Related Experiment Video
Updated: Apr 6, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Application of machine learning algorithm for predicting acute malnutrition among under 5 children in east Africa
Habtamu Guaguahu Feleke1, Mulat Belay Simegn2, Zenebe Abebe Gebreegziabher3
1Department of Public Health, College of Medicine and Health Sciences, Debre Markos University, Debre Markos, Ethiopia. guaguahuhabtamu@gmail.com.
Insights
Machine learning models can predict acute malnutrition in East African children. The Random Forest model showed the best performance, identifying key risk and protective factors for early intervention.
Area of Science:
- Public Health
- Machine Learning
- Pediatrics
Background:
- Acute malnutrition is a major cause of death in children under five in East Africa.
- Early detection through predictive modeling can improve intervention outcomes.
- Existing surveillance systems need enhancement for timely identification of at-risk children.
Purpose of the Study:
- To develop and evaluate machine learning models for predicting acute malnutrition in East African children under five.
- To identify key risk and protective factors associated with acute malnutrition.
- To assess the potential of machine learning for improving nutrition surveillance.
Main Methods:
- Cross-sectional analysis of Demographic and Health Survey (DHS) data from 12 East African countries (n=76,224).
- Data preprocessing included imputation, encoding, SMOTE, and feature selection.
- Ten supervised machine learning algorithms were trained and validated; performance was assessed using accuracy, AUC, precision, recall, and F1-score. SHapley Additive exPlanations (SHAP) were used for interpretability.
Main Results:
- The prevalence of acute malnutrition was 6.08% across East Africa.
- The Random Forest model achieved the highest performance (AUC 74.6%, accuracy 71.2%).
- Key predictors included rural residence, large family size, multiple young children, poor maternal and child health practices, and inadequate water/sanitation. Protective factors included maternal literacy, ANC, vitamin A supplementation, and longer birth intervals.
Conclusions:
- Machine learning, particularly Random Forest, offers a powerful tool for predicting acute malnutrition in East African children.
- Integrating predictive models into national nutrition surveillance can enable early detection and targeted interventions.
- Interventions should focus on addressing identified risk factors, especially in rural areas, and strengthening maternal and child health services.
Abstract:
Acute malnutrition remains a critical public health challenge across East Africa, contributing substantially to under-five morbidity and mortality. Early identification of at-risk children using predictive models could enhance timely intervention. This study aimed to develop and evaluate machine learning models for predicting acute malnutrition among under-five children in East Africa. A cross-sectional analysis was conducted using the most recent DHS data from 12 East African countries. A total of 76,224 children under-five years were included. Data preprocessing involved multiple imputation for missing values, one-hot encoding for categorical variables, SMOTE to address class imbalance, and multiple feature selection. ten supervised machine learning algorithms; Logistic Regression, Random Forest, K-Nearest Neighbors, Decision Tree, Support Vector Machine, Naïve Bayes, XGBoost, LightGBM, CatBoost, and Stochastic Gradient Descent were trained and evaluated using an 80/20 train-test split and stratified five-fold cross-validation. Model performance was assessed using accuracy, AUC, precision, recall, and F1-score, and interpretability was explored using SHapley Additive exPlanations (SHAP). The overall prevalence of acute malnutrition across east Africa was 6.08% (95% CI 5.91-6.25%), ranging from 1.2% in Rwanda to 12.27% in Ethiopia. The Random Forest algorithm demonstrated the best predictive performance, achieving an AUC of 74.6% (95% CI 73.0-76.2), accuracy of 71.2%, precision of 13.1%, recall of 66.2%, specificity of 71.5%, and an F1-score of 0.218. SHAP analysis identified important predictors of acute malnutrition as rural residence, large family size (≥ 6 members), higher number of under-five children (≥ 3), small or very small birth size, inadequate antenatal care, unimproved water sources, inappropriate disposal of child feces, recent diarrheal illness, and lack of latrine facilities. Protective factors included maternal literacy, antenatal care attendance, vitamin A supplementation, longer birth intervals (≥ 2 years), and maternal employment. Random Forest, demonstrate superior predictive capacity for identifying children at risk of acute malnutrition in East Africa. The integration of such models into national nutrition surveillance systems could enable early detection and targeted interventions. Strategies should prioritize rural communities, strengthen maternal education and empowerment, improve water and sanitation infrastructure, and antenatal care to mitigate risk factors and enhance child nutritional outcomes.
