Uncovering Polysubstance Use Patterns in Canadian Youth with Machine Learning on Longitudinal COMPASS Data
Bibliographic record
Abstract
Abstract Understanding polysubstance use (PSU) patterns and their associated factors among youth is crucial for addressing the complex issue of substance use in this population. This study aims to investigate PSU patterns in a large sample of Canadian youth and explore associated factors using data from COMPASS, a longitudinal health survey of Canadian secondary school students. The study sample consisted of 8824 students from grades 9 and 10 at baseline in 2016/17, followed over 3 years until 2018/19. Leveraging machine learning methods, especially the least absolute shrinkage and selection operator (LASSO) and multivariate latent Markov models, we conducted a comprehensive examination of PSU patterns. Our analyses revealed distinct PSU patterns among Canadian youth, including no-use (C1), alcohol-only (C2), concurrent use of e-cigarettes and alcohol (C3), and poly-use (C4). C1 showed the highest prevalence (60.5%) in 2016/17, declining by 2.4 times over 3 years, while C3 became the dominant pattern (32.5%) in 2018/19. The prevalence of C3 and C4 increased by 2.3 and 4.4 times, respectively, indicating a growing trend of dual and multiple substance use. Risk factors associated with PSU patterns included truancy (ORC2 = 1.67, 95 % CI [1.55, 1.79]; ORC3 = 1.92, 95 % CI [1.80, 2.04]; ORC4 = 2.79, 95 % CI [2.64, 2.94]), having more smoking friends, more weekly allowance, elevated BMI, being older, and attending schools unsupportive in quitting drugs/alcohol. In contrast, not gambling online (ORC2 = 0.22, 95 % CI [−0.16, 0.58]; ORC3 = 0.14, 95 % CI [-0.24, 0.52]; ORC4 = 0.08, 95 % CI [−0.47, 0.63]), eating breakfast, residing in urban areas, and having higher school connectedness were protective factors against a higher-use pattern. This study provides insights for policymakers, educators, and health professionals to design targeted and evidence-based interventions, addressing youth substance use challenges through a comprehensive examination of PSU patterns and influential factors impacting substance use behaviors.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".