scores within a 3.40 unit margin. The top 10 correlates identified by RF included other measures of mental health (anxiety symptoms, flourishing, emotional dysregulation), home life (excessive parental expectations, happy home life, ability to talk to family), school connectedness, sleep duration, and gender. In predicting clinically relevant depression, the algorithm showed 84% accuracy, 0.89 sensitivity, and 0.79 AUROC, aligning closely with the correlates identified for depression score.

CONCLUSION

This study highlights RF's utility in identifying important correlates of adolescent depressive symptoms. RF's natural hierarchy offers an advantage over traditional methods. The findings underscore the importance and additional potential of sleep health promotion and school belonging initiatives in preventing adolescent depression.

Inequitable Changes in School Connectedness During the Ongoing COVID-19 Pandemic in a Cohort of Canadian Adolescents

BACKGROUND

We examined whether subgroups of adolescents experienced disparate changes in school connectedness-a robust predictor of multiple health outcomes-from before the COVID-19 pandemic to the first full school year following pandemic onset.

METHODS

We used 2 waves of prospective survey data from 7178 students attending 41 Canadian secondary schools that participated during the 2019-2020 (T1; pre-COVID-19 onset) and 2020-2021 (T2; ongoing pandemic) school years. Fixed effects analyses tested differences in school connectedness changes by gender, race, bullying victimization, socioeconomic position, and school learning mode.

RESULTS

Relatively greater declines in school connectedness were reported by students that identified as females, were bullied, perceived their family to be less financially comfortable than their classmates, and attended schools in lower income areas. Marginally greater school connectedness declines resulted among students attending schools that were fully online at T2 than those at schools using a blended model.

CONCLUSION

Results point to disparate school connectedness declines during the pandemic, which may exacerbate pre-existing health inequities by gender and socioeconomic position, and among bullied youth.

IMPLICATIONS FOR SCHOOL HEALTH POLICY, PRACTICE, AND EQUITY

Effective strategies to improve school climates for equity denied groups are critical for pandemic recovery and preparedness for future related events.

Exploring risk factors and their differences on suicidal ideation and suicide attempts among depressed adolescents based on decision tree model

BACKGROUND

Suicide has been recognized as a major global public health issue. Depressed adolescents are more prone to experiencing it. We explore risk factors and their differences on suicidal ideation and suicide attempts to further enhance our understanding of suicidal behavior.

METHODS

2343 depressed adolescents aged 12-18 from 9 provinces/cities in China participated in this cross-sectional study. We utilized decision tree model, incorporating 32 factors encompassing participants' suicidal behavior. The feature importance of each factor was measured using Gini coefficients.

RESULTS

The decision tree model demonstrated a good fit with high accuracy (SI = 0.86, SA = 0.85 and F-Score (SI = 0.85, SA = 0.83). The predictive importance of each factor varied between groups with suicidal ideation and with suicide attempts. The most significant risk factor in both groups was depression (SI = 16.7 %, SA = 19.8 %). However, factors such as academic stress (SI = 7.2 %, SA = 1.6 %), hopelessness (SI = 9.1 %, SA = 5.0 %), and age (SI = 7.1 %, SA = 3.2 %) were more closely associated with suicidal ideation than suicide attempts. Factors related to the schooling status (SI = 3.5 %, SA = 10.1 %), total years of education (SI = 2.6 %, SA = 8.6 %), and loneliness (SI = 2.3 %, SA = 7.4 %) were relatively more important in the suicide attempt stage compared to suicidal ideation.

LIMITATIONS

The cross-sectional design limited the ability to capture changes in suicidal behavior among depressed adolescents over time. Possible bias may exist in the measurement of suicidal ideation.

CONCLUSION

The relative importance of each risk factor for suicidal ideation and attempted suicide varies. These findings provide further empirical evidence for understanding suicide behavior. Targeted treatment measures should be taken for different stages of suicide in clinical interventions.

Adolescents' Depression and Anxiety Symptoms During the COVID-19 Pandemic: Longitudinal Evidence From COMPASS

PURPOSE

There is concern over the potentially detrimental impact of the COVID-19 pandemic on adolescents' mental health. We examined changes in depression and anxiety symptoms from before (2018-19) to the early (2019-20) and ongoing pandemic (2020-21) responses among Canadian adolescents in the context of a natural experiment.

METHODS

We used linked survey data from 5,368 Canadian secondary school students who participated in three consecutive waves of the cannabis use, obesity, mental health, physical activity, alcohol use, smoking, and sedentary behaviour study during the 2018-19, 2019-20, and 2020-21 school year. Separate fixed effects models examined whether changes in depression (Center for Epidemiologic Studies Depression Scale Revised-10) and anxiety (General Anxiety Disorder-7) symptoms differed between two cohorts. The cohorts differed in the timing of their second data collection wave; one cohort participated before the pandemic and the other cohort participated in the early pandemic (spring 2020).

RESULTS

Depression and anxiety symptoms increased during the early and ongoing pandemic periods in the overall sample and both cohorts. The two cohorts experienced similar elevations in their symptoms. Females and younger respondents presented greater elevations over time. The proportion of adolescents with significant depressive (29.4%) and moderate-to-severe anxiety (17.6%) symptoms at baseline increased by 1.5 times, reaching 44.8% and 29.8% in the ongoing pandemic period, respectively.

DISCUSSION

Findings suggest that internalizing symptoms have consistently increased since before the onset of COVID-19, particularly in the ongoing pandemic period; however, we found no evidence of the increase being due to the pandemic in the early COVID-19 period when comparing the two cohorts. Ongoing evaluation of adolescents' mental health is necessary to capture potentially dynamic impacts over time.