LVQ Algorithm for The Classification of Hypertension Based on ESH Guideline

Abstract

Hypertension was a global health problem, including Indonesia, that increases mortality, morbidity, and cost. In Indonesia, hypertension kept on increasing due to change in lifestyle, consumptions of food with a high level of fat, cholesterol, less physical activity, and a high level of stress, etc. One of the classifications of hypertension used in some country were European Society of Hypertension (ESH) guideline. Learning Vector Quantization (LVQ) was a method in machine learning for classifying data. LVQ were often used in pattern recognition processes such as images, sounds, etc. The purpose of this study was to see an increase in accuracy of hypertension classification based on ESH guideline as weight data. In this study, hypertension classification based on ESH guideline was used as weight data with LVQ method and the parameters used were 2 features, 100 epochs, 0.05 learning rate, 0.01 reducing factor, train data 70%, validation data 30%, and test data 30% from total data used. The result obtained in this study were 94.6667% in the hypertension classification process based on ESH guideline using LVQ method. The conclusion of this study, there was an increase in the accuracy of hypertension classification based on ESH guideline using the LVQ method.