Intelligent approaches for prognosticating atherosclerotic and non-atherosclerotic individuals

In human cardiovascular system, arteries plays a vital role in carrying pure blood away from the heart and supplying them to the superior and inferior parts of the body. Atherosclerosis is a condition where the arteries become narrowed and hardened due to an excessive build- up of plaque around artery wall. The growth of the disease is slow, asymptomatic, and may lead to abrupt cardiac arrest, stroke, or myocardial infarction. Currently imaging methods are applied, however they lack the required resolution and sensitivity for detection. In this work clinical observations and habits of individuals are considered. Intelligent machine learning technique, multiclass SVM is used for assorting the individuals. A case study was made in this work regarding the atherosclerosis disease progression and crucial features were selected for effectuating the performance of the classifier. The state-of-the-art technique was enhanced with efficient pre-processing technique. Optimized missing value imputation strategy, Principal Component Analysis (PCA) for STULONG dataset and efficient feature subset selection method, hybrid FCBF have been employed for extracting the relevant features and dismissing the redundant features. Further proceeding to intensify the target, our work has outperformed with utmost accuracy of about 98.97% compared with other state-of-the-art machine learning techniques.