Automatic heart disease prediction using feature selection and data mining technique

Abstract

This paper presents an automatic Heart Disease (HD) prediction method based on feature selection with data mining techniques using the provided symptoms and clinical information assigned in the patients dataset. Data mining which allows the extraction of hidden knowledges from the data and explores the relationship between attributes, is the promising technique for HD prediction. HD symptoms can be effectively learned by the computer to classify HD into different classes. However, the information provided may include redundant and interrelated symptoms. The use of such information may degrade the classification performance. Feature selection is an effective way to remove such noisy information meanwhile improving the learning accuracy and facilitating a better understanding for learning model. In our method, HD attributes are weighted and re-ordered based on their rank and assigned by Infinite Latent Feature Selection (ILFS) method. A soft margin linear Support Vector Machine (SVM) is applied to classify a subset of selected attributes into different HD classes. The experiment is performed using UCI Machine Learning Repository Heart Disease public dataset. Experimental result demonstrated the effectiveness of proposed method for precise HD prediction making, our method gained the best performance with an accuracy of 90,65% and an AUC of 0.96 for distinguishing ‘No presence’ HD with ‘Presence’ HD.