Heart disease is defined as any abnormal heart condition, and it is prevalent in people today. Considering human body as one big system, many factors play role on this disease. Examining the body provides quite lot of data in many different ways, though understanding the signs in collected data about heart disease requires experience, knowledge, and time from physicians. Computer based expert systems are designed to reduce the burden on physicians by automation. One of the important components of expert systems is data classifiers, and in this paper, I present the use of Radial Basis Function Networks (RBFN) with a Gaussian function as data classifier for heart disease classification. The proposed method in the paper makes use of same training data after they are used for training to reduce false classifications which makes this project unique in itself. For development and testing, I utilized patient records from Prince Sultan Cardiac Center-Qassim in Saudi Arabia. This paper discusses the use of RBFN for the classification of heart diseases, and it proposes a model system that forms data collection, processing, storage, and usage procedures.
[1]
K. Usha Rani,et al.
Class : Class 0 : Normal Person . Class 1 : first stroke Class 2 : second stroke Class 3 : end of life Attribute Description
,
2011
.
[2]
K. Rajeswari,et al.
A Novel Risk Level Classification of Ischemic Heart Disease using Artificial Neural Network Technique - An Indian Case Study
,
2011
.
[3]
P. A. Tijare,et al.
Classification of Heart Disease Dataset using Multilayer Feed forward backpropogation Algorithm
,
2013
.
[4]
Ashraf Afifi,et al.
Laguerre Kernels -Based SVM for Image Classification
,
2014
.
[5]
R. Detrano,et al.
International application of a new probability algorithm for the diagnosis of coronary artery disease.
,
1989,
The American journal of cardiology.
[6]
Friedhelm Schwenker,et al.
Three learning phases for radial-basis-function networks
,
2001,
Neural Networks.