A Review in Prediction of Malnutrition Status Using Data Mining Techniques

Abstract

Child nutritional deficiency comes under various facts such as malnutrition, low birth weight, infant and young child feeding, iodine, and Vitamin deficiency. In recent years, malnutrition is a widespread problem at a global level. This research produces a review of data mining techniques is used to predict the malnutrition status of young children. The root cause of child malnutrition varies across the regions in every country because of various impacts such as lifestyle, food intake, environmental changes, maternal care, and also motherhood care. Most of the research, the results predict the malnutrition status using some anthropometric parameters of preschool age from 5 to under10 age of children and clinical sign parameters are considered to predict the best accuracy. Recently, data mining uses the proposed method of clustering, classification techniques, Regression, and machine learning algorithms to predict the malnutrition status with the highest accuracy using anthropometric parameters (height, weight, and age) for stunted (low height-for-age) and wasted (low weight-for-height), underweight (low weight-for-age) and clinical sign attributes to predict the statuses of malnutrition with and without transformed attributes.