Identifying risk profiles for marijuana vaping among U.S. young adults by recreational marijuana legalization status: A machine learning approach. (1st March 2022)

• Record Type: Journal Article
• Authors: Han, Dae-Hee; Seo, Dong-Chul
• Is Part Of: Drug and alcohol dependence. Volume 232(2022)
• Publication Date: 2022-03-01
• Subjects: Marijuana vaping -- Young adults -- Risk profile -- Endophenotype -- Machine learning -- Recreational marijuana legalization; Drug abuse -- Periodicals; Alcoholism -- Periodicals; 616.86
• DOI: 10.1016/j.drugalcdep.2022.109330
• Languages: English
• ISSNs: 0376-8716

Abstract

Abstract: Introduction: This study attempted to identify risk profiles of marijuana vaping by state-level recreational marijuana legalization (RML) status among U.S. young adults (YA). Methods: Data were drawn from the most recent two waves of restricted use files of the Population Assessment of Tobacco and Health Study with state identifiers. We analyzed 6155 young adult (18–24 years) respondents who were naïve to marijuana vaping at Wave 4 and had matched data at Wave 5. We employed a two-stage machine learning approach to predict marijuana vaping initiation at Wave 5 with predictors measured at Wave 4. Results: Among YA who had never vaped marijuana at Wave 4, 19% of those who lived in the states with RML and 15% of those who lived in the states without RML reported marijuana vaping at Wave 5. Substance-use-related predictors were rarely found as leading predictors in the states with RML. In the states without RML, substance use behaviors, including electronic nicotine delivery systems and smokeless tobacco use, and the presence of externalizing symptoms emerged as predictors for marijuana vaping. Results also revealed that nonlinear interactions between the predictors of marijuana vaping. Conclusions: Our results highlight the importance of accounting for the RML status in developing risk profiles of marijuana vaping. Externalizing symptoms may be a behavioral endophenotype of marijuana vaping in the states without RML. Machine learning appears to be a promising analytical approach to identify complex interactions between factors in predicting an emerging risk behavior such as marijuana vaping. Highlights: Rates of marijuana vaping initiation differed by marijuana legalization status. Predictors of marijuana vaping initiation differed by marijuana legalization status. Machine learning analysis helped reveal complex and nonlinear interactions. Externalizing problems may be a behavioral endophenotype of marijuana vaping.