An intelligent approach based on Principal Component Analysis and Adaptive Neuro Fuzzy Inference System for predicting the risk of cardiovascular diseases

Medical diagnosis is done mostly by medical practitioner´s expertise and experience. But in some cases, it may lead to wrong diagnosis and treatment. In this paper, a medical diagnosis system is proposed to predict the risk of cardiovascular diseases with high prediction accuracy. This system is built using an intelligent approach based on Principal Component Analysis (PCA) and Adaptive Neuro Fuzzy Inference System (ANFIS). This system has two stages: In the first stage, dimension of heart disease dataset that has 13 attributes is reduced to 7 attributes using PCA. In the second stage, diagnosis of heart disease is conducted using ANFIS. In ANFIS, the learning capabilities of neural network and reasoning capabilities of fuzzy logic is combined inorder to give better prediction. The heart disease dataset used is Cleveland Heart Disease dataset provided by the University of California, Irvine (UCI) Machine Learning Repository. The obtained classification accuracy using this approach is 93.2%.