This paper aims to demonstrate the importance of studying interactions among various sociodemographic risk factors of childhood stunting in Bangladesh with the help of an interpretable machine learning method. Data used for the analyses are extracted from the Bangladesh Demographic and Health Survey (BDHS) 2014 and pertain to a sample of 6,170 under-5 children. Social and economic determinants such as wealth, mother’s decision making on healthcare, parental education are considered in addition to geographic divisions and common demographic characteristics of children including age, sex and birth order. A classification tree was first constructed to identify important interaction-based rules that characterize children with different profiles of risk for stunting. Then binary logistic regression models were fitted to measure the importance of these interactions along with the individual risk factors. Results revealed that, as individual factors, living in Sylhet division (OR: 1.57; CI: 1.26–1.96), being an urban resident (OR: 1.28; CI: 1.03–1.96) and having working mothers (OR: 1.21; CI: 1.02–1.44) were associated with higher likelihoods of childhood stunting, whereas belonging to the richest households (OR: 0.56; CI: 0.35–0.90), higher BMI of mothers (OR: 0.68 CI: 0.56–0.84) and mothers’ involvement in decision making about children’s healthcare with father (OR: 0.83, CI: 0.71–0.97) were linked to lower likelihoods of stunting. Importantly however, risk classifications defined by the interplay of multiple sociodemographic factors showed more extreme odds ratios (OR) of stunting than single factor ORs. For example, children aged 14 months or above who belong to poor wealth class, have lowly educated fathers and reside in either Dhaka, Barisal, Chittagong or Sylhet division are the most vulnerable to stunting (OR: 2.52, CI: 1.85–3.44). The findings endorse the need for tailored-intervention programs for children based on their distinct risk profiles and sociodemographic characteristics.

Despite a decrease in the prevalence of low birth weight (LBW) over time, its ongoing significance as a public health concern in Bangladesh remains evident. Low birth weight is believed to be a contributing factor to infant mortality, prolonged health complications, and vulnerability to non-communicable diseases. This study utilizes nationally representative data from the Multiple Indicator Cluster Surveys (MICS) conducted in 2012-2013 and 2019 to explore factors associated with birth weight. Modeling birth weight data considers interactions among factors, clustering in data, and spatial correlation. District-level maps are generated to identify high-risk areas for LBW. The average birth weight has shown a modest increase, rising from 2.93 kg in 2012-2013 to 2.96 kg in 2019. The study employs a regression tree, a popular machine learning algorithm, to discern essential interactions among potential determinants of birth weight. Findings from various models, including fixed effect, mixed effect, and spatial dependence models, highlight the significance of factors such as maternal age, household head's education, antenatal care, and few data-driven interactions influencing birth weight. District-specific maps reveal lower average birth weights in the southwestern region and selected northern districts, persisting across the two survey periods. Accounting for hierarchical structure and spatial autocorrelation improves model performance, particularly when fitting the most recent round of survey data. The study aims to inform policy formulation and targeted interventions at the district level by utilizing a machine learning technique and regression models to identify vulnerable groups of children requiring heightened attention.

This paper examines the current state of food insecurity in Bangladesh and its socio-economic drivers using data from the latest Household Income and Expenditure Survey (HIES 2022). Unlike previous studies that relied on less precise measures of food insecurity, such as food expenditure, diversity, and calorie intake, this study employs the internationally recognized Food Insecurity Experience Scale (FIES) and Rasch model-based thresholds to classify households as food secure or insecure. Multilevel logistic regression is used to identify significant predictors of moderate and severe food insecurity, considering the hierarchical structure of the data, with households nested within geographical clusters. Key factors found to be significantly associated with food security include the wealth index, land ownership, education of the household head, family size, remittance income and exposure to shocks. A classification tree, a popular machine learning method, is also applied to explore important interactions among these determinants. The tree analysis confirms the importance of several regression-based predictors and identifies households at the highest risk of food insecurity through variable interactions. Factors such as poverty, lack of land ownership, low education levels, and high dependency ratios collectively increase a household's vulnerability to moderate food insecurity to around 51% while the national prevalence is 19%. District-level maps of food insecurity prevalence reveal significant regional disparities, underscoring the need for targeted, district-specific interventions to effectively combat food insecurity. More broadly, policies promoting education and family planning, training in better shock management, and facilitating remittance flows through simplified processes may contribute to addressing the food insecurity challenge.

Hands-on gardening is linked with healthy eating behaviors, increased outdoor activities, and overall well-being, all contributing factors to preventing obesity. Although these positive associations are widely established for adults and school-aged children, little evidence can be found on how such relationships may extend to early childhood, especially in the preschool years (3–5 years). One recent study conducted in North Carolina (NC) showed that participating in hands-on gardening significantly increased preschoolers’ accurate identification of fruits and vegetables (FV) and FV consumption compared to children who did not participate in hands-on gardening, but no association was found between participation in hands-on gardening and the children’s liking (eating preferences) of FV. FV identification and liking during the early years may lead to lifelong healthy eating behaviors and preferences, making hands-on gardening a critical health intervention in early childhood environments, especially in childcare centers where a majority of the 13 million children in the United States between the ages of 0 and 5 spend most of their waking hours. This research aimed to investigate how hands-on gardening in childcare centers may impact preschoolers’ (3–5 years old) FV knowledge (identification) and liking in a semi-arid climate zone with a high concentration of Hispanic families by conducting experimental research with eight childcare centers and one hundred forty-nine children (n = 149) in Lubbock County, located in West Texas. The findings showed changes in average liking scores are generally positive in the experimental group of children who participated in hands-on gardening (compared to the control non-gardening group), implying an improved liking. The findings indicate that the benefits of hands-on gardening in childcare centers for enhancing healthy eating preferences are evident even in a semi-arid climate zone, where high temperatures and limited rainfall present significant gardening challenges. This research underscores the importance of integrating hands-on gardening into childcare programs, highlighting its potential as an effective obesity prevention strategy not only within the US but also in other regions with similar environmental constraints.

Hands-on gardening is linked with healthy eating behaviors, increased outdoor activities, and overall well-being. Although these positive associations are widely established for adults and school-agers, little evidence can be found on how such relationships may extend to early childhood, especially in the preschool years (3-5 years). One recent study conducted in North Carolina (NC) showed that participating in hands-on gardening significantly increased preschoolers’ accurate identification of fruits and vegetables (FV) and FV consumption compared to children who did not participate in hands-on gardening, but no association was found between participation in hands-on gardening and children’s liking (eating preferences) of FV. FV identification and liking during the early years may lead to lifelong healthy eating behaviors and preferences, making hands-on gardening a critical health intervention in early childhood environments, especially in childcare centers where a majority of the 13 million children in the United States between the ages of 0 and 5 spend most of their waking hours. This research aimed to investigate how hands-on gardening in childcare centers may impact preschoolers’ (3-5 years old) FV knowledge (identification) and liking in a semi-arid climate zone with a high concentration of Hispanic families by conducting experimental research with eight childcare centers and one hundred forty-nine children (n=149) in Lubbock County located in West Texas. Findings showed changes in average liking scores are generally positive in the experiment group of children who participated in hands-on gardening (compared to the control non-gardening group), implying improved liking. The findings indicate that the benefits of hands-on gardening in childcare centers for enhancing healthy eating preferences are evident even in a semi-arid climate zone, where high temperatures and limited rainfall present significant gardening challenges. This research underscores the importance of integrating hands-on gardening into childcare programs, highlighting its potential as an effective obesity prevention strategy not only within the U.S. but also in other regions with similar environmental constraints.