Studying adolescent vaping is becoming increasingly important since, in the COVID-19 era, it can pose a greater risk to potential health issues. In a new study, researchers have developed a machine learning approach to uncover differentiating predictors of vaping dependence for adolescent daily and non-daily vapers, as well as those unique to the COVID-19 era.
The research was conducted by MDPI, a multidisciplinary open access publisher since 1996 with a worldwide reach. They focus on delivering high-quality peer-reviewed scientific works to the scientific community. The study team analyzed the survey data of adolescents from 25 different countries collected through the Youth Tobacco Policy Survey. Analyzing data from 2020 to 2022, they developed a machine learning approach to investigate several predictors associated with vaping dependence.
The study revealed that differentiating predictors of vaping dependence varied by vaping frequency. Among daily vapers, factors such as being male, having poor parental support, and having more peers who vape were strongly associated with higher likelihood of developing dependence. On the other hand, non-daily vapers had more predictors of dependence such as smoking and drinking, experimental substance use, and being more susceptible to peer influence.
The findings from this research could help inform strategists on how to target youth on the factors that contribute to vaping dependence and develop more useful interventions. The study is also especially timely as it sheds light on the importance of monitoring adolescent vaping behavior during the COVID-19 era, as the risk may be particularly high due to its being a pandemic experience.
By providing open access to their works, MDPI highlights the importance of scientific research in identifying predictors of vaping dependence that can help inform the fields of public health and youth tobacco policy. Their open access policy allows anyone to access and reuse part of their articles, including figures and tables, without requiring special permission as long as the original article is cited.
