Despite the harmful effect on health, e-cigarette and hookah smoking in youth in the U.S. has increased. Developing tailored e-cigarette and hookah cessation programs for youth is imperative. The aim of this study was to identify predictor variables such as social, mental, and environmental determinants that cause nicotine addiction in youth e-cigarette or hookah users and build nicotine addiction prediction models using machine learning algorithms. A total of 6511 participants were identified as ever having used e-cigarettes or hookah from the National Youth Tobacco Survey (2019) datasets. Prediction models were built by Random Forest with ReliefF and Least Absolute Shrinkage and Selection Operator (LASSO). ReliefF identified important predictor variables, and the Davies–Bouldin clustering evaluation index selected the optimal number of predictors for Random Forest. A total of 193 predictor variables were included in the final analysis. Performance of prediction models was measured by Root Mean Square Error (RMSE) and Confusion Matrix. The results suggested high performance of prediction. Identified predictor variables were aligned with previous research. The noble predictors found, such as ‘witnessed e-cigarette use in their household’ and ‘perception of their tobacco use’, could be used in public awareness or targeted e-cigarette and hookah youth education and for policymakers.

Introduction: Rapid increase in youth use of Electronic Nicotine Delivery Systems (ENDS) led the state and the federal governments to implement minimum-age policies to restrict minors’ access to vaping products. Limited success of the age restrictions fueled efforts to increase the distribution age of all tobacco products to 21 (ie, Tobacco 21 or T21 policies). With limited data on the T21 policies, the current study examines the prevalence of ENDS use and the perceptions about ENDS among youth in the pre- and post-policy-implementation periods for one of these bans in the state of Florida. Methods: This study conducted secondary analysis on the responses from the 2014 and 2015 Florida Youth Tobacco Survey, which collected cross-sectional data. Results: Compared to the data from spring of 2014, the minimum-age policy enacted on July 1, 2014 did not lead to a significant decrease in Florida’s high school and middle school students’ ever ENDS use (14.9% in 2014 vs 25.8% in 2015) and current ENDS use (7.5% in 2014 vs 12.4% in 2015). There was some ambiguity among students regarding the ENDS harm—more students in 2015 thought of ENDS as both equally (11.0% vs 7.7%) and less (32.4% vs 28%) harmful than cigarettes. There was a decrease in the proportion of students who were unsure about their answer to this question (51.5% vs 59.2%). Conclusions: Policy change alone may not be effective in shifting the trend of ENDS use among middle and high school students. Although students may know about some of the ENDS effects, many of them are still not aware about the harms. Interventions in school and in the community should be aiming to raise this awareness.

Background Due to the COVID-19 pandemic, telehealth resurfaced as a convenient efficient healthcare delivery method. Researchers indicate that Artificial Intelligence (AI) could further facilitate delivering quality care in telehealth. It is essential to find supporting evidence to use AI-assisted telehealth interventions in nursing. Objectives This scoping review focuses on finding users’ satisfaction and perception of AI-assisted telehealth intervention, performances of AI algorithms, and the types of AI technology used. Methods A structured search was performed in six databases, PubMed, CINAHL, Web of Science, OVID, PsycINFO, and ProQuest, following the guidance of the Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews. The quality of the final reviewed studies was assessed using the Medical Education Research Study Quality Instrument. Results Eight of the 41 studies published between 2017 and 2022 were included in the final review. Six studies were conducted in the United States, one in Japan, and one in South Korea. Four studies collected data from participants ( n = 3014). Two studies used image data ( n = 1986), and two used sensor data from smart homes to detect patients’ health events for nurses ( n = 35). The quality of studies implied moderate to high-quality study (mean = 10.1, range = 7.7–13.7). Two studies reported high user satisfaction, three assessed user perception of AI in telehealth, and only one showed high AI acceptability. Two studies revealed the high performance of AI algorithms. Five studies used machine learning algorithms. Conclusions AI-assisted telehealth interventions were efficient and promising and could be an effective care delivery method in nursing.