Early Childhood Health Risk Prediction using ML Techniques

Early identification of health risks in children under five, such as malnutrition, stunting, wasting, and anemia, is critical for effective intervention and improving child health outcomes. This study explores the application of machine learning algorithms - including Random Forest, Logistic Regression, Support Vector Machine (SVM), Decision Tree, and KNearest Neighbors (KNN) - to predict these health outcomes using key features: age, height, weight, and hemoglobin (hb) levels. The dataset underwent standard preprocessing, including handling missing values and feature standardization, followed by model training and evaluation using metrics such as accuracy, precision, recall, and F1-score. Results demonstrate that the Random Forest algorithm achieved the highest accuracy, effectively capturing non-linear relationships within the data, while Logistic Regression and SVM also showed strong predictive performance. The findings highlight the feasibility of leveraging machine learning models in pediatric healthcare for early detection of health risks, enabling timely interventions and datadriven decision-making. Future work may explore the inclusion of additional features such as dietary patterns and socioeconomic indicators to further enhance predictive accuracy and generalizability.