CHAPTER ONE

GENERAL INTRODUCTION

1.1              Background of the Study

Recent trends in the field of data mining have driven to the emergence of expert systems for medical applications. Many computational tools and algorithms have been recently developed to increase the experiences and the abilities of physicians for taking decisions about different diseases. Normally physician acquires knowledge and experience after analyzing sufficient number of cases. This experience is reached only in the middle of a physician’s career. However, for the case of rare or new diseases, experienced physicians are also in the same situation as new comers. In fact, humans do not work like statistic computers but as pattern recognition systems. Humans can distinguish patterns or objects very easily but fail when probabilities have to be allocated for observations (Salim, 2004).

Recent papers demonstrated the power of artificial neural networks and evaluated their limits, possible trends, future developments and connections to other branches of human medicine in (Filippo et al., 2013). They concluded that Artificial Neural Networks (ANNs) represent a powerful tool to help physicians perform diagnosis and other enforcements. In this study, we will be diagnosing disease of the Cardiovascular System using Subtractive Clustering and Artificial Neural Network.

The cardiovascular system, also called the circulatory system or the vascular system, is an organ system that permits blood to circulate and transport nutrients (such as amino acids and electrolytes), oxygen, carbon dioxide, hormones, and blood cells to and from the cells in the body to provide nourishment and help in fighting diseases, stabilize temperature and pH, and maintain homeostasis (Burns, 2013).

The essential components of the human cardiovascular system are the heart, blood and blood vessels. It includes the pulmonary circulation, a "loop" through the lungs where blood is oxygenated; and the systemic circulation, a "loop" through the rest of the body to provide oxygenated blood. The systemic circulation can also be seen to function in two parts; a macrocirculation and a microcirculation (Sherwood, 2015). An average adult contains five to six quarts (roughly 4.7 to 5.7 liters) of blood, accounting for approximately 7% of their total body weight. Blood consists of plasma, red blood cells, white blood cells, and platelets. Also, the digestive system works with the circulatory system to provide the nutrients the system needs to keep the heart pumping (Herman, 2016). There are some diseases that affect the functionality of the cardiovascular system; these diseases are called generally called cardiovascular disease.

Cardiovascular disease (CVD) is a class of diseases that involve the heart or blood vessels. Cardiovascular disease includes coronary artery diseases (CAD) such as angina and myocardial infarction (commonly known as a heart attack) (Nichols, Townsend, Scarborough and Rayner, 2014). Other CVDs include stroke, heart failure, hypertensive heart disease, rheumatic heart disease, cardiomyopathy, heart arrhythmia, congenital heart disease, valvular heart disease, carditis, aortic aneurysms, peripheral artery disease, thromboembolic disease, and venous thrombosis (Nichols et al., 2014).

Coronary artery disease, stroke, and peripheral artery disease involve atherosclerosis. This may be caused by high blood pressure, smoking, diabetes, lack of exercise, obesity, high blood cholesterol, poor diet, and excessive alcohol consumption, among others. High blood pressure results in 13% of CVD deaths, while tobacco results in 9%, diabetes 6%, lack of exercise 6% and obesity 5% (Puska, Mendis, Norrving, and World Health Organization, 2011).

Cardiovascular diseases are the leading cause of death globally. Together they resulted in 17.9 million deaths (32.1%) in 2015 up from 12.3 million (25.8%) in 1990 (Abubakar et al., 2015). Coronary artery disease and stroke account for 80% of CVD deaths in males and 75% of CVD deaths in females (Abubakar et al., 2015). Most cardiovascular disease affects older adults. In the Africa 11% of people between 20 and 40 have CVD, while 37% between 40 and 60, 71% of people between 60 and 80, and 85% of people over 80 have CVD (Abubakar et al., 2015). The average age of death from coronary artery disease in the developed world is around 80 while it is around 68 in the developing world (Abubakar et al., 2015).

Over the years, numerous methods have been developed for clustering patterns. Each method can have its own technique (i.e. partitioning or hierarchical), approach (fuzzy or crisp clustering), or special purpose (i.e. for sequential data set, very large database, etc.). Researchers have been working to improve them, or to create new methods to satisfy present demand (Adeyemo et al., 2011). To design cardiovascular disease diagnosis system with high performance, this research will be using combination of Subtractive Clustering and Artificial Neural Networks on the medical records of patients suffering from this ailment.

The Subtractive clustering is one-pass algorithm for estimating the number of clusters and initial location of cluster centers, and extracts the fuzzy rules through the training data in a given dataset to pre-process the dataset. When the data groups are formed, classification process can continue (Nakkrasae et al., 2004).

An artificial neural network (ANN) is a computational model based on the structure and functions of biological neural networks. Information that flows through the network affects the structure of the ANN because a neural network changes or learns, in a sense based on input and output. ANNs have three layers that are interconnected. The first layer consists of input neurons. Those neurons send data on to the second layer, which in turn sends information to the output neurons (third layer). Training an artificial neural network involves choosing from allowed models for which there are several associated algorithms like Levenberg-Marquardt, Scaled Conjugate Gradient, and so on (CireşAn et al., 2012).

1.2       Statement of the Problem

Presence of noise in a dataset affects the quality of the decision that can be made from such dataset. The larger a dataset, the higher the probability of noise been present in the dataset; with the increase in numbers of medical data its very rear to collate a medical data without noise. Hence, removing the noise through data pre-processing is paramount for effective decision making. Furthermore, training and designing a system with a large dataset samples consume a lot of system memory with higher execution time. Therefore, the use of subtractive clustering is being envisaged as a good technique for generating initial cluster to remove noise in the dataset and to group the data samples whereby numbers of samples will be reduce which will reduce the execution time and system memory. The clustered dataset will then be used in training the system using ANN.

1.3       Aim and Objectives

The aim of this study is to develop a system that diagnoses cardiovascular disease using Subtractive Clustering and Artificial Neural Networks Algorithms.

The objectives are to:

        i.            Cluster cardiovascular disease dataset using Subtractive Clustering.

      ii.            Classify the clustered cardiovascular disease dataset using Artificial Neural Network (ANN).

    iii.            Evaluate the performance on the system.

1.4       Scope and Limitation of the Study

The scope of this study is to diagnose cardiovascular disease using subtractive clustering and artificial neural network (ANN). Cardiovascular disease data will be collated. The collated data will be converted to numerical values follow by pre-processing and clustering of data using subtractive clustering. The clustered data will then be used to train the system using ANN and the performance of the system will be evaluated.

This study is limited to diagnosing disease of the cardiovascular system using subtractive clustering and ANN. Furthermore, this study did not consider various values or neighborhood radius in subtractive clustering algorithm.

1.5       Significance of the Study

This study would be of high importance to the medical practitioners and researchers whose aim is to perform classification of cardiovascular disease using AI technique. It can be used to assist doctors and young physicians as a tool to improve the quality of care for the cardiovascular disease patients.

This system is designed to assist doctor and health professionals in determining the diagnosis of patient data relating to cardiovascular disease. Therefore, this system could help doctors and health professionals to determine the diagnosis and analysis of the patient cardiovascular health status.

1.6       Definition of Terms

        i.            Cardiovascular System: is an organ system that permits blood to circulate and transport nutrients to and from the cells in the body.

      ii.            Cardiovascular Disease: is a general term for conditions affecting the heart or blood vessels. It is usually associated with a build-up of fatty deposits inside the arteries.

    iii.            Clustering: is a process of grouping a number of similar objects into a class.

    iv.            Artificial Neural Network: a real or virtual computer system designed to emulate the human brain in its ability to learn and to assess imprecise data.

You either get what you want or your money back. T&C Apply

Talk to us right now: (+234)906-451-7926 (Call/WhatsApp)

---

Get This Project's Source Code: CARDIOVASCULAR DISEASE DIAGNOSIS SYSTEM USING SUBTRACTIVE CLUSTERING AND ARTIFICIAL NEURAL NETWORK