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

## TL;DR

This study uses deep learning to identify groups of adolescents with different patterns of mental health issues and finds that some groups are at higher risk for suicide and need targeted support.

## Contribution

The novel use of deep clustering to classify adolescent mental health trajectories and identify predictors of suicide risk.

## Key findings

- Five distinct mental health trajectory clusters were identified in adolescents.
- The 'discrepant' cluster showed the highest risk for self-harm and suicidal ideation despite being overlooked by caregivers.
- Avoiding help-seeking for depression predicted membership in the high-risk 'discrepant' cluster.

## Abstract

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.

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.

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.

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.

Japan Ministry of Health, Labor and Welfare, Japan Agency for Medical Research and Development, and 10.13039/501100002241Japan Science and Technology Agency.