Heart Attack Prediction System Using Fuzzy C Means Classifier

Cardiovascular disease remains the biggest cause of deaths worldwide. The percentage of premature death from this disease ranges from 4% in high income countries and 42 % in low income countries. This shows the importance of predicting heart disease at the early stage. In this paper, a new unsupervised classification system is adopted for heart attack prediction at the early stage using the patient's medical record. The information in the patient record are preprocessed initially using data mining techniques and then the attributes are classified using a Fuzzy C means classifier. In the classification stage 13 attributes are given as input to the Fuzzy C Means (FCM) classifier to determine the risk of heart attack. FCM is an unsupervised clustering algorithm, which allows one piece of data to belong to two or more clusters. The proposed system will provide an aid for the physicians to diagnosis the disease in a more efficient way. The efficiency of the classifier is tested using the records collected from 270 patients, which gives a classification accuracy of 92%. The result shows that the proposed clustering algorithm can predict the likelihood of patients getting a heart attack in a more efficient and cost effective way than the other well known algorithms.