Early Prediction of Cardiovascular Diseases
Using ECG signal: Review
Nurul Hikmah Kamaruddin
#1
, M.Murugappan
#2
, Mohammad Iqbal Omar
#3
#
School of Mechatronic Engineering, University Malaysia Perlis,
Kampus Pauh, 02600 Ulu Pauh, Perlis, MALAYSIA.
1
nurulhikmah88@gmail.com,
2
murugappan@unimap.edu.my,
3
iqbalomar@unimap.edu.my
Abstract- Recent survey has pointed out that, by 2030,
almost 23.6 million people will die from
Cardiovascular Diseases (CVD), mainly from heart
disease and stroke. These are projected to remain the
single leading causes of death. One of CVD risk
factors is atherosclerosis which can be predicted by
myocardial ischemia detection; where this condition is
caused by the lack of oxygen and nutrients to the
contractile cells [3]. Ischemia changes of the ECG
frequently affect the entire wave shape of ST-T
complex, thus are inadequately described by isolated
feature such as ST slope, ST-J amplitude and positive
and negative amplitude of the T wave. In order to
identify the abnormal CVDs due to the traditional
risk factor such as tobacco smoking, there are several
types of classifier have been used in the previous
research works such as Artificial Neural Network
(ANN)[21], Fuzzy Logic system[22], Linear
Discriminant Analysis (LDA) and Support Vector
Machine (SVM). Most of the researchers used SVM
and Fuzzy Logic system in their studies [11][23].
Keywords- Cardiovascular Disease (CVD);
Myocardial Ischemia; Electrocardiogram (ECG;,
Discrete Wavelet Transform (DWT); Support Vector
Machine (SVM)
I. INTRODUCTION
Cardiovascular disease (CVD) is one of the major leading
causes of mortality in the worldwide including Malaysia.
The main cardiovascular diseases are heart attack, angina,
stroke and peripheral vascular disease (PVD). CVD is the
heart abnormalities which mean malfunctioning and
dysfunction of heart in which it eventually leads to less
oxygen supply to all vital parts of the body. It affects
oxygen transportation to brain, lungs, internal and heart
itself and supply of less oxygen leads to cause more
problems in the body [2]. The natural functioning of the
heart and its generation of electrical impulses are affected
by the risk factor such as smoking will it leads to induce
several CVD diseases and it increases the dizziness with
more palpitation. Finally abnormal blood flows with a
chance of heart attack are the more severe conditions.
According to the recent survey, 17.1 million people were
died from CVDs in 2004, representing 29 % of all global
deaths. Of these deaths, an estimation of 7.2 million was
due to coronary heart diseases and 5.7 million were due
to stroke [2]. Low- and middle-income countries are
disproportionally affected, 82% of CVD deaths take place
in low- and middle-income countries and occur almost
equally in men and women. Recent survey has pointed
out that, by 2030, almost 23.6 million people will die
from CVDs, mainly from heart disease and stroke. These
are projected to remain the single leading causes of death.
The largest percentage of death due to CVDs will occur
in the Eastern Mediterranean Region [2].Currently, the
best practice for reducing human mortality rates caused
by complex diseases is to detect their symptoms at early
stages. Through the early recognition of symptoms one
can get the most effective clinical treatment for the best
outcome [4]. The medical treatment has been supported
by computerized processes. Signals recorded from the
human body provided valuable information about the
activities of its organ. Their characteristic shape and
spectral property can be correlated with a normal or
pathological function [5]. Most of the previous research
focuses on ECG signal processing in order to predict the
cardiovascular disease in early stage. In this paper, we
present a review of the recent advancement in prediction
of cardiovascular disease research using ECG signal
analysis; in specific to the database used and the
designation of data acquisition, features extraction and
classification methodologies. The goal of this review is to
access and improve the efficiency of the prediction
system for the early stage of cardiovascular disease with
the knowledge of the current advancement in the
technology.
II. CARDIOVASCULAR DISEASE RISK FACTORS
There are several risk factors that associated to
Cardiovascular Diseases, such as smoking, high levels of
cholesterol and triglycerides in the blood, high blood
pressure, lack of exercise, obesity, diabetes [1]. Smoking
accelerates the process of atherosclerosis, or the build-up
of fatty deposits and cholesterol in the arteries. Each time
a person smokes a cigarette, the blood vessels become
sticky from the chemicals in the tobacco smoke and this
leads to fat collecting and sticking to the artery walls.
Most of the other cardiovascular diseases and coronary
978-1-4673-5160-7/12/$26.00 ©2012 IEEE
S2-1
2012 IEEE Student Conference on Research and Development
48