Analysis of Blood Pressure using Data Mining Techniques

Abstract

Hypertension is a serious public health concern. Diseases related to high blood pressure (BP) such as cardiovascular disease (CVDs) have emerged as one of the main dangers to human health. Cardiovascular disease caused due to hypertension is a widespread chronic disease. Monitoring blood pressure (BP), a physiological indication for cardiovascular systems is a useful strategy for preventing CVDs. An intervention that helps in the early management and prevention of hypertension is risk prediction. Effective incident prevention has been shown to need continuous BP measurement. The use of non-intrusive blood pressure monitoring in continuous measurement appears promising in contrast to conventional prediction models that have poor measurement accuracy or require extensive training. As a result, linear regression is suggested and used to address the issue in this study. The goal is to build predictive models, such as linear regression - a machine learning technique that can identify people at a high risk of developing hypertension without invasive clinical procedures. With the help of one or more independent variables, a dependent variable is predicted using the Modelling technique of linear regression. In this article, blood pressure is analyzed by considering age, weight, stress, and pulse.