Predirol: Predicting Cholesterol Saturation Levels Using Big Data, Logistic Regression, and Dissipative Particle Dynamics Simulation

Abstract

Four out of ten Mexican adults have high cholesterol, according to the National Institute of Cardiology. Cholesterol is essential for the production of substances in our body, such as hormones and vitamin D metabolism; it is essential for the absorption of calcium and bile acids. However, excess cholesterol causes hardening and narrowing in the walls of the arteries and can form a clot that causes a heart attack or stroke. Taking into account this problem, in this chapter, we present PREDIROL: Predicting Cholesterol Saturation Levels Using Big Data, Logistic Regression, and Dissipative Particle Dynamics Simulation, which presents an approach with Big Data and mesoscopic simulation techniques with a method of Particle Dynamics DPD (Dissipative Particle Dynamics). Parallel computing using CUDA was implemented to build the DPD model that would represent the cholesterol and blood molecules. However, considering the quantity of cholesterol and blood molecules generated in 3D, which required high computing power, we opted for the 3Dmol.js library based on WebGL for rendering 3D graphics within any web browser. PREDIROL seeks to raise awareness about the care of cholesterol concentration levels since having high levels is detrimental to health, but having low concentration levels, the body does not produce cells in the body. This is a tool for preventive medicine and to improve the lifestyle of users before they develop more serious ailments and even heart attacks or strokes.