Background Adolescence represents a sensitive developmental period characterised by an increased incidence of emerging mental health symptoms and formal diagnostic onset. These conditions can remain a significant burden throughout life. The Longitudinal Adolescent Brain Study (LABS) commenced in 2018 to track the onset and trajectory of mental health symptoms among general population participants. This research aims to identify polysymptomatic clusters of emerging mental health symptoms in adolescents and examine how these clusters vary by age and change over time, providing insights into the pluripotentiality of disorder development.

Methods LABS participants aged 12-17 years (n=166) completed the Mini International Neuropsychiatric Interview (MINI Kid) approximately every 4 months, with up to 15 timepoints. Due to this high dimensional dataset, the data was first processed using a dimensionality reduction step (uniform manifold approximation and projection; UMAP). Following this, the data was clustered using Bayesian model averaging of k-means, gaussian mixture model and hierarchical clustering to identify distinct symptom clusters. Symptom clusters were described in terms of the original neuropsychiatric interview responses using separate XGBoost classifier models. Symptom cluster dynamics were analysed using Markov chain transition probability matrices and longitudinal analysis. To explore the relationship between symptom clusters and psychological distress and wellbeing, correlational analyses were conducted using scores from the Kessler Psychological Distress Scale (K10) and the COMPAS-W Wellbeing Scale.

Outcomes Six symptom-based clusters (states) were identified: attention, anxiety, depression, manic episode - heritability, anhedonia, and well. Depression and anxiety clusters had the greatest pluripotentiality. Analysis of psychological distress and wellbeing demonstrated an inverse relationship between the states: those with greater psychological distress had more symptoms, conversely those with greater wellbeing had fewer symptoms.

Interpretations Mapping polysymptomatic clusters of mental health symptoms and their pluripotential and transitory trajectories in adolescents enables more effective targeting of preventive interventions. This approach moves beyond categorical classifications to mitigate the progression of early symptoms into enduring psychiatric disorders.

The authors have declared no competing interest.

This work was supported by a grant from the Prioritising Mental Health Initiative, Australian Commonwealth Government.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

This observational cohort study was conducted in adherence with the Declaration of Helsinki and is approved by the University of the Sunshine Coast Human Research Ethics Committee (A1811064). All participants and guardians provided informed written consent prior to commencement of study participation.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

the data and code necessary to reproduce the analyses here are not publicly accessible, as are materials necessary to replicate the findings. Analyses were not preregistered.