APPLICATION OF MACHINE LEARNING IN DETERMINING THE CLASSIFICATION OF CHILDREN'S NUTRITION WITH DECISION TREE

Abstract

The problem of nutrition for children is a health problem that must be solved by the government. Malnutrition is a very important problem in the development of children, especially during the growth period. Lack of nutritional intake in children will have a negative impact on resistance to the virus. This will risk death caused by malnutrition. There is direct monitoring from the government, hospitals, and health offices in looking at the classification of nutrition in children in a system. This study aims to classify the nutritional status of children using a machine learning model, which then the final result can show the classification of nutritional vulnerability in each patient at the North Aceh Hospital. The stages of the research include the identification of theories about nutritional problems. Second, data collection is in the form of symptoms and diagnosis of disease classification in machine learning implementation. The third is to analyze the data using the research and development (R&D) method according to the classification of children's nutrition. Finally, the implementation of the patient classification model with decision tree into machine learning The variables included in the system include JK(X1), U (X2), BB(X3), TB (X4), and BB (X3), which are the variables that have the most influence on malnutrition in children. The results of this study for testing weight 16, height 9.7, age 33 months, nutritional value 54,23772 which the program output results are normal. Patient Syafira Nisman, weight 9, height 72, age 21 months, suffered from malnutrition. The results of the research on the application of machine learning for the classification of malnutrition using the decision tree method make it easier for patients and hospitals to classify children's nutrition.