Estimating mean arterial pressure affected by stress scores using spline nonparametric regression model approach

Abstract

An average arterial blood pressure needed for blood circulation to the brain is called as mean arterial pressure (MAP). Blood circulation to the brain supplies food and oxygen to the brain for nutrition and brain activity. If the MAP is too low, it can cause diseases such as tachycardi heart rate and hypotension. In contrast, if MAP is too high, it can cause brain blood vessel rupture and hypertension. Stress is believed to has a relationship with hypertension. This is thought to be through sympathetic nerve activity which can increase blood pressure intermittently. Also, stress can stimulate kidneys to release adrenaline hormone and stimulate the heart to beat faster and stronger, so that blood pressure will increase. An increase in stress scores can be followed by an increase in MAP as well. In this study, we are interested to investigate the aftermath of changes in the stress scores on MAP by using spline nonparametric regression model approach which can accommodate changes in data patterns, and then compare it with the parametric regression model approach. The results showed that based on the mean square error values, the nonparametric regression model approach based on spline estimator is better than the parametric regression model approach. The estimated model that we got can be used to predict and interpret the values of MAP affected by stress scores as an effort to prevent hypertension.