Machine Learning–Based Prediction of Substance Use in Adolescents in Three Independent Worldwide Cohorts: Algorithm Development and Validation Study
Based on multinational datasets from South Korea, the United States, and Norway, this study shows the potential of ML models, particularly the XGBoost model, in predicting adolescent substance use. These findings provide a solid basis for future research exploring additional influencing factors or developing targeted intervention strategies.
Authors
- Jaeyu Park (ORCID: https://orcid.org/0009-0005-2009-386X)
- Hayeon Lee (ORCID: https://orcid.org/0009-0000-2403-6241)
- Selin Woo (ORCID: https://orcid.org/0000-0001-7961-2074)
- Dong Keon Yon (ORCID: https://orcid.org/0000-0003-1628-9948)
- Rosie Kwon (ORCID: https://orcid.org/0000-0001-5422-4446)
- Guillaume B. Fond (ORCID: https://orcid.org/0000-0003-3249-2030)
- Hyejun Kim (ORCID: https://orcid.org/0009-0009-1409-6123)
- Min Seo Kim (ORCID: https://orcid.org/0000-0003-2115-7835)
- Lee Smith (ORCID: https://orcid.org/0000-0002-5340-9833)
- Hojae Lee (ORCID: https://orcid.org/0009-0002-1737-2540)
- Sung Wook Baik (ORCID: https://orcid.org/0000-0002-6678-7788)
- Hyeon Jin Kim (ORCID: https://orcid.org/0000-0003-1286-4669)
- Yujin Choi (ORCID: https://orcid.org/0009-0002-4131-712X)
- Laurent Boyer (ORCID: https://orcid.org/0000-0003-1229-6622)
- Ahmed Hammoodi (ORCID: https://orcid.org/0009-0004-6381-5087)
- Soeun Kim (ORCID: https://orcid.org/0009-0009-5874-417X)
- Seokjun Kim (ORCID: https://orcid.org/0009-0006-8716-7904)
Institutions
- Broad Institute (US)
- Yonsei University (KR)
- Aix-Marseille Université (FR)
- Sejong University (KR)
- Kyung Hee University (KR)
- Assistance Publique Hôpitaux de Marseille (FR)
- Kyung Hee University Medical Center (KR)
- Anglia Ruskin University (GB)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-01-16
- DOI
- https://doi.org/10.2196/62805
- Citations
- 2
- Primary Topic
- Health, Environment, Cognitive Aging
- Type
- article
- Field-Weighted Citation Impact
- 2.40