Towards Early Detection of Pediatric Malnutrition in Chittagong Region: A Stacked Ensemble and XAI-Based Study

Malnutrition can be a significant issue in a developing country like Bangladesh. Weight-for-Age Z-score (WAZ), Height-for-Age Z-score (HAZ), Weight-for-Height Z-score (WHZ), and Mid-Upper Arm Circumference (MUAC) are standard anthropometric measures used to assess the nutritional health of children under five. The dataset used in this study was collected from two districts (Noakhali and Lakshmipur) in the Chittagong region and is employed to explore machine learning models for predicting pediatric nutritional status. Several supervised machine learning models, including Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP), are implemented in this research. A stacking ensemble model is developed by combining three classifiers, such as DT, MLP, and LR, to improve classification performance. The…