Assessing acceptance and effects of child feeding counselling on nutritional status of children aged 6-23 months in a semi-urban community.

In Bangladesh, only 34 % of the children aged 18-23 months old are given minimum acceptable diets of complementary foods. Objective of the study was to find the effects of complementary feeding counselling on nutritional status among 6-23 months old children of poor families. This was a community-based randomised control trial. A total of 192 children in two groups were randomly selected. Nutrition education was given for a period of 4 months with post-intervention follow-up for 2 months. After 4 months of intervention, the difference in height for age Z score, weight for height Z score and weight for age Z score were significantly higher in the intervention group than in the control group (1·01 ± 0·31 v. 0·19 ± 0·01, P =< 0·001; 1·34 ± 0·15 v 0·72 ± 0·11, P =< 0·001; 1·5 ± 0·24 v. 0·62 ± 0·04, P =< 0·001). Mid-upper arm circumference Z score also improved in the intervention group than in the control group (0·95 ± 0·03 v. 0·57 ± 0·12, P =< 0·001). Morbidity of the children in the intervention group significantly reduced than in the control group (49 % v 80·20 %, P =< 0·001). Higher feeding frequency (3-4 times) (71·9 % v. 45·8 %) and energy intake increased in the intervention group than in the control group. Promotion of complementary feeding from the family foods can improve the nutritional status of 6-23 months old children of poor families within a short period.

An assessment of random forest technique using simulation study: illustration with infant mortality in Bangladesh.

We aimed to assess different machine learning techniques for predicting infant mortality (<1 year) in Bangladesh. The decision tree (DT), random forest (RF), support vector machine (SVM) and logistic regression (LR) approaches were evaluated through accuracy, sensitivity, specificity, precision, F1-score, receiver operating characteristics curve and k-fold cross-validation via simulations. The Boruta algorithm and chi-square ( χ 2 ) test were used for features selection of infant mortality. Overall, the RF technique (Boruta: accuracy = 0.8890, sensitivity = 0.0480, specificity = 0.9789, precision = 0.1960, F1-score = 0.0771, AUC = 0.6590; χ 2 : accuracy = 0.8856, sensitivity = 0.0536, specificity = 0.9745, precision = 0.1837, F1-score = 0.0828, AUC = 0.6480) showed higher predictive performance for infant mortality compared to other approaches. Age at first marriage and birth, body mass index (BMI), birth interval, place of residence, religion, administrative division, parents education, occupation of mother, media-exposure, wealth index, gender of child, birth order, children ever born, toilet facility and cooking fuel were potential determinants of infant mortality in Bangladesh. Study findings may help women, stakeholders and policy-makers to take necessary steps for reducing infant mortality by creating awareness, expanding educational programs at community levels and public health interventions.

Perceived stress, eating behavior, and overweight and obesity among urban adolescents.

BACKGROUND: WHO estimated 20% of adolescents (10-19 years) have mental health problems. We examined the prevalence and associated risk predictors of overweight/obesity and perceived stress using eating behaviors and physical activity among school-and-college-going urban adolescents in Bangladesh. METHODS: A cross-sectional study with a multistage sampling technique was employed to select 4609 adolescent students, aged 13-19 years, from all eight Bangladesh divisions during January-June 2019. Data were collected using a self-administered questionnaire containing Turconi Physical Activity Questionnaire (PAQ), Adolescent Stress Questionnaire (ASQ), Dutch Eating Behavior Questionnaire (DEBQ), and Anthropometric measurements. Logistic regression and different association measures assessed relationships among adolescent characteristics. RESULTS: The major 61.5% of adolescents were in moderate-to-extremely-severe levels of stress, 28.2% were overweight/obese, only 2.7% had a very active lifestyle, and 30.5% had a sedentary lifestyle. Perceived stress was positively and significantly correlated with eating behaviors and body mass index, whereas physical activity was significantly associated with the prevalence of overweight/obesity and high stress. The prevalence of overweight/obesity (53.8%) and high stress (52.5%) was higher in males. Adolescents' obesity was 2.212 times more likely who had a sedentary lifestyle (95% CI 1.377-3.552), 1.13 times more likely for those who had experienced stress due to school/leisure conflict (95% CI 1.051-1.222), and 1.634 times more likely for those who were tempted by restrained eating behavior (95% CI 1.495-1.786). CONCLUSION: Stress on secondary school-and-college-going students needs to be recognized, and strategies need to be developed to improve adolescents' mental health.

Prevalence and predicting factors of perceived stress among Bangladeshi university students using machine learning algorithms.

BACKGROUND: Stress-related mental health problems are one of the most common causes of the burden in university students worldwide. Many studies have been conducted to predict the prevalence of stress among university students, however most of these analyses were predominantly performed using the basic logistic regression (LR) model. As an alternative, we used the advanced machine learning (ML) approaches for detecting significant risk factors and to predict the prevalence of stress among Bangladeshi university students. METHODS: This prevalence study surveyed 355 students from twenty-eight different Bangladeshi universities using questions concerning anthropometric measurements, academic, lifestyles, and health-related information, which referred to the perceived stress status of the respondents (yes or no). Boruta algorithm was used in determining the significant prognostic factors of the prevalence of stress. Prediction models were built using decision tree (DT), random forest (RF), support vector machine (SVM), and LR, and their performances were evaluated using parameters of confusion matrix, receiver operating characteristics (ROC) curves, and k-fold cross-validation techniques. RESULTS: One-third of university students reported stress within the last 12 months. Students' pulse rate, systolic and diastolic blood pressures, sleep status, smoking status, and academic background were selected as the important features for predicting the prevalence of stress. Evaluated performance revealed that the highest performance observed from RF (accuracy = 0.8972, precision = 0.9241, sensitivity = 0.9250, specificity = 0.8148, area under the ROC curve (AUC) = 0.8715, k-fold accuracy = 0.8983) and the lowest from LR (accuracy = 0.7476, precision = 0.8354, sensitivity = 0.8250, specificity = 0.5185, AUC = 0.7822, k-fold accuracy = 07713) and SVM with polynomial kernel of degree 2 (accuracy = 0.7570, precision = 0.7975, sensitivity = 0.8630, specificity = 0.5294, AUC = 0.7717, k-fold accuracy = 0.7855). Overall, the RF model performs better and authentically predicted stress compared with other ML techniques, including individual and interaction effects of predictors. CONCLUSION: The machine learning framework can be detected the significant prognostic factors and predicted this psychological problem more accurately, thereby helping the policy-makers, stakeholders, and families to understand and prevent this serious crisis by improving policy-making strategies, mental health promotion, and establishing effective university counseling services.

Factors associated with coverage of vitamin a supplementation among Bangladeshi children: mixed modelling approach.

BACKGROUND: Vitamin A deficiency (VAD) is a prominent and widespread public health problem in developing countries, including Bangladesh. About 2% of all deaths among under-five children are attributable to VAD. Evidence-based information is required to understand the influential factors to increase vitamin A supplementation (VAS) coverage and reduce VAD. We investigated the potential factors affecting VAS coverage and its significant predictors among Bangladeshi children aged 6 to 59 months using the VAS clustered data extracted from the latest Bangladesh Demographic and Health Survey 2014. METHODS: Data were analysed using mixed logistic regression (MLR) modelling approach in the generalised linear mixed model framework. The MLR model performs better than logistic regression for analysing the clustered data because of its minimum Akaike information criterion value. The likelihood ratio test showed that the variance component was significant. Therefore, the clustering effect among children was inevitable to use. RESULTS: VAS coverage among under-five children was 63.6%, which is not optimal and below the WHO's recommendation and the country's target of 90%. Children aged 25 to 36 months (AOR = 2.07, 95% CI: 1.711 to 2.513), who had higher educated mothers (AOR = 1.37, p = 0.033, 95% CI: 1.026-1.820) and fathers (AOR = 1.32, p = 0.027, 95% CI: 1.032-1.683), whose mothers had media exposure (AOR = 1.22, p = 0.006, 95% CI: 1.059-1.408) and NGO membership (AOR = 1.24, p = 0.002, 95% CI: 1.089-1.422) were more likely to consume VAS. CONCLUSION: The relevant authorities should create proactive awareness programs for highly vulnerable local communities, specifically targeted to educate the children's mothers about the necessity and benefits of childhood nutrition.