Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia

Identifying determinants of malnutrition in under-five children in Bangladesh: insights from the BDHS-2022 cross-sectional study

Malnutrition remains one of the most pressing global health challenges, particularly in developing countries like Bangladesh, where it continues to significantly impact child health and contribute to chronic illness and high child mortality. Despite the potential of machine learning to improve malnutrition predictions, research in this area remains limited in the country. This study utilizes Bangladesh Demographic and Health Survey (BDHS) 2022 data to identify and quantify key determinants of under-five malnutrition (underweight, wasting, stunting) and evaluates various machine learning models for predicting malnutrition. By addressing a critical gap, this research provides deeper insights into the root causes of malnutrition in Bangladesh. Descriptive statistics were conducted to summarize the key characteristics of the dataset. Boruta algorithm was employed to identify important features related to malnutrition which were then used to evaluate several machine learning models, including K-Nearest Neighbors (KNN), Neural Networks (NN), Classification and Regression Trees (CART), XGBoost (XGBM), Support Vector Machines (SVM), and Random Forest (RF), in addition to the traditional logistic regression (LR) model. The best-performing model was selected to identify the most important factors contributing to malnutrition. The significance of these variables was further assessed using Feature Importance plot (Based on Gini Importance) and Shapley Additive Explanation (SHAP) values. Model performance was evaluated through various metrics, including accuracy, 95% Confidence Interval (CI), Cohen's kappa, sensitivity, specificity, F1 score and precision. The study examined a cohort of 7,910 children, reporting prevalence rates of 19% for stunting, 8% for wasting, and 17% for underweight. The Boruta algorithm identified 18 confirmed features for stunting, 22 for wasting, and 19 for underweight. For stunting, the Random Forest (RF) model outperformed other methods with an accuracy of 64.19%, 95% CI of (0.623, 0.666), Cohen's kappa of 0.158, sensitivity of 56.25%, specificity of 66.00%, F1 score of 0.750 and precision of 0.60. In wasting prediction, RF achieved the highest accuracy at 76.68%, 95% CI of (0.743, 0.787), Cohen's kappa of 0.049, sensitivity of 27.22%, specificity of 80.98%, F1 score of 0.865 and precision of 0.810. Similarly, for underweight, RF demonstrated superior performance with an accuracy of 68.18%, 95% CI of (0.662, 0.703), Cohen's kappa of 0.130, sensitivity of 43.02%, specificity of 73.48%, F1 score of 0.792 and precision of 0.735. Across all malnutrition types, the RF model consistently outperformed traditional logistic regression (LR) and other ML techniques in terms of accuracy, sensitivity, specificity, and other performance metrics. For stunting, key predictors identified in both the Shapley and Gini importance plots included mother's education, father's occupation, place of delivery, wealth index, birth order, and toilet facility; for wasting, significant predictors were antenatal care, unmet family planning, mother's BMI, birth interval, father's occupation, and television ownership; and for underweight, important factors included father's occupation, mother's education, child's age, birth order, wealth index, and place of delivery. This study highlights the effectiveness of Random Forest (RF) in predicting malnutrition outcomes-stunting, wasting, and underweight-using key features identified by the Boruta algorithm. While RF demonstrates moderate performance in predicting stunting and underweight, it shows strong predictive ability for wasting. This underscores RF's potential in guiding targeted interventions for wasting, though further improvements are needed for stunting and underweight predictions. Moreover, the study identifies key contributors for each malnutrition outcome. By pinpointing these determinants, the study provides actionable insights for designing targeted interventions to combat malnutrition more effectively. These findings align with the global development agenda, particularly Sustainable Development Goal (SDG) 2: Zero Hunger and SDG 3: Good Health and Well-being, reinforcing efforts to reduce malnutrition and improve child health outcomes in Bangladesh.

Prediction of malnutrition in kids by integrating ResNet-50-based deep learning technique using facial images

In recent times, severe acute malnutrition (SAM) in India is considered a serious issue as per UNICEF 2022 records. In that record, 35.5% of children under age 5 are stunted, 19.3% are wasted, and 32% are underweight. Malnutrition, defined as these three conditions, affects 5.7 million children globally. This research utilizes an artificial intelligence-based image segmentation technique to predict malnutrition in children. The primary goal of this research is to use a deep learning model to eliminate the need for multiple manual diagnostic tests and simplify the prediction of malnutrition in kids. The traditional model uses text-based data and takes more time with continuous monitoring of kids by analysing body mass index (BMI) over different periods. Children in rural areas often miss medical expert appointments, and a lack of knowledge among parents can lead to severe malnutrition. The aim of the proposed system is to eliminate the need for manual blood tests and regular visits to medical experts. This study uses the ResNet-50 deep learning model's built-in shortcut connection to solve the image-based vanishing gradient problem. This makes training more efficient for image segmentation tasks in predicting malnutrition. The model is 98.49% accurate in predicting the kids who are malnourished among the kids who are healthy. It is evident from the results that the proposed system serves better than other deep learning models, such as XG Boost (75.29% accuracy), VGG 16 (94% accuracy), Xception (95.41% accuracy), and MobileNet (92.42% accuracy). Hence, the proposed technique is effective in detecting malnutrition and diagnose it earlier, without using predictive analysis function or advice from the medical experts.

A deep learning approach for classifying and predicting children's nutritional status in Ethiopia using LSTM-FC neural networks

BACKGROUND

This study employs a LSTM-FC neural networks to address the critical public health issue of child undernutrition in Ethiopia. By employing this method, the study aims classify children's nutritional status and predict transitions between different undernutrition states over time. This analysis is based on longitudinal data extracted from the Young Lives cohort study, which tracked 1,997 Ethiopian children across five survey rounds conducted from 2002 to 2016. This paper applies rigorous data preprocessing, including handling missing values, normalization, and balancing, to ensure optimal model performance. Feature selection was performed using SHapley Additive exPlanations to identify key factors influencing nutritional status predictions. Hyperparameter tuning was thoroughly applied during model training to optimize performance. Furthermore, this paper compares the performance of LSTM-FC with existing baseline models to demonstrate its superiority. We used Python's TensorFlow and Keras libraries on a GPU-equipped system for model training.

RESULTS

LSTM-FC demonstrated superior predictive accuracy and long-term forecasting compared to baseline models for assessing child nutritional status. The classification and prediction performance of the model showed high accuracy rates above 93%, with perfect predictions for Normal (N) and Stunted & Wasted (SW) categories, minimal errors in most other nutritional statuses, and slight over- or underestimations in a few instances. The LSTM-FC model demonstrates strong generalization performance across multiple folds, with high recall and consistent F1-scores, indicating its robustness in predicting nutritional status. We analyzed the prevalence of children's nutritional status during their transition from late adolescence to early adulthood. The results show a notable decline in normal nutritional status among males, decreasing from 58.3% at age 5 to 33.5% by age 25. At the same time, the risk of severe undernutrition, including conditions of being underweight, stunted, and wasted (USW), increased from 1.3% to 9.4%.

CONCLUSIONS

The LSTM-FC model outperforms baseline methods in classifying and predicting Ethiopian children's nutritional statuses. The findings reveal a critical rise in undernutrition, emphasizing the need for urgent public health interventions.

Predicting home delivery and identifying its determinants among women aged 15-49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016-2023: a machine learning algorithm

BACKGROUND

Birth-related mortality is significantly increased by home births without skilled medical assistance during delivery, presenting a major risk to the public's health. The objective of this study is to predict home delivery and identify the determinants using machine learning algorithm in sub-Saharan African.

METHODS

This study used design science approaches. The data set obtained from demographic health survey in sub-Saharan African weighted sample of 299,759 women was included in the stud. Machine learning models such as Random Forest, Decision Tree, K-Nearest Neighbor, Logistic Regression, Extreme Gradient Boosting, AdaBoost, Artificial Neural Network, and Naive Bayes were used. The predictive model was evaluated by area under the curve, accuracy, precision, recall, and F-measure.

RESULTS

The final experimentation results indicated that random forest model performed the best to predict home delivery with accuracy (83%) and, ROC curve (89%). The Shapley additive explanation features an importance plot optimized for random forest model to identifying the most predictors of home delivery. Association rules findings showed that inadequate antenatal care visits, marital status married, no education, mobile phone, television, electricity, poor wealth index, infrequent television viewing, and rural residence were predictor of home delivery.

CONCLUSION

The random forest machine learning model provides greater predictive power for estimating home delivery risk factors. To reduce the prevalence of home delivery, this finding recommends to emphasis on improving antenatal care services, education, and awareness about health facility delivery.

Burden of undernutrition and its associated factors among children aged 6-59 months: findings from 2016 Ethiopian demographic health survey (EDHS) data

BACKGROUND

Despite numerous government nutrition-specific and sensitive interventions, undernutrition (e.g., underweight) remains the major public health concern among under-five-year-old children in Ethiopia. Therefore, this study aimed to assess underweight and associated factors among children in Ethiopia using 2016 EDHS data.

METHOD

The current study used 9,013 children under five years old. An ordinal logistic regression (e.g., proportional odds model) was applied to determine the associated risk factors of being underweight. The current study used SAS software version 9.4 at the 5% significance level.

RESULTS

The prevalence of underweight was 25.3%. Variables such as children's sex, place of residence, whether the child is twin at birth, breastfeeding status, size of children at birth, childbirth order, employment status of mothers, parents' educational level, children's age groups, the incidence of diarrhea in the past two weeks, and baby fortified food were statistically associated with underweight among under-five age in years.

CONCLUSIONS

Underweight among under-five children is predicted by place of residence. In addition, there is a regional disparity of underweight among children. Therefore, further effort is needed to improve health education in children's welfare and health facilities to enhance patients' understanding of proper information and feeding.

Lactate-related gene signatures as prognostic predictors and comprehensive analysis of immune profiles in nasopharyngeal carcinoma

OBJECTIVES

Nasopharyngeal carcinoma (NPC) is an aggressive malignancy with high rates of morbidity and mortality, largely because of its late diagnosis and metastatic potential. Lactate metabolism and protein lactylation are thought to play roles in NPC pathogenesis by modulating the tumor microenvironment and immune evasion. However, research specifically linking lactate-related mechanisms to NPC remains limited. This study aimed to identify lactate-associated biomarkers in NPC and explore their underlying mechanisms, with a particular focus on immune modulation and tumor progression.

METHODS

To achieve these objectives, we utilized a bioinformatics approach in which publicly available gene expression datasets related to NPC were analysed. Differential expression analysis revealed differentially expressed genes (DEGs) between NPC and normal tissues. We performed weighted gene coexpression network analysis (WGCNA) to identify module genes significantly associated with NPC. Overlaps among DEGs, key module genes and lactate-related genes (LRGs) were analysed to derive lactate-related differentially expressed genes (LR-DEGs). Machine learning algorithms can be used to predict potential biomarkers, and immune infiltration analysis can be used to examine the relationships between identified biomarkers and immune cell types, particularly M0 macrophages and B cells.

RESULTS

A total of 1,058 DEGs were identified between the NPC and normal tissue groups. From this set, 372 key module genes associated with NPC were isolated. By intersecting the DEGs, key module genes and lactate-related genes (LRGs), 17 lactate-related DEGs (LR-DEGs) were identified. Using three machine learning algorithms, this list was further refined, resulting in three primary lactate-related biomarkers: TPPP3, MUC4 and CLIC6. These biomarkers were significantly enriched in pathways related to "immune cell activation" and the "extracellular matrix environment". Additionally, M0 and B macrophages were found to be closely associated with these biomarkers, suggesting their involvement in shaping the NPC immune microenvironment.

CONCLUSION

In summary, this study identified TPPP3, MUC4 and CLIC6 as lactate-associated clinical modelling indicators linked to NPC, providing a foundation for advancing diagnostic and therapeutic strategies for this malignancy.

Prediction of incomplete immunization among under-five children in East Africa from recent demographic and health surveys: a machine learning approach

The World Health Organization as part of the goal of universal vaccination coverage by 2030 for all individuals. The global under-five mortality rate declined from 59% in 1990 to 38% in 2019, due to high immunization coverage. Despite the significant improvements in immunization coverage, about 20 million children were either unvaccinated or had incomplete immunization, making them more susceptible to mortality and morbidity. This study aimed to identify predictors of incomplete vaccination among children under-5 years in East Africa. An analysis of secondary data from six east African countries using Demographic and Health Survey dataset from 2016 to the recent 2021 was performed. A total weighted sample of 27,806 children aged (12-35) months was included in this study. Data were extracted using STATA version 17 statistical software and imported to a Jupyter notebook for further analysis. A supervised machine learning algorithm was implemented using different classification models. All analysis and calculations were performed using Python 3 programming language in Jupyter Notebook using imblearn, sklearn, XGBoost, and shap packages. XGBoost classifier demonstrated the best performance with accuracy (79.01%), recall (89.88%), F1-score (81.10%), precision (73.89%), and AUC 86%. Predictors of incomplete immunization are identified using XGBoost models with help of Shapely additive eXplanation. This study revealed that the number of living children during birth, antenatal care follow-up, maternal age, place of delivery, birth order, preceding birth interval and mothers' occupation were the top predicting factors of incomplete immunization. Thus, family planning programs should prioritize the number of living children during birth and the preceding birth interval by enhancing maternal education. In conclusion promoting institutional delivery and increasing the number of antenatal care follow-ups by more than fourfold is encouraged.

Predictors of micronutrient deficiency among children aged 6-23 months in Ethiopia: a machine learning approach

Introduction

Micronutrient (MN) deficiencies are a major public health problem in developing countries including Ethiopia, leading to childhood morbidity and mortality. Effective implementation of programs aimed at reducing MN deficiencies requires an understanding of the important drivers of suboptimal MN intake. Therefore, this study aimed to identify important predictors of MN deficiency among children aged 6-23 months in Ethiopia using machine learning algorithms.

Methods

This study employed data from the 2019 Ethiopia Mini Demographic and Health Survey (2019 EMDHS) and included a sample of 1,455 children aged 6-23 months for analysis. Machine Learning (ML) methods including, Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Neural Network (NN), and Naïve Bayes (NB) were used to prioritize risk factors for MN deficiency prediction. Performance metrics including accuracy, sensitivity, specificity, and Area Under the Receiver Operating Characteristic (AUROC) curves were used to evaluate model prediction performance.

Results

The prediction performance of the RF model was the best performing ML model in predicting child MN deficiency, with an AUROC of 80.01% and accuracy of 72.41% in the test data. The RF algorithm identified the eastern region of Ethiopia, poorest wealth index, no maternal education, lack of media exposure, home delivery, and younger child age as the top prioritized risk factors in their order of importance for MN deficiency prediction.

Conclusion

The RF algorithm outperformed other ML algorithms in predicting child MN deficiency in Ethiopia. Based on the findings of this study, improving women's education, increasing exposure to mass media, introducing MN-rich foods in early childhood, enhancing access to health services, and targeted intervention in the eastern region are strongly recommended to significantly reduce child MN deficiency.

Feature selection and association rule learning identify risk factors of malnutrition among Ethiopian schoolchildren

Introduction

Previous studies have sought to identify risk factors for malnutrition in populations of schoolchildren, depending on traditional logistic regression methods. However, holistic machine learning (ML) approaches are emerging that may provide a more comprehensive analysis of risk factors.

Methods

This study employed feature selection and association rule learning ML methods in conjunction with logistic regression on epidemiological survey data from 1,036 Ethiopian school children. Our first analysis used the entire dataset and then we reran this analysis on age, residence, and sex population subsets.

Results

Both logistic regression and ML methods identified older childhood age as a significant risk factor, while females and vaccinated individuals showed reduced odds of stunting. Our machine learning analyses provided additional insights into the data, as feature selection identified that age, school latrine cleanliness, large family size, and nail trimming habits were significant risk factors for stunting, underweight, and thinness. Association rule learning revealed an association between co-occurring hygiene and socio-economical variables with malnutrition that was otherwise missed using traditional statistical methods.

Discussion

Our analysis supports the benefit of integrating feature selection methods, association rules learning techniques, and logistic regression to identify comprehensive risk factors associated with malnutrition in young children.

Prediction of Stunting Among Under-5 Children in Rwanda Using Machine Learning Techniques

OBJECTIVES

Rwanda reported a stunting rate of 33% in 2020, decreasing from 38% in 2015; however, stunting remains an issue. Globally, child deaths from malnutrition stand at 45%. The best options for the early detection and treatment of stunting should be made a community policy priority, and health services remain an issue. Hence, this research aimed to develop a model for predicting stunting in Rwandan children.

METHODS

The Rwanda Demographic and Health Survey 2019-2020 was used as secondary data. Stratified 10-fold cross-validation was used, and different machine learning classifiers were trained to predict stunting status. The prediction models were compared using different metrics, and the best model was chosen.

RESULTS

The best model was developed with the gradient boosting classifier algorithm, with a training accuracy of 80.49% based on the performance indicators of several models. Based on a confusion matrix, the test accuracy, sensitivity, specificity, and F1 were calculated, yielding the model's ability to classify stunting cases correctly at 79.33%, identify stunted children accurately at 72.51%, and categorize non-stunted children correctly at 94.49%, with an area under the curve of 0.89. The model found that the mother's height, television, the child's age, province, mother's education, birth weight, and childbirth size were the most important predictors of stunting status.

CONCLUSIONS

Therefore, machine-learning techniques may be used in Rwanda to construct an accurate model that can detect the early stages of stunting and offer the best predictive attributes to help prevent and control stunting in under five Rwandan children.

Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia

Stunting is a global public health issue. We sought to train and evaluate machine learning (ML) classification algorithms on the Zambia Demographic Health Survey (ZDHS) dataset to predict stunting among children under the age of five in Zambia. We applied Logistic regression (LR), Random Forest (RF), SV classification (SVC), XG Boost (XgB) and Naïve Bayes (NB) algorithms to predict the probability of stunting among children under five years of age, on the 2018 ZDHS dataset. We calibrated predicted probabilities and plotted the calibration curves to compare model performance. We computed accuracy, recall, precision and F1 for each machine learning algorithm. About 2327 (34.2%) children were stunted. Thirteen of fifty-eight features were selected for inclusion in the model using random forest. Calibrating the predicted probabilities improved the performance of machine learning algorithms when evaluated using calibration curves. RF was the most accurate algorithm, with an accuracy score of 79% in the testing and 61.6% in the training data while Naïve Bayesian was the worst performing algorithm for predicting stunting among children under five in Zambia using the 2018 ZDHS dataset. ML models aids quick diagnosis of stunting and the timely development of interventions aimed at preventing stunting.

Predicting child anaemia in the North-Eastern states of India: a machine learning approach

Child anaemia is a serious global health issue and India is one of the highest contributors among the developing nations. Researchers identify many harmful effects of anaemia, which include psychomotor retardation, which in turn decreases the learning ability and causes low intelligence among pre-school children. The effects also include behavioural delays, low immunity, and susceptibility to frequent infections, increased mortality, and disability. The present study aims to predict anaemia among children in North-East India by applying Machine Learning (ML) algorithms to latest available National Family Health Survey (NFHS)-4 data. Out of the total 29,312 eligible children (6–59 months) in North-East India, a total of 21,000 children with demographic variables without any missing observations, wherein 10,460 are anaemic, is considered for this study. Machine learning (ML) algorithms have been applied through 3 different types of penalized regression methods—ridge, least absolute shrinkage and selection operator, and elastic net for predicting anaemia. A systematic assessment of algorithms is performed in terms of accuracy, sensitivity, specificity, F1-Score, and Cohen’s \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$k$$\end{document} k -Statistics. Having achieved the receiver operating characteristic value of over 70% in training and accuracy of above 64% while testing, it can be safely asserted that factors like mother’s anaemic status, age of the child, social status, mother’s age, mother’s education, religion are important in identifying the child as anaemic.