Predictors of perceived success in quitting smoking by vaping: A machine learning approach.

Prior research has suggested that a set of unique characteristics may be associated with
adult cigarette smokers who are able to quit smoking using e-cigarettes (vaping). In this
cross-sectional study, we aimed to identify and rank the importance of these characteristics
using machine learning. During July and August 2019, an online survey was administered to
a convenience sample of 889 adult smokers (age � 20) in Ontario, Canada who tried vaping
to quit smoking in the past 12 months. Fifty-one person-level characteristics, including a
Vaping Experiences Score, were assessed in a gradient boosting machine model to classify
the status of perceived success in vaping-assisted smoking cessation. This model was
trained using cross-validation and tested using the receiver operating characteristic (ROC)
curve. The top five most important predictors were identified using a score between 0% and
100% that represented the relative importance of each variable in model training. About
20% of participants (N = 174, 19.6%) reported success in vaping-assisted smoking cessation.
The model achieved relatively high performance with an area under the ROC curve of
0.865 and classification accuracy of 0.831 (95% CI [confidence interval] 0.780 to 0.874).
The top five most important predictors of perceived success in vaping-assisted smoking
cessation were more positive experiences measured by the Vaping Experiences Score
(100%), less previously failed quit attempts by vaping (39.0%), younger age (21.9%), having
vaped 100 times (16.8%), and vaping shortly after waking up (15.8%). Our findings provide
strong statistical evidence that shows better vaping experiences are associated with greater
perceived success in smoking cessation by vaping. Furthermore, our study confirmed the
strength of machine learning techniques in vaping-related outcomes research based on
observational data.

Fu R, Schwartz R, Mitsakakis N, Diemert LM, O’Connor S, Cohen JE. Predictors of perceived success in quitting smoking by vaping: A machine learning approach. PloS one. 2022;17(1):1. doi:10.1371/journal.pone.0262407