Determination of children's nutritional status with machine learning classification analysis approach

Abstract

Malnutrition is a problem that is often faced by every country around the world. Various facts show that malnutrition is of particular concern to many researchers. To can overcome this problem, every effort has been made such as developing analytical models in identification, classification, and prediction. This study aims to determine the nutritional status of children using the machine learning (ML) classification analysis approach. The methods used in the ML analysis process consist of cluster K-Means, artificial neural network (ANN), sum square error (SSE), pearson correlation (PC), and decision tree (DT). The dataset for this study uses data on child nutrition cases that occurred in the previous and was sourced from the provincial general hospital (RSUP) M. Djamil, Padang, West Sumatera. Based on the research presented, ML performance in the nutritional status classification analysis gave maximum results. These results are reported based on the level of precision with an accuracy of 99.23%. The results of the analysis can also present a knowledge-based nutritional status classification. This research can contribute to and update the analytical model in determining nutritional status. The results of this study can also provide benefits in handling nutritional status problems that occur in children.