Age patterns in overweight and wasting prevalence of under 5-year-old children from low- and middle-income countries

Unlocking insights: Using machine learning to identify wasting and risk factors in Egyptian children under 5

INTRODUCTION

Malnutrition, particularly wasting, continues to be a significant public health issue among children under five years in Egypt. Despite global advancements in child health, the prevalence of wasting remains a critical concern. This study employs machine learning techniques to identify and analyze the determinants of wasting in this population.

AIM

To evaluate the prevalence of wasting among children under five years in Egypt and identify key factors associated with wasting using machine learning models.

METHODS

This study is based on secondary data sourced from the Demographic and Health Surveys (DHS), conducted in 2005, 2008, and 2014. Six machine learning classifiers (XGBoost, Logistic Regression, Random Forest, Gradient Boosting, K-Nearest Neighbor, and Decision Tree) were applied to the dataset. The study included children under five years of age, focusing on nutritional status, maternal health, and socio-economic factors. The dataset was cleaned, preprocessed, encoded using one-hot encoding, and split into training (70%) and test (30%) sets. Additionally, k-fold cross-validation and the StandardScaler function from Scikit-learn were used. Performance metrics such as accuracy, precision, recall, F1 score, and ROC-AUC were used to evaluate and compare the algorithms.

RESULTS

It was observed that 76.2% of the children in the dataset have normal nutritional status. Furthermore, 5.2% were found to be suffering from wasting (1.7% experiencing severe wasting and 3.5% moderate wasting), with notable regional disparities. The XGBoost model outperformed other models. Its efficiency metrics include an accuracy of 94.8%, precision of 94.7%, recall of 94.7%, F1 score of 94.7%, and an ROC-AUC of 99.4%. These results indicate that XGBoost was highly effective in predicting wasting.

CONCLUSION

Machine learning techniques, particularly XGBoost, show significant potential for improving the classification of nutritional status and addressing wasting among children in Egypt. However, the limitations in simpler models highlight the need for further research to refine predictive tools and develop targeted interventions. Addressing the identified determinants of wasting can contribute to more effective public health strategies.

Childhood wasting and associated factors in Africa: evidence from standard demographic and health surveys from 35 countries

INTRODUCTION

Child malnutrition remains a critical public health challenge globally. Childhood wasting, a severe form of malnutrition, indicates acute undernutrition, leading to significant loss of muscle and fat tissue. The World Health Organization's Global Nutrition Target aims to reduce childhood wasting to less than 5% in over half of low- and middle-income countries by 2025. The enduring hunger crisis in Africa is a complex issue that demands our continuous commitment, innovative solutions, and coordinated efforts. This study aims to assess the prevalence and associated factors of childhood wasting in Africa.

METHOD

This study conducted a secondary analysis of demographic and health survey datasets from 2010 to 2022 in 35 African countries. A total of 212,715 children under the age of 5 years were included, using a weighted sample. We employed a mixed-effects model to evaluate the factors associated with childhood wasting. The significance of the fixed effects was assessed using the adjusted odds ratio (AOR) and the corresponding 95% confidence interval.

RESULT

The prevalence of childhood wasting in Africa was estimated to be 7.16% (95% CI: 7.05-7.27). Several factors were significantly associated with childhood wasting, including the child's age, male gender, birth weight, maternal education level, wealth index, lack of antenatal care (ANC) visits, home delivery, multiple gestational births, and rural residence.

CONCLUSION

Childhood wasting in Africa exceeds the global target set for 2025, which aims to reduce it to less than 5%. To address this critical issue, educating mothers without formal education and rural residents about antenatal care visits, institutional delivery, and proper child feeding practices is essential. Moreover, a renewed focus on tackling the multifaceted factors of undernutrition, strengthening health systems, and implementing evidence-based interventions tailored to the local context is crucial for achieving meaningful and sustained reductions in wasting prevalence across the region.

Malnutrition in infants aged 6-23 months in China's poorest rural counties from 2016 to 2021: cross sectional study

OBJECTIVES

To assess trends and differences in child malnutrition by population subgroups among infants aged 6-23 months in China's poorest rural counties.

DESIGN

Six consecutive cross sectional surveys were conducted annually.

SETTING

The study was conducted in 116 counties in 19 provinces from 2016 to 2021, representing China's 832 poorest counties.

PARTICIPANTS

A total of 210 088 participants were selected through a multistage cluster sampling procedure; all participants were infants aged 6-23 months.

MAIN OUTCOME MEASURES

Prevalence of anaemia, stunting, wasting, overweight, and growth status in children (measured by length-for-age and weight-for-length z scores).

RESULTS

Four main malnutrition forms were prevalent in 2016: anaemia (prevalence 18.3%), stunting (7.5%), wasting (4.7%), and overweight (3.1%). The prevalence of any two coexisting malnutrition forms was low. All four forms of malnutrition decreased from 2016 to 2021. Anaemia decreased by more than half, with an annual reduction rate of 9.11% (95% confidence interval (CI) 4.83% to 13.20%). Stunting was reduced by over a third, with an annual reduction rate of 10.44% (7.56% to 13.22%), which is faster than the World Health Organization's target of 3.9%. Differences in child growth by county gross domestic product quarters were small and decreased over time, but growth differences related to education persisted. Infants whose mothers completed education up to primary school level had approximately twice the risk of stunting (adjusted rate ratio 2.29 (95% CI 1.87 to 2.81)) and wasting (1.73 (1.40 to 2.13)) compared with children whose mothers had an education level of a college degree or above. Boys had poorer growth and higher anaemia than did girls. For all outcomes, differences related to sex and education were greatest at 6 months of age.

CONCLUSIONS

Education related inequalities in growth of infants persists, with these differences particularly affecting children whose mothers completed education only up to primary school level.

Family economic trajectories and body mass index in Indonesia: Evidence from the Indonesian Family Life Surveys 2 to 5

Indonesia faces the double burdens of childhood obesity and malnutrition. A family's socioeconomic status has been suggested to be one of the most influential factors contributing to childhood nutritional problems. This study aimed to: 1) identify the distinct trajectories of family economics; and 2) assess whether a family's economic trajectory influences children's body mass index (BMI). We analyzed trajectory patterns of family economic levels from 1997 to 2015 among 846 children aged under 3 years in 1997 using data from Indonesian Family Life Surveys. Trajectory patterns were identified with Group-Based Trajectory Modeling using the traj plug-in in STATA software. The BMI was classified according to 2007 World Health Organization growth standards. Adjusted relative risk ratios (aRRRs) of family economic level trajectories and children's BMI were calculated using multinomial logistic regressions. We identified three distinct trajectories of family economic level: stable poorest, stable middle, and increasing richest. In the total sample, there were no significant relationships between a family's income trajectory and children's BMI in the adjusted models. A significant relationship existed for male children, but not for female children, of compared to the poorest family trajectory group, male children in the increasing richest trajectory group were more likely to be overweight/obese (aRRR 6.1, 95% confidence interval: 1.22-30.62) after adjusting for age and BMI. The present results highlight the importance of early interventions to minimize the potential adverse impacts of excessive BMI later in adulthood.

Shared correlates of maternal and childhood overweight in Cameroon: a cross-sectional analysis of demographic and health survey data

BACKGROUND

Overweight parents are likelier to bear overweight babies, who are likelier to grow into overweight adults. Understanding the shared risks of being overweight between the mother-child dyad is essential for targeted life course interventions. In this study, we aimed to identify such risk factors in Cameroon.

METHODS

We conducted secondary data analysis using Cameroon's 2018 Demographic and Health Surveys. We used weighted multilevel binary logistic regressions to examine individual, household, and community correlates of maternal (15-49 years) and child (under five years) overweight.

RESULTS

We retained 4511 complete records for childhood and 4644 for maternal analysis. We found that 37% [95%CI:36-38%] of mothers and 12% [95%CI:11-13%] of children were overweight or obese. Many environmental and sociodemographic factors were positively associated with maternal overweight, namely urban residence, wealthier households, higher education, parity and being a Christian. Childhood overweight was positively associated with a child being older and a mother being overweight, a worker, or a Christian. Therefore, only religion affected both mothers overweight (aOR: 0.71[95%CI:0.56-0.91]) and childhood overweight (aOR 0.67[95%CI: 0.5-0.91]). Most of the potentially shared factors only indirectly affected childhood overweight through maternal overweight.

CONCLUSION

Besides religion, which affects both mothers and childhood overweight (with the Muslim faith being protective), much of childhood overweight is not directly explained by many of the observed determinants of maternal overweight. These determinants are likely to influence childhood overweight indirectly through maternal overweight. Extending this analysis to include unobserved correlates such as physical activity, dietary, and genetic characteristics would produce a more comprehensive picture of shared mother-child overweight correlates.

Nutritional Status of Underprivileged Indian Children and Youth with Type-1 Diabetes - A Multicentre Study

Background

India has the highest number of prevalent type-1 diabetes (T1D) cases in the under-20-year age population. Data on the anthropometry of underprivileged Indian children with T1D are scarce. In economically disadvantaged countries like India, poor growth in patients with T1D is a major concern due to limited accessibility and affordability. Besides, due to the double burden of malnutrition, the prevalence of obesity is increasing mirroring the global trends, which may lead to the development of insulin resistance.

Objectives

This study aims to assess the prevalence of malnutrition in Indian children and youth with T1D and to identify the determinants of short stature.

Methods

A registry-based cross-sectional analysis of data collected from various centres across India enrolled in the Changing Diabetes in Children (CDiC) programme.

Results

We observed that 6.4% were undernourished (3.4% severe undernutrition) and 17.7% (overweight 13.2%) had combined overweight/obesity. 21.2% of participants had short stature (adjusted for mid-parental height) with 7.4% cases of familial short stature. Longer duration of illness and insulin requirement were significant positive predictors of short stature while glycaemic control, insulin regimen and mid-parental height did not have a significant relationship with short stature. Participants on basal-bolus regimen had significantly higher insulin requirements and better glycaemic control than the ones on mixed-split regimen.

Conclusion

We report that around one-fifth of children and youth with T1D were overweight/obese and around a fourth were stunted, especially those with longer duration of diabetes and higher insulin requirements. Close monitoring of anthropometric parameters is necessary for all children with T1D to optimize growth and nutrition.

Child wasting before and after age two years: A cross-sectional study of 94 countries

BACKGROUND

Wasting reflects infections and poor nutrition and affects almost 50 million children at any given time. Wasting comes with immediate risk of mortality and increased risks for long-term negative consequences for development. Children under two are particularly sensitive to undernutrition and infections. We estimated the age patterning in wasting prevalence.

METHODS

We calculated wasting prevalence and used Poisson regression models to estimate prevalence ratios comparing prevalence in children under and over two years using data from Demographic and Health Surveys and Multiple Indicator Cluster Surveys from 94 mostly low- and middle-income countries, including 804,172 children under five, born to a nationally representative sample of women 15-49 years old. Wasting prevalence was defined as the percentage of children with weight-for-height below -2 z-score from the median of the WHO 2006 growth standard.

FINDINGS

Wasting prevalence for children under two was 14% (95% CI: 13, 14) while it was 9% (95% CI: 9, 9) for children 2-4 years old-leading to a prevalence ratio of 0·66 (95% CI: 0·64, 0·67) in our pooled sample. Prevalence ratios were less than one, indicating lower prevalence in children over two, in 87 countries and statistically significantly lower than one at a 5% level (non-adjusted) in 68 countries. Wasting prevalence was generally lower in children under two for males and females and the wealthiest and poorest households.

INTERPRETATION

Since wasting prevalence was observed to be greater among children 0-2 years, and adverse exposure to undernutrition and infections are particularly harmful and interventions are more effective during the 1000 days from conception until age two, nutrition interventions should ensure coverage of children under two through programmatic measures to increase detection and enrollment in wasting programs.

FUNDING

UNICEF, Nutrition Section, Programme Division in New York.