Trend of risk and correlates of under-five child undernutrition in Bangladesh: an analysis based on Bangladesh Demographic and Health Survey data, 2007-2017/2018.

OBJECTIVES: The objectives of this study are to identify the trend of undernutrition risk among under-five children (U5C) in Bangladesh and the trend of its correlates. DESIGN: Multiple cross-sectional data sets from different time points were used. SETTING: Nationally representative Bangladesh Demographic and Health Surveys (BDHSs) were conducted in 2007, 2011, 2014 and 2017/2018. PARTICIPANTS: In the BDHSs, the sample sizes for ever-married women (age: 15-49 years) were 5300 in 2007, 7647 in 2011, 6965 in 2014 and 7902 in 2017/2018. OUTCOMES: Extant indicators of undernutrition (stunted, wasted and underweight) have been considered as the outcome variables. MATERIALS AND METHODS: Descriptive statistics, bivariate analysis and factor loadings from factor analysis have been used to determine the prevalence of undernutrition over the years and find the trend of risk and its correlates. RESULTS: Risks of stunting among the U5C were 41.70%, 40.67%, 36.57% and 31.14%; that of wasting were 16.94%, 15.48%, 14.43% and 8.44%; and that of underweight were 39.79%, 35.80%, 32.45% and 22.46% in 2007, 2011, 2014 and 2017/2018, respectively. From the factor analysis, it has been found that the top five potential correlates of undernutrition are the wealth index, the education of the father and mother, the frequency of antenatal visits during pregnancy, the father's occupation and/or the type of place of residence in the last four consecutive surveys. CONCLUSION: This study helps us gain a better understanding of the impact of the top correlates on child undernutrition. To accelerate the reduction of child undernutrition more by 2030, Government and non-government organisations should focus on improving education and household income-generating activities among poor households and raising awareness among women about the importance of receiving antenatal care during pregnancy.

Predicting the risk of hypertension using machine learning algorithms: A cross sectional study in Ethiopia.

BACKGROUND AND OBJECTIVES: Hypertension (HTN), a major global health concern, is a leading cause of cardiovascular disease, premature death and disability, worldwide. It is important to develop an automated system to diagnose HTN at an early stage. Therefore, this study devised a machine learning (ML) system for predicting patients with the risk of developing HTN in Ethiopia. MATERIALS AND METHODS: The HTN data was taken from Ethiopia, which included 612 respondents with 27 factors. We employed Boruta-based feature selection method to identify the important risk factors of HTN. The four well-known models [logistics regression, artificial neural network, random forest, and extreme gradient boosting (XGB)] were developed to predict HTN patients on the training set using the selected risk factors. The performances of the models were evaluated by accuracy, precision, recall, F1-score, and area under the curve (AUC) on the testing set. Additionally, the SHapley Additive exPlanations (SHAP) method is one of the explainable artificial intelligences (XAI) methods, was used to investigate the associated predictive risk factors of HTN. RESULTS: The overall prevalence of HTN patients is 21.2%. This study showed that XGB-based model was the most appropriate model for predicting patients with the risk of HTN and achieved the accuracy of 88.81%, precision of 89.62%, recall of 97.04%, F1-score of 93.18%, and AUC of 0. 894. The XBG with SHAP analysis reveal that age, weight, fat, income, body mass index, diabetes mulitas, salt, history of HTN, drinking, and smoking were the associated risk factors of developing HTN. CONCLUSIONS: The proposed framework provides an effective tool for accurately predicting individuals in Ethiopia who are at risk for developing HTN at an early stage and may help with early prevention and individualized treatment.

Predicting the risk of diabetic retinopathy using explainable machine learning algorithms.

BACKGROUND AND OBJECTIVE: Diabetic retinopathy (DR) is a global health concern among diabetic patients. The objective of this study was to propose an explainable machine learning (ML)-based system for predicting the risk of DR. MATERIALS AND METHODS: This study utilized publicly available cross-sectional data in a Chinese cohort of 6374 respondents. We employed boruta and least absolute shrinkage and selection operator (LASSO) based feature selection methods to identify the common predictors of DR. Using the identified predictors, we trained and optimized four widly applicable models (artificial neural network, support vector machine, random forest, and extreme gradient boosting (XGBoost) to predict patients with DR. Moreover, shapely additive explanation (SHAP) was adopted to show the contribution of each predictor of DR in the prediction. RESULTS: Combining Boruta and LASSO method revealed that community, TCTG, HDLC, BUN, FPG, HbAlc, weight, and duration were the most important predictors of DR. The XGBoost-based model outperformed the other models, with an accuracy of 90.01%, precision of 91.80%, recall of 97.91%, F1 score of 94.86%, and AUC of 0.850. Moreover, SHAP method showed that HbA1c, community, FPG, TCTG, duration, and UA1b were the influencing predictors of DR. CONCLUSION: The proposed integrating system will be helpful as a tool for selecting significant predictors, which can predict patients who are at high risk of DR at an early stage in China.

Socioeconomic inequality in the prevalence of low birth weight and its associated determinants in Bangladesh.

BACKGROUND AND OBJECTIVE: Low birth weight (LBW) is a major risk factor of child mortality and morbidity during infancy (0-3 years) and early childhood (3-8 years) in low and lower-middle-income countries, including Bangladesh. LBW is a vital public health concern in Bangladesh. The objective of the research was to investigate the socioeconomic inequality in the prevalence of LBW among singleton births and identify the significantly associated determinants of singleton LBW in Bangladesh. MATERIALS AND METHODS: The data utilized in this research was derived from the latest nationally representative Bangladesh Demographic and Health Survey, 2017-18, and included a total of 2327 respondents. The concentration index (C-index) and concentration curve were used to investigate the socioeconomic inequality in LBW among the singleton newborn babies. Additionally, an adjusted binary logistic regression model was utilized for calculating adjusted odds ratio and p-value (<0.05) to identify the significant determinants of LBW. RESULTS: The overall prevalence of LBW among singleton births in Bangladesh was 14.27%. We observed that LBW rates were inequitably distributed across the socioeconomic groups (C-index: -0.096, 95% confidence interval: [-0.175, -0.016], P = 0.029), with a higher concentration of LBW infants among mothers living in the lowest wealth quintile (poorest). Regression analysis revealed that maternal age, region, maternal education level, wealth index, height, age at 1st birth, and the child's aliveness (alive or died) at the time of the survey were significantly associated determinants of LBW in Bangladesh. CONCLUSION: In this study, socioeconomic disparity in the prevalence of singleton LBW was evident in Bangladesh. Incidence of LBW might be reduced by improving the socioeconomic status of poor families, paying special attention to mothers who have no education and live in low-income households in the eastern divisions (e.g., Sylhet, Chittagong). Governments, agencies, and non-governmental organizations should address the multifaceted issues and implement preventive programs and policies in Bangladesh to reduce LBW.

Tobacco control policies to promote awareness and smoke-free environments in residence and workplace to reduce passive tobacco smoking in Bangladesh and its correlates.

BACKGROUND: Bangladesh is one of the highest tobacco consuming countries in the world, with reported 21.2% of the population as daily smokers, 24.3% as smokeless tobacco users, and 36.3% as adult passive smoker. Given the high prevalence and established harmful effects of passive tobacco smoking, this study aimed to estimate of pattern of smoking policies in residential and work place, and to identify the associated socio-economic and demographic correlates in Bangladesh. DATA AND METHODS: Secondary data of sample size 9629 collected by the Global Adult Tobacco Survey (GATS) 2010 has been used. Along with descriptive analysis, binary logistic regression model has been used to analyze the socio-demographic and economic correlates to tobacco smoking policy. RESULTS: The prevalence of male and female passive tobacco smokers was 74.3% and 25.8% respectively. Among the passive tobacco smokers, 22.2% reported that smoking was allowed at their home and 29.8% reported that there was no such smoking policy at their home. Alternatively, 26.0% passive tobacco smokers reported that smoking was allowed and 27.5% reported that there was no such smoking policy at their work place. Logistic regression analysis indicated that for tobacco smokers group, the odds of allowing smoking at home was 4.85 times higher than the non-smoker respondent (OR = 4.85, 95% CI = 4.13, 5.71), 1.18 times more likely to be allowed at home in rural areas than urban areas (OR = 1.18, 95% CI = 1.06,1.32) and less for college/university completed and (or) higher educated respondent than no formal schooling (OR = 0.35, 95% CI = 0.24, 0.52). On the other hand, smoking was 1.70 times more likely to be allowed at work place for tobacco smokers than their counter part respondent (OR = 1.70, 95% CI = 1.36, 2.14) and was less likely to be allowed for college/university completed and (or) higher educated respondent (OR = 0.26, 95% CI = 0.14, 0.45) than respondent with no formal schooling. CONCLUSION: To reduce the passive smoking, lower educated people and people in urban areas should advocate more about the adverse effect of active and passive tobacco smoking. Also, smoking policy should reform introducing smoking zone at work places and residential buildings.

Pharmacokinetics, tissue residue and plasma protein binding of ofloxacin in goats.

Ofloxacin was administered to six male goats intravenously (5 mg/kg) to determine its kinetic behavior, tissue residue, in vitro plasma protein binding and to compute a rational dosage regimen. The concentration of ofloxacin in plasma and tissue samples collected at prescheduled time were estimated by using HPLC. The pharmacokinetic parameters were determined by non-compartmental model and plasma protein binding was estimated by equilibrium dialysis technique. The therapeutic concentration (> or =0.5 microg/ml) was maintained up to 36 h and the initial concentration at 2.5 min (14.76 +/- 0.47 microg/ml) declined to 0.05 +/- 0.03 microg/ml at 96 h with a secondary peak (0.64 +/- 0.15 microg/ml) at 24 h. The mean AUC, AUMC, t1/2, MRT, Cl and Vd were calculated to be 58.94 +/- 19.43 microg x h/ml, 1539.57 +/- 724.69 microg x h2/ml, 15.58 +/- 1.87 h, 22.46 +/- 2.71 h, 135.60 +/- 31.12 ml/h/kg and 2.85 +/- 0.74 L/kg respectively. Significantly high concentration of drug was detected in different tissues after 24 h of intravenous dosing of 5 mg/kg, at 24 h interval for 5 days. The in vitro plasma protein binding of ofloxacin was found to be 15.28 +/- 0.94%. Based on these kinetic parameters, a loading dose of 5 mg/kg followed by the maintenance dose of 3 mg/kg at 24 h dosing interval by intravenous route is recommended.