OBJECTIVES: Over-the-counter (OTC) antibiotic use can cause antibiotic resistance, threatening global public health gains. To counter OTC use, this study used machine learning (ML) methods to identify predictors of OTC antibiotic use in rural Pune, India. METHODS: The features of OTC antibiotic use were selected using stepwise logistic, lasso, random forest, XGBoost, and Boruta algorithms. Regression and tree-based models with all confirmed and tentatively important features were built to predict the use of OTC antibiotics. Five-fold cross-validation was used to tune the models’ hyperparameters. The final model was selected based on the highest area under the curve (AUROC) with a 95% confidence interval (CI) and the lowest log-loss. RESULTS: In rural Pune, the prevalence of OTC antibiotic use was 35.9% (95% CI, 31.6 to 40.5). The perception that buying medicines directly from a medicine shop/pharmacy is useful, using antibiotics for eye-related complaints, more household members consuming antibiotics, and longer duration and higher doses of antibiotic consumption in rural blocks and other social groups were confirmed as important features by the Boruta algorithm. The final model was the XGBoost+Boruta model with 7 predictors (AUROC, 0.934; 95% CI, 0.891 to 0.978; log-loss, 0.279) log-loss. CONCLUSIONS XGBoost+Boruta, with 7 predictors, was the most accurate model for predicting OTC antibiotic use in rural Pune. Using OTC antibiotics for eye-related complaints, higher consumption of antibiotics and the perception that buying antibiotics directly from a medicine shop/pharmacy is useful were identified as key factors for planning interventions to improve awareness about proper antibiotic use.

OBJECTIVES: Hitherto regarded as a public health issue of well-heeled nations, overweight and obesity have emerged as a problem of concern in developing nations. Although social and demographic factors are equally important as proximal lifestyle factors affecting health, their role is neither well researched nor well understood. We conducted a novel study to determine the distribution, prevalence, and social and demographic determinants of overweight/obesity in Malawi.METHODS: A population-based, quantitative cross-sectional study using data from the Malawi Demographic and Health Survey (2015–2016) was conducted among non-pregnant women aged 18–49 years. A total of 6,443 women were included in the analysis. Overweight/obesity, defined as a body mass index (BMI) ≥25.0 kg/m² , was the main outcome variable. The analysis was done in SPSS version 20.0; after calculating descriptive statistics, bivariate and multivariate logistic regression was conducted to evaluate associations and determine odds.RESULTS: In total, 16.8% and 6.3% of women were overweight and obese, respectively (p<0.001). Overweight and obesity were more prevalent in urban than in rural areas. The BMI distribution among women varied across different background characteristics. Women from the Ngoni ethnicity were more likely to be overweight/obese than others (adjusted odds ratio [aOR], 1.54; 95% confidence interval [CI], 1.14 to 2.08). Socioeconomic status (SES) and the age of the respondent were highly significant determinants that were strongly associated with being overweight/obese. The richest women were 3 times more likely to be overweight/obese than the poorest (aOR, 3.30; 95% CI, 2.46 to 4.43).CONCLUSIONS: Overweight and obesity were highly prevalent and significantly associated with increasing SES, age, and being from the Ngoni ethnicity. Holistic interventions should also focus on improving social determinants in order to entirely curb the epidemic.
Adult ; Body Mass Index ; Cross-Sectional Studies ; Demography ; Developing Countries ; Female ; Health Surveys ; Humans ; Life Style ; Logistic Models ; Malawi ; Obesity ; Odds Ratio ; Overweight ; Prevalence ; Public Health ; Social Class ; Surveys and Questionnaires

OBJECTIVES: Hitherto regarded as a public health issue of well-heeled nations, overweight and obesity have emerged as a problem of concern in developing nations. Although social and demographic factors are equally important as proximal lifestyle factors affecting health, their role is neither well researched nor well understood. We conducted a novel study to determine the distribution, prevalence, and social and demographic determinants of overweight/obesity in Malawi. METHODS: A population-based, quantitative cross-sectional study using data from the Malawi Demographic and Health Survey (2015–2016) was conducted among non-pregnant women aged 18–49 years. A total of 6,443 women were included in the analysis. Overweight/obesity, defined as a body mass index (BMI) ≥25.0 kg/m² , was the main outcome variable. The analysis was done in SPSS version 20.0; after calculating descriptive statistics, bivariate and multivariate logistic regression was conducted to evaluate associations and determine odds. RESULTS: In total, 16.8% and 6.3% of women were overweight and obese, respectively (p<0.001). Overweight and obesity were more prevalent in urban than in rural areas. The BMI distribution among women varied across different background characteristics. Women from the Ngoni ethnicity were more likely to be overweight/obese than others (adjusted odds ratio [aOR], 1.54; 95% confidence interval [CI], 1.14 to 2.08). Socioeconomic status (SES) and the age of the respondent were highly significant determinants that were strongly associated with being overweight/obese. The richest women were 3 times more likely to be overweight/obese than the poorest (aOR, 3.30; 95% CI, 2.46 to 4.43). CONCLUSIONS Overweight and obesity were highly prevalent and significantly associated with increasing SES, age, and being from the Ngoni ethnicity. Holistic interventions should also focus on improving social determinants in order to entirely curb the epidemic.