A data mining approach using CPAR and SVM classifiers based on HRV features and carotid arterial wall thickness achieved 85%-90% goodness of fit for predicting cardiovascular disease.
Observational
Does a data mining approach using HRV features and carotid arterial wall thickness accurately predict coronary heart disease?
Machine learning classifiers, specifically CPAR and SVM, utilizing heart rate variability and carotid intima-media thickness can predict coronary heart disease with 85-90% accuracy.
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.
Lee et al. (Thu,) conducted a observational in Coronary Heart Disease. CPAR and SVM classification methods vs. Other classification methods was evaluated on Goodness of fit for cardiovascular disease prediction. A data mining approach using CPAR and SVM classifiers based on HRV features and carotid arterial wall thickness achieved 85%-90% goodness of fit for predicting cardiovascular disease.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: