Advanced Medical based Child Malnutrition Prediction using ML

Abstract - Childhood undernourishment represents a critical health challenge with far-reaching consequences for a country's economic development. 1 Adequate dietary intake is vital for children's survival and growth, yet poor nutrition continues to affect millions of young children worldwide, particularly in less developed nations. 2 To address this challenge, researchers developed an intelligent system to predict nutritional outcomes in children under five years old. 4 The platform leverages Kaggle datasets to identify underlying trends and crucial variables linked to undernourishment through analytical mining techniques. Using a Bayesian classification algorithm renowned for its precision, the system forecasts a child's dietary status. Results are presented via an intuitive graphical interface. Following comprehensive testing and verification, healthcare practitioners can utilize these findings to create prevention programs and minimize undernourishment in vulnerable communities. Designed as a live application for social impact, the platform employs Visual Studio for user interface development and SQL Server for database management. These technologies provide an ideal foundation for building a reliable and effective real-time solution. This initiative demonstrates how analytical classification methods can be applied to medical datasets to anticipate and evaluate childhood undernourishment, ultimately enhancing health outcomes. Keywords:Child malnutrition, Bayesian classifier, data mining, nutitional status, prediction, machine learning, healthcare informatics, classification algorithms, preventive healthcare, public health, economic development