Background: Obesity prevalence has become one of the most prominent issues in global public health. Physical activity has been recognized as a key player in the obesity epidemic. Objectives: The objectives of this study are to (1) examine the relationship between physical activity and weight status and (2) assess the performance and predictive power of a set of popular machine learning and traditional statistical methods. Methods: National Health and Nutrition Examination Survey (NHANES, 2003 to 2006) data were used. A total of 7162 participants met our inclusion criteria (3682 males and 3480 females), with average age ranging from 48.6 (normal weight) to 52.1 years old (overweight). Eleven classifying algorithms—including logistic regression, naïve Bayes, Radial Basis Function (RBF), local k-nearest neighbors (k-NN), classification via regression (CVR), random subspace, decision table, multiobjective evolutionary fuzzy classifier, random tree, J48, and multilayer perceptron—were implemented and evaluated, and they were compared with traditional logistic regression model estimates. Results: With physical activity and basic demographic status, of all methods analyzed, the random subspace classifier algorithm achieved the highest overall accuracy and area under the receiver operating characteristic (ROC) curve (AUC). The duration of vigorous-intensity activity in one week and the duration of moderate-intensity activity in one week were important attributes. In general, most algorithms showed similar performance. Logistic regression was middle-ranking in terms of overall accuracy, sensitivity, specificity, and AUC among all methods. Conclusions: Physical activity was an important factor in predicting weight status, with gender, age, and race/ethnicity being less but still essential factors associated with weight outcomes. Tailored intervention policies and programs should target the differences rooted in these demographic factors to curb the increase in the prevalence of obesity and reduce disparities among sub-demographic populations.

Background: Social media platforms provide a valuable source of public health information, as one-third of US adults seek specific health information online. Many antitobacco campaigns have recognized such trends among youth and have shifted their advertising time and effort toward digital platforms. Timely evidence is needed to inform the adaptation of antitobacco campaigns to changing social media platforms. Objective: In this study, we conducted a content analysis of major antitobacco campaigns on Facebook using machine learning and natural language processing (NLP) methods, as well as a traditional approach, to investigate the factors that may influence effective antismoking information dissemination and user engagement. Methods: We collected 3515 posts and 28,125 associated comments from 7 large national and local antitobacco campaigns on Facebook between 2018 and 2021, including the Real Cost, Truth, CDC Tobacco Free (formally known as Tips from Former Smokers, where “CDC” refers to the Centers for Disease Control and Prevention), the Tobacco Prevention Toolkit, Behind the Haze VA, the Campaign for Tobacco-Free Kids, and Smoke Free US campaigns. NLP methods were used for content analysis, including parsimonious rule–based models for sentiment analysis and topic modeling. Logistic regression models were fitted to examine the relationship of antismoking message-framing strategies and viewer responses and engagement. Results: We found that large campaigns from government and nonprofit organizations had more user engagements compared to local and smaller campaigns. Facebook users were more likely to engage in negatively framed campaign posts. Negative posts tended to receive more negative comments (odds ratio [OR] 1.40, 95% CI 1.20-1.65). Positively framed posts generated more negative comments (OR 1.41, 95% CI 1.19-1.66) as well as positive comments (OR 1.29, 95% CI 1.13-1.48). Our content analysis and topic modeling uncovered that the most popular campaign posts tended to be informational (ie, providing new information), where the key phrases included talking about harmful chemicals (n=43, 43%) as well as the risk to pets (n=17, 17%). Conclusions: Facebook users tend to engage more in antitobacco educational campaigns that are framed negatively. The most popular campaign posts are those providing new information, with key phrases and topics discussing harmful chemicals and risks of secondhand smoke for pets. Educational campaign designers can use such insights to increase the reach of antismoking campaigns and promote behavioral changes.

Background: Although Pinterest has become a popular platform for distributing influential information that shapes users’ behaviors, the role of recipes pinned on Pinterest in these behaviors is not well understood. Objective: This study aims to explore the patterns of food ingredients and the nutritional content of recipes posted on Pinterest and to examine the factors associated with recipes that engage more users. Methods: Data were collected from Pinterest between June 28 and July 12, 2020 (207 recipes and 2818 comments). All samples were collected via 2 new user accounts with no search history. A codebook was developed with a raw agreement rate of 0.97 across all variables. Content analysis and natural language processing sentiment analysis techniques were employed. Results: Recipes using seafood or vegetables as the main ingredient had, on average, fewer calories and less sodium, sugar, and cholesterol than meat- or poultry-based recipes. For recipes using meat as the main ingredient, more than half of the energy was obtained from fat (277/490, 56.6%). Although the most followed pinners tended to post recipes containing more poultry or seafood and less meat, recipes with higher fat content or providing more calories per serving were more popular, having more shared photos or videos and comments. The natural language processing–based sentiment analysis suggested that Pinterest users weighted taste more heavily than complexity (225/2818, 8.0%) and health (84/2828, 2.9%). Conclusions: Although popular pinners tended to post recipes with more seafood or poultry or vegetables and less meat, recipes with higher fat and sugar content were more user-engaging, with more photo or video shares and comments. Data on Pinterest behaviors can inform the development and implementation of nutrition health interventions to promote healthy recipe sharing on social media platforms.

Anti-tobacco campaigns contributed to the great decline of adolescent cigarette smoking in the United States from 2000 to 2022. However, studies on the ways in which campaigns are designed and disseminated on social media to generate optimal impact are limited. We aim to examine the effect of various campaign designs implemented under different structures of social-network influencers on reducing tobacco use among youth in Virginia. An agent-based model (ABM) was deployed from bottom-up to project the influence of anti-tobacco media campaign intervention and social media influencers on students’ smoking decisions. High school students in ninth grade reporting never smoking were followed for 48 months through 12th grade. Simulation models assessed student smoking behaviors, accounting for potential interactions with assigned micro/macro factors, social-network structures, and interventions. We found that an anti-tobacco campaign is more likely to reduce smoking intensity than prevalence. A 10% increase in the state-wide campaign reach was associated with 1.31 fewer cigarettes consumed monthly [95% confidence interval (CI): 1.06–1.56], with the effects more substantial in the central and southwest regions of Virginia. For campaigns utilizing five social-media influencers per 1000 youth, a 10% increase in reach was associated with 2.60 fewer cigarettes consumed monthly (95% CI: 2.34–2.87), where the effect of the campaign reach was maximized at 15.13%. Our pioneer study suggests that engaging social media influencers in anti-tobacco social media campaigns is one potentially effective strategy for tobacco use control and prevention. Future research is needed to validate findings in other samples.

Objective: To examine dose-response associations between use of specific social media sites and the use of electronic cigarettes (e-cigarettes) and traditional cigarettes. Methods: This was a cross-sectional study of 298 first-year college students enrolled in the fall 2019 semester at a large state university. Heckman selection and Probit model were used to estimate associations between use of specific social media sites and e-cigarette/traditional cigarette use. Results: Each additional hour per day spent on Snapchat was associated with a 4.61% increase in the probability of lifetime e-cigarette use. In addition, among current e-cigarette users, more time spent on Snapchat was associated with more frequent e-cigarette use (marginal effects: 0.13, p = 0.001). Facebook, Twitter, Snapchat and Instagram were not associated with traditional cigarette smoking. Conclusion: Snapchat was the only major social media platform associated with both lifetime and current e-cigarette use.

Background and Objective: Chronic obstructive pulmonary disease (COPD) is the third leading cause of death in the United States. COPD is expensive to treat, whereas the quality of care is difficult to evaluate due to the high prevalence of multi-morbidity among COPD patients. In the US, the Hospital Readmissions Reduction Program (HRRP) was initiated by the Centers for Medicare and Medicaid Services to penalize hospitals for excessive 30-day readmission rates for six diseases, including COPD. This study examines the difference in 30-day readmission risk between COPD patients with and without comorbidities. Methods: In this retrospective cohort study, we used Cox regression to estimate the hazard ratio of 30-day readmission rates for COPD patients who had no comorbidity and those who had one, two or three, or four or more comorbidities. We controlled for individual, hospital and geographic factors. Data came from three sources: Healthcare Cost and Utilization Project (HCUP) State Inpatient Databases (SID), Area Health Resources Files (AHRF) and the American Hospital Association’s (AHA’s) annual survey database for the year of 2013. Results: COPD patients with comorbidities were less likely to be readmitted within 30 days relative to patients without comorbidities (aHR from 0.84 to 0.87, p < 0.05). In a stratified analysis, female patients with one comorbidity had a lower risk of 30-day readmission compared to female patients without comorbidity (aHR = 0.80, p < 0.05). Patients with public insurance who had comorbidities were less likely to be readmitted within 30 days in comparison with those who had no comorbidity (aHR from 0.79 to 0.84, p < 0.05). Conclusion: COPD patients with comorbidities had a lower risk of 30-day readmission compared with patients without comorbidity. Future research could use a different study design to identify the effectiveness of the HRRP.