A data mining approach for coronary heart disease prediction using HRV features and carotid arterial wall thickness

The main objective of our work has been to develop and then propose a new and unique methodology useful in developing the various features of heart rate variability (HRV) and carotid arterial wall thickness helpful in diagnosing cardiovascular disease. We also propose a suitable prediction model to enhance the reliability of medical examinations and treatments for cardiovascular disease. We analyzed HRV for three recumbent postures. The interaction effects between the recumbent postures and groups of normal people and heart patients were observed based on HRV indexes. We also measured intima-media of carotid arteries and used measurements of arterial wall thickness as other features. Patients underwent carotid artery scanning using high-resolution ultrasound devised in a previous study. In order to extract various features, we tested six classification methods. As a result, CPAR and SVM (gave about 85%-90% goodness of fit) outperforming the other classifiers.