International Conference on Information and Knowledge Technology

فارسی

Home / یازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

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

Authors :

Vahid Safari Dehnavi¹ Masoud Shafiee²

1- Amirkabir University of Technology 2- Amirkabir University of Technology

Keywords :

Cardiovascular disease, prediction, patient’s condition, expert system.

Abstract :

In recent years, intelligent systems have been widely used as an expert system. In this paper, an intelligent system is provided for determining the risk of cardiovascular diseases; therefore, an expert system based on fuzzy inference has been used to determine the risk of heart disease for patients. At first, a structure based on neuro-fuzzy is used in which the input of this networks includes patient's data such as blood pressure, and age, and the output of this networks indicates the risk of cardiovascular disease for the patient over the next 10 years. In this article, by using a genetic algorithm (GA), we try to reduce the input characteristics to determine the patient's condition. The least-squares algorithm is used to determine the linear parameters of the neuro-fuzzy and, the proposed improved grasshopper optimization algorithm is used to optimize the nonlinear parameters of the fuzzy sets. Then the neuro-fuzzy network is used to determine the patient's condition. Finally, the proposed network and algorithm are validated by using quantitative patient data which was obtained from patients in Framingham. The results show that the network and algorithm are acceptable, and fuzzy logic has a simpler structure.