Search

BACKGROUND: Although prior studies have established the association of asthma with smoking and obesity, literature on difference-in-differences analyses involving sexual identity is sparse. Therefore, this study aimed to examine the between and within sexual identity-group differences in asthma prevalence among individuals who smoke and are obese. METHODS: We aggregated the 2017-2019 National Survey on Drug Use and Health data on adults (N = 128,319) to perform weighted multivariable logistic regression analysis and marginal estimates and marginsplot to determine asthma prevalence by sexual identity and the status of smoking and obesity. RESULTS: About 66% of the study population reported having asthma. Among the individuals with asthma, 42% were obese, 10% were daily cigarette smokers, and 6% identified as bisexual persons. Lesbian/gay daily smokers (86%) or former smokers (75%) had a higher probability of having asthma than bisexual (daily smokers = 78% vs former smokers = 72%) and heterosexual (daily smokers = 68% vs former smokers = 65%) persons. Within each sexual identity subgroup, daily smokers (68-86%) had the highest probability of asthma. Obese bisexual (73%) or lesbian/gay (72%) persons had higher probabilities of having asthma than heterosexual persons (69%). Obese (73%) or overweight (72%) bisexual (compared to normal weight = 70% or underweight = 51%) and obese (69%) or overweight (65%) heterosexual (compared to normal weight = 62% or underweight = 57%) persons had the highest probabilities of having asthma within their groups, whereas overweight persons (overweight = 81% vs underweight = 79%, normal weight = 78%, and obese = 72%) had the highest probabilities within lesbian/gay persons. CONCLUSIONS: Smoking and obesity show heightened odds for asthma, with significant odds for sexual minorities in asthma diagnosis relative to heterosexuals. These findings provide formative information for future longitudinal and experimental studies to explore these mechanisms of asthma risks among sexual and gender minorities. [ABSTRACT FROM AUTHOR]

Objective: Child undernutrition is a global public health problem with serious implications. In this study, we estimate predictive algorithms for the determinants of childhood stunting by using various machine learning (ML) algorithms.Design: This study draws on data from the Ethiopian Demographic and Health Survey of 2016. Five ML algorithms including eXtreme gradient boosting, k-nearest neighbours (k-NN), random forest, neural network and the generalised linear models were considered to predict the socio-demographic risk factors for undernutrition in Ethiopia.Setting: Households in Ethiopia.Participants: A total of 9471 children below 5 years of age participated in this study.Results: The descriptive results show substantial regional variations in child stunting, wasting and underweight in Ethiopia. Also, among the five ML algorithms, xgbTree algorithm shows a better prediction ability than the generalised linear mixed algorithm. The best predicting algorithm (xgbTree) shows diverse important predictors of undernutrition across the three outcomes which include time to water source, anaemia history, child age greater than 30 months, small birth size and maternal underweight, among others.Conclusions: The xgbTree algorithm was a reasonably superior ML algorithm for predicting childhood undernutrition in Ethiopia compared to other ML algorithms considered in this study. The findings support improvement in access to water supply, food security and fertility regulation, among others, in the quest to considerably improve childhood nutrition in Ethiopia. [ABSTRACT FROM AUTHOR]