Абстрактный

Heart Disease Analysis System Using Data Mining Techniques

G.Karthiga, C.Preethi, R.Delshi Howsalya Devi

Data mining is an iterative progress in which evolution is defined by detection, through usual or manual methods. Knowledge discovery and data mining have found various applications in scientific domain Heart disease is a term for defining a huge amount of healthcare conditions that are related to the heart. This medicinal condition defines the unpredicted health conditions that directly control all the parts of the heart. Different data mining techniques such as association rule mining, classification, clustering are used to predict the heart disease in health care industry .The heart disease database is preprocessed to make the mining process more efficient. The preprocessed data is clustered using clustering algorithms like K-means to cluster relevant data in database. Maximal Frequent Itemset Algorithm (MAFIA) is used for mining maximal frequent patterns in heart disease database. The frequent patterns can be classified using C4.5 algorithm as training algorithm using the concept of information entropy. The results showed that the designed prediction system is capable of predicting the heart attack with good accuracy.