A Dual Approach: Naïve Bayes and Decision Tree for Malnutrition Prediction

The system of support for medical decisions for the prediction of malnutrition in children deals with a critical problem of malnutrition in children under the age of five, especially in developing countries where malnutrition significantly affects health and future economic productivity. The proposed system uses key anthropometric and clinical parameters, including age, gender, height, weight, weight for age (WAZ), heights for age (HAZ) and weight score (WHZ) to assess the state of nutrition. Two machine learning algorithms, naive bayes and decision -making tree have been implemented since zero to support real -time prediction using dynamic data sets. The method of extraction of gross force elements was used to identify the most influential attributes affecting malnutrition. Experimental evaluation showed that the naive Bayes model achieved an accuracy of 94% with a minimum calculation time and exceeded the model of the decision tree that reached 85%. The system integrates Visual Studio as a frontend and SQL server as a backend, which demonstrates practical usability for healthcare professionals and public health organizers.