Longitudinal e-Cigarette and Cigarette Use Among US Youth in the PATH Study (2013-2015)

Abstract

Background: Evidence is accumulating that youth who try Electronic Nicotine Delivery Systems (ENDS, e-cigarettes) may go on to try cigarettes. This analysis examines the bidirectional patterns of ENDS and cigarette use among US youth over one year and uses propensity score matching (PSM) to examine frequency of ENDS use on changes in cigarette smoking.

Methods: Our analysis included 11 996 participants who had two waves of available data (Wave 1 [W1] 2013-2014; Wave 2 [W2] 2014-2015) drawn from the longitudinal Population Assessment of Tobacco and Health Study. Cross-sectional weighted prevalence estimates are reported for cigarettes and ENDS. We used PSM to estimate the likelihood of ENDS use at W1 and to draw matched analytic samples, then used regression (logistic or linear) models to examine the effect of W1 ENDS use on W2 cigarette smoking. All statistical tests were two-sided.

Results: In weighted analyses, 69.3% of W1 past-30-day cigarette smokers exhibited past-30-day smoking at W2; 42.2% of W1 past-30-day ENDS users were using ENDS at W2. W1 ever use of either product was similarly associated with W2 new use of the other product. Unweighted PSM models indicated W1 cigarette-naïve ENDS use was associated with W2 ever-cigarette smoking (n = 676; adjusted odds ratio = 3.21, 95% confidence interval [CI] = 1.95 to 5.45, P < .001); W1 ever-ENDS use did not affect change in cigarette frequency at W2 (n = 1020, beta = 0.31, 95% CI = -0.76 to 1.39, P = .57); 1-5 days ENDS use compared with ever, no past-30-day ENDS use was associated with a statistically significant decrease of W2 smoking days (n = 256, beta = -2.64, 95% CI = -4.96 to -0.32; P = .03); and W1 6+ day ENDS users did not show a decrease in frequency of cigarette smoking.

Conclusions: Ever-ENDS use predicts future cigarette smoking, and frequency of ENDS use has a differential impact on subsequent cigarette smoking uptake or reduction. These results suggest that both cigarettes and ENDS should be targeted in early tobacco prevention efforts with youth.

Figure 1.

Weighted percentage of ever and past-30-day cigarette smoking and ENDS use among youth (12–17 years) at Wave 1 (W1; 2013–2014) and Wave 2 (W2; 2014–2015) of the Population Assessment of Tobacco and Health Study Study. Ever use of cigarettes and Electronic Nicotine Delivery System was defined as having ever used the product. Past-30-day (P30D) use was defined as any use of the product in the past 30 days. n = unweighted sample size. Sample sizes in Figure 1 reflect cross-sectional data at each wave and are not limited to respondents in both waves (W1 total youth sample 13 651; W2 total youth sample 12 172); the W2 cross-sectional sample may include youth who aged into the study (W1 shadow youth who are youth at W2; n = 2091), youth at W1 and W2 (n = 10 081), or exclude youth who transitioned into the adult sample (youth who were age 17 years at W1 and were age 18 years at W2; n = 1915).

Figure 2.

Unweighted mean change in past-30-day cigarette frequency from Wave 1 (W1; 2013–2014) to Wave 2 (W2; 2014–2015) among W1 youth ever-cigarette smokers in the Population Assessment of Tobacco and Health Study. P30D refers to past-30-day use, defined as any use of the product in the past 30 days. n = unweighted sample size n = 18 ever-cigarette and e-cigarette users at Wave 1 had missing e-cigarette frequency at W1 (18/785 = 2.3%). Mean number of days smoked cigarettes in the P30D among W1 ever-cigarette smokers based on Electronic Nicotine Delivery System (ENDS) use status are as follows: among never-ENDS users, mean number of smoking days at W1 = 1.62, W2 = 3.06; among ever-ENDS users, mean number of smoking days at W1 = 6.66, W2 = 8.74; among ever, no-P30D-ENDS users, mean number of smoking days at W1 = 5.76, W2 = 8.18; among 1–5 day-ENDS users, mean number of smoking days at W1 = 8.71, W2 = 9.41; and among 6+ day ENDS users, mean number of smoking days at W1 = 8.31, W2 = 11.91.