Stunting Prediction in Children Using Random Forest Algorithm

Stunted child growth and development caused by chronic malnutrition has remained a significant global public health problem worldwide, especially in low-and middle-income countries. Thus, it is essential to employ effective predictive models that can identify those at risk so as to implement appropriate interventions. In this research, a predictive model for childhood stunting based on artificial intelligence (AI) methods will be introduced. The machine learning algorithms and statistical techniques are employed in the model which integrates several socio-economic, demographic, dietary and health related factors to predict stunting among children under five years of age. This includes training the model using survey data that is nationally representative as well as longitudinal studies to ensure its reliability and applicability across populations with different characteristics. Some of the metrics used to assess the predictive performance include accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC-ROC). Many interpretability techniques have been utilized to highlight the primary factors associated with an increased risk of stunting thereby becoming a valuable tool for policy makers and health care providers in planning focused interventions and resource allocation effectively. Utilizing AI, this predictive model presents a proactive strategy to address childhood stunting, ultimately enhancing child health and well-being globally.