HEART DISEASE PREDICTION SYSTEM USING MACHINE LEARNING ALGORITHM

Abstract

Abstract—Information decision support systems are becoming
more in use as we are living in the era of digital data and
rise of artificial intelligence. Heart disease as one of the most
known and dangerous is getting very important attention, this
attention is translated into digital and prediction system that
detects the presence of disease according to the available data
and information. Such systems faced a lot of problems since the
first rise, but now with the deveolopment of machine learnig
field we are using them in developing new models to detect the
presence of this disease, in addition to algorithms data is very
important which also form the heart of the predicton systems,
as we know prediction algorithms take decisions and these
decisions must be based on facts, and these facts are extracted
from data, as a result data is the starting point of every system.
In this paper we propose a Heart Disease Prediction System
using Machine Learning Algorithms, in terms of data we used
Cleveland dataset, this dataset is normalized then divided into
three scnearios in terms of traning and testing respectively,
80%-20%, 50%-50%, 30%-70%. In each case of dataset if
it is normalized or not we will have these three scenarios.
We used three machine learning algorithms for every scenario
of the mentioned before which are SVM, SMO and MLP, in
these algorithms we’ve used two different kernels to test the
results upon that. These two types of simulation are added to
the collection of scenarios mentioned above to become as the
following we have at the main level two types normalized and
unnormalized dataset, then for each one we have three types
according to the amount of training and testing dataset, then
for each of these scenarios we have two scenarios according to
the type of kernel to become 30 scenarios in total, our proposed
system have shown a dominance in terms of accuracy over the
other previous works.