TITLE:
Automatic Heart Disease Diagnosis System Based on Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) Approaches
AUTHORS:
Mohammad A. M. Abushariah, Assal A. M. Alqudah, Omar Y. Adwan, Rana M. M. Yousef
KEYWORDS:
Heart Disease, ANN, ANFIS, Multilayer Perceptron, Neuro-Fuzzy, Cleveland Data Set
JOURNAL NAME:
Journal of Software Engineering and Applications,
Vol.7 No.12,
November
28,
2014
ABSTRACT: This paper aims to design
and implement an automatic heart disease diagnosis system usingMATLAB. The Cleveland data set for
heart diseases was used as the main database for training and testing the
developed system. In order to train and test the Cleveland data set, two
systems were developed. The first system is based on the Multilayer Perceptron
(MLP) structure on the Artificial Neural Network (ANN), whereas the second
system is based on the Adaptive Neuro-Fuzzy Inference Systems (ANFIS) approach.
Each system has two main modules, namely, training and testing,where 80% and 20% of the Cleveland
data set were randomly selected for training and testingpurposes respectively. Each system also
has an additional module known as case-based module,where the user has to input values for
13 required attributes as specified by the Cleveland data set,in order to test the status of the
patient whether heart disease is present or absent from that particular
patient. In addition, the effects of different values for important parameters
were investigated in the ANN-based and Neuro-Fuzzy-based systems in order to
select the best parameters that obtain the highest performance. Based on the
experimental work, it is clear that the Neuro-Fuzzy system outperforms the ANN
system using the training data set, where the accuracy for each system was 100%
and 90.74%, respectively. However, using the testing data set, it is clear that
the ANN system outperforms the Neuro-Fuzzy system, where the best accuracy for
each system was 87.04% and 75.93%, respectively.