Identifying Risk Factors of Substance Use in Finland
A Machine Learning Approach
Bibliographic Data
| ID | 21645458 |
|---|---|
| Authors | Ali Unlu (0000-0003-0140-7761, University of Virginia, corresponding author), Pekka Hakkarainen (0000-0002-6402-5579, Alcohol, The Promotional and Preventive Work Unit, Finnish Institute for Health and Welfare (THL)), Karoliina Karjalainen (0000-0003-2377-3324, Alcohol, The Promotional and Preventive Work Unit, Finnish Institute for Health and Welfare (THL)), Tuukka Tammi (0000-0001-5114-3026, Research Program Director, Finnish Institute for Health and Welfare (THL)), Abdulhamit Subasi (0000-0001-7630-4084, Information Sciences & Technology Department, College of Emergency Preparedness, Homeland Security & Cybersecurity, University at Albany, SUNY) |
| Year | 2025 |
| Volume | 60 |
| Issue | 12 |
| Pages | 1753-1770 |
| Publication date | 2025-10-15 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Substance Use & Misuse (JOURNAL) |
| Journal identifiers | ISSN: 1082-6084 • E-ISSN: 1532-2491 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/10826084.2025.2516738 |
| PMID | 40522359 |
| OpenAlex | W4411344132 |
| Language | EN |
| References cited | 56 |
Background: This study explores the dynamics of substance use in Finland, employing Artificial Intelligence (AI) and Machine Learning techniques to identify key risk factors and predict patterns of drug use. Objectives: Using data from the Finnish National Drug Survey and applying 15 feature selection methodologies, this study identifies 23 risk factors associated with the five most used illicit substances: cannabis, ecstasy, amphetamines, cocaine, and non-medical prescription drugs. Results: The most common risk factors include the consumption of e-cigarettes, free and purchased drug offers, and drug-related health problems. This study explores the application of the Bidirectional Long Short-Term Memory (BiLSTM) model for predicting substance use across, demonstrating promising accuracy in this context. Conclusions: By integrating AI methodologies with epidemiological data, this research offers valuable insights for targeted prevention strategies and policy interventions. The findings underscore the complexity of substance use behaviors and highlight the potential of predictive analytics in public health research, aiming to inform and enhance prevention efforts in Finland
Substance use · Artificial Intelligence in Healthcare · Clinical Psychology · Data Quality and Management · Machine Learning in Healthcare · Medicine · Psychology
A review of psychosocial factors linked to adolescent substance use
Self-reported health as a predictor of mortality
Epidemiology of substance use disorders
Epidemiology of DSM-5 Drug Use Disorder
Social vulnerabilities for substance use
Feature Selection with the Boruta Package
Health Literacy, Self-Perceived Health, and Substance Use Behavior among Young People with Alcohol and Substance Use Disorders
| Highly cited | No |
|---|