2026-05-06 バッファロー大学（UB）
＜関連情報＞
- https://www.buffalo.edu/news/releases/2026/05/Youth-vaping-AI-cessation-strategies.html
- https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001031
若年成人における電子タバコ使用中止に関連する要因の特定：機械学習とXAIアプローチ Identifying factors associated with vaping cessation in young adults: A machine learning and XAI approach
Poolakkad S. Satheeshkumar,Ian Lango,Swarnali Zafo,Mikaiel Ebanks,Rahul Kumar Das,Kit Wai Cheung,Roberto Pili,Supriya D. Mahajan
PLOS Digital Health Published: May 5, 2026
DOI:https://doi.org/10.1371/journal.pdig.0001031
Abstract
The public health impact of vaping in the United States reflects a complex balance of potential benefits and emerging risks, as e‑cigarettes may reduce exposure to toxic combustion byproducts and support adult smoking cessation, yet growing evidence links vaping to respiratory and cardiovascular harm and youth uptake remains concerning, with 38.4% of adolescent users in 2024 reporting habitual use. To inform the optimal use of predictive technologies in cessation efforts, this study sought to characterize cessation‑related behaviors and attitudes among young adult vapers and evaluate machine learning and explainable AI methods for predicting quit attempts and cessation success. A social media–based survey captured behavioral, contextual, and demographic factors, and cessation was defined as self‑reported abstinence from all vaping products for at least 30 days. Predictors were identified using forward selection and backward elimination, and data were split into training and testing sets. Linear models (LASSO, ridge regression, elastic net) and nonlinear models (random forest, support vector machine) were trained and evaluated using AUC and Brier scores. Linear models demonstrated the strongest overall performance: LASSO achieved AUCs of 0.89 (training) and 0.91 (testing), ridge regression 0.88 and 0.93, and elastic net 0.91 for both sets. Nonlinear models showed signs of overfitting, with random forest achieving 0.99 in training but only 0.70 in testing, and SVM achieving 0.89 and 0.72. Key predictors included age, environmental triggers, vaping frequency, sex, and long‑term behavioral outlook. Individuals under 25 showed greater vulnerability to continued use, environmental cues, especially social exposure, were strongly associated with relapse, and erratic vaping patterns predicted lower cessation success. While these models highlight behavioral and contextual factors that may influence cessation, findings should be interpreted as exploratory given the cross‑sectional design and sample characteristics. Larger, longitudinal studies are needed to validate these insights and clarify the potential of predictive modeling to inform targeted public health interventions.
Author summary
Vaping has become increasingly common among young adults in the United States, yet many users struggle to quit despite growing awareness of potential health risks. To better understand this challenge, we surveyed young adult vapers about their behaviors, motivations, and experiences with trying to stop. We then used several machine‑learning approaches to see whether these patterns could help predict who attempts to quit and who succeeds.
Our findings show that a combination of personal habits and environmental influences plays a major role in cessation. Younger adults, especially those under 25, were more likely to continue vaping, and social situations often triggered relapse. People who vaped frequently or in irregular patterns had a harder time quitting, while differences between men and women suggested that tailored support strategies may be helpful. Among the predictive tools we tested, simpler linear models performed the most reliably.
This study highlights how data‑driven methods can help identify factors linked to vaping cessation, but it also underscores the need for larger, long‑term research. Our results should be viewed as early insights that can guide future work aimed at reducing nicotine dependence and supporting young adults who want to quit.
