Search

Identifying determinants of smoking cessation is critical for developing optimal cessation treatments and interventions. Machine learning (ML) is becoming more prevalent for smoking cessation success prediction in treatment programs. However, only individuals with an intention to quit smoking cigarettes participate in such programs, which limits the generalizability of the results. This study applies data from the Population Assessment of Tobacco and Health (PATH), a United States longitudinal nationally representative survey, to select primary determinants of smoking cessation and to train ML classification models for predicting smoking cessation among the general population. An analytical sample of 9,281 adult current established smokers from the PATH survey wave 1 was used to develop classification models to predict smoking cessation by wave 2. Random forest and gradient boosting machines were applied for variable selection, and the SHapley Additive explanation method was used to show the effect direction of the top-ranked variables. The final model predicted wave 2 smoking cessation for current established smokers in wave 1 with an accuracy of 72% in the test dataset. The validation results showed that a similar model could predict wave 3 smoking cessation of wave 2 smokers with an accuracy of 70%. Our analysis indicated that more past 30 days e-cigarette use at the time of quitting, fewer past 30 days cigarette use before quitting, ages older than 18 at smoking initiation, fewer years of smoking, poly tobacco past 30-days use before quitting, and higher BMI resulted in higher chances of cigarette cessation for adult smokers in the US.

Identifying determinants of smoking cessation is critical for developing optimal cessation treatments and interventions. Machine learning (ML) is becoming more prevalent for smoking cessation success prediction in treatment programs. However, only individuals with an intention to quit smoking cigarettes participate in such programs, which limits the generalizability of the results. This study applies data from the Population Assessment of Tobacco and Health (PATH), a United States longitudinal nationally representative survey, to select primary determinants of smoking cessation and to train ML classification models for predicting smoking cessation among the general population. An analytical sample of 9,281 adult current established smokers from the PATH survey wave 1 was used to develop classification models to predict smoking cessation by wave 2. Random forest and gradient boosting machines were applied for variable selection, and the SHapley Additive explanation method was used to show the effect direction of the top-ranked variables. The final model predicted wave 2 smoking cessation for current established smokers in wave 1 with an accuracy of 72% in the test dataset. The validation results showed that a similar model could predict wave 3 smoking cessation of wave 2 smokers with an accuracy of 70%. Our analysis indicated that more past 30 days e-cigarette use at the time of quitting, fewer past 30 days cigarette use before quitting, ages older than 18 at smoking initiation, fewer years of smoking, poly tobacco past 30-days use before quitting, and higher BMI resulted in higher chances of cigarette cessation for adult smokers in the US.

BackgroundNondaily smoking has been on the rise, especially in Mexico. While Mexico has strengthened its tobacco control policies, their effects on nondaily smokers have gone largely unexamined. We developed a simulation model to estimate the impact of tobacco control policies on daily and nondaily smoking in Mexico.MethodsA previously validated Mexico SimSmoke model that estimated overall trends in smoking prevalence from 2002 through 2013 was extended to 2018 and adapted to distinguish daily and nondaily smoking prevalence. The model was then validated using data from Mexican surveys through 2016. To gauge the potential effects of policies, we compared the trends in smoking under current policies with trends from policies kept at their 2002 levels.ResultsBetween 2002 and 2016, Mexico SimSmoke underestimated the reduction in male and female daily smoking rates. For nondaily smoking, SimSmoke predicted a decline among both males and females, while survey rates showed increasing rates in both genders, primarily among ages 15-44. Of the total reduction in smoking rates predicted by the model by 2018, tax policies account for more than 55%, followed by health warnings, cessation treatment, smoke-free air laws, and tobacco control spending.ConclusionsAlthough Mexico SimSmoke did not successfully explain trends in daily and nondaily smoking, it helps to identify gaps in surveillance and policy evaluation for nondaily smokers. Future research should consider appropriate measures of nondaily smoking prevalence, trajectories between daily and nondaily smoking, and the separate impact of tobacco control policies on each group.