The risk prediction of heart disease by using neuro-fuzzy and improved GOA

Abstract

In recent years, artificial intelligent has been widely used as expert systems. In this paper, an intelligent system is provided for determining the risk of cardiovascular diseases. At first, a neuro-fuzzy network is used for risk prediction which the input of this network includes patient's data such as blood pressure, blood sugar, heart rate, number of cigarettes per day, and age, and the output of this network indicates the risk of cardiovascular disease for patients over the next 10 years. In this article, by using genetic algorithm (GA), the features for determining the patient's condition were reduced from 16 to 6 and least-squares algorithm is used to determine the linear network's parameters and, the improved grasshopper optimization algorithm is used to optimize the nonlinear parameters of fuzzy sets. Finally, the proposed network and algorithm are validated by using patient's data which was obtained from patients in Framingham. The results show that the network and algorithm are acceptable.