Factors Associated with E-Cigarette Use in U.S. Young Adult Never Smokers of Conventional Cigarettes: A Machine Learning Approach

Abstract

E-cigarette use is increasing among young adult never smokers of conventional cigarettes, but the awareness of the factors associated with e-cigarette use in this population is limited. The goal of this work was to use machine learning (ML) algorithms to determine the factors associated with current e-cigarette use among US young adult never cigarette smokers. Young adult (18–34 years) never cigarette smokers from the 2016 and 2017 Behavioral Risk Factor Surveillance System (BRFSS) who reported current or never e-cigarette use were used for the analysis (n = 79,539). Variables associated with current e-cigarette use were selected by two ML algorithms (Boruta and Least absolute shrinkage and selection operator (LASSO)). Odds ratios were calculated to determine the association between e-cigarette use and the variables selected by the ML algorithms, after adjusting for age, gender and race/ethnicity and incorporating the BRFSS complex design. The prevalence of e-cigarette use varied across states. Factors previously reported in the literature, such as age, race/ethnicity, alcohol use, depression, as well as novel factors associated with e-cigarette use, such as disabilities, obesity, history of diabetes and history of arthritis were identified. These results can be used to generate further hypotheses for research, increase public awareness and help provide targeted e-cigarette education.

E-Cigarette Use in Young Adult Never Cigarette Smokers with Disabilities: Results from the Behavioral Risk Factor Surveillance System Survey

“…The ML approach identified previously unreported features associated with e-cigarette use such as cognitive, independent living, vision, and self-care disabilities. The ML approach found no association between e-cigarette use and hearing and mobility disabilities [27]. In this study, these findings were confirmed after creating subgroups with participants who reported different disabilities and no disability, and adjusting with confounders specific to the disability of interest.…”

“…The LASSO algorithm has been used to select variables associated with current ecigarette use in young adult never cigarette smokers [27] and has been used in other types of survey and medical data [42][43][44]. The LASSO algorithm penalizes the regression model parameters and reduces the least important variables to zero, thereby selecting the most important variables for the model [39].…”

“…To reduce the limitations and errors due to one application of the LASSO algorithm, and to reduce the sensitivity of LASSO to small perturbations in the data [46], 300 iterations of LASSO were performed. For each iteration, random samples comprising of 80% of the original data were used [27]. For each iteration, a 10-fold cross-validation selected the lambda (λ m ) that produced the minimum mean cross validation error [39,47].…”

“…All the variables that were selected in >95% of the iterations were considered significant variables for e-cigarette use or the disability of interest. More details can be found elsewhere [27].…”

“…This study built on recent work by Atuegwu et al that used machine learning (ML) techniques to identify factors associated with current e-cigarette use in young adult never cigarette smokers. The ML algorithms identified previously unreported potential associations between e-cigarette use and some types of disability in young adult never cigarette smokers [27]. The goal of this study was to examine the associations between the different types of disability and e-cigarette use in young adult never cigarette smokers.…”