Support Vector Machine to Detect Hypertension

Abstract

Development of tools to facilitate diagnosis of some disease such as cancer, cardiovascular, hypertension, diabetes, is of great relevance in the medical field. In this paper, we will present a method based on Support Vector Machine regression model to detect the hypertension based on some risk factors including obesity, stress, systolic and diastolic blood pressure, physical exercises, cigaret consumption and diet lifestyle. Data represents a group of students from the Lebanese universities. After the data pre-processing, two Support Vector Machine models are designed and implemented in order to estimate systolic and diastolic blood pressure. The outcomes of the methods are diastolic and systolic blood pressure. Accurate results have been obtained which proves the effectiveness of the proposed Support Vector Machine for preliminary detection of hypertension.