Heart Disease Diagnosis Using Fuzzy Supervised Learning Based on Dynamic Reduced Features

Heart Disease Diagnosis Using Fuzzy Supervised Learning Based on Dynamic Reduced Features

Walid Moudani, Mohamad Hussein, Mariam abdelRazzak, Félix Mora-Camino
Copyright: © 2019 |Pages: 26
DOI: 10.4018/978-1-5225-8185-7.ch006
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The health industry collects huge amounts of health data which, unfortunately, are not mined to discover hidden information. However, there is a lack of effective analytical tools to discover hidden relationships and trends in data. Information technologies can provide alternative approaches to the diagnosis of the heart attach disease. In this study, a proficient methodology for the extraction of significant patterns from the Coronary Heart Disease warehouses for heart attack prediction, which unfortunately continues to be a leading cause of mortality in the whole world, has been presented. For this purpose, we propose to develop an innovative fuzzy classification solution approach based on dynamic reduced sets of potential risk factors using the promising Rough Set theory which is a new mathematical approach to data analysis based on classification of objects. Therefore, we propose to validate the classification using Multi-classifier decision tree to identify the risky heart disease cases. This work is based on a dataset collected from several clinical institutions based on the medical profile of patient. Moreover, the experts' knowledge in this field has been taken into consideration in order to define the disease, its risk factors, to follow up the issue results, and to establish significant knowledge relationships between medical factors related to Coronary Heart Disease. To identify cases of heart attack, experiments of several classification techniques have been performed leading to rank the suitable techniques. The reduction of potential risk factors contributes to enumerate dynamically one or more optimal subsets of the potential risk factors of high interest which implicitly leads to reduce the complexity of the classification problems while maintaining the prediction classification quality. The performance of the proposed model is analyzed and evaluated based on set of benchmark techniques applied in this classification problem.
Chapter Preview
Top

1. Introduction

Medical diagnosis is an important but complicated task that should be performed accurately and efficiently in which its automation would be very useful and advantageous. Unfortunately, all doctors do not possess expertise in every sub specialty. Moreover, they are in many places a scarce resource. However, appropriate computer-based information and/or decision support systems can aid in enhancing medical care and in achieving clinical tests at a reduced cost. Or, efficient and accurate implementation of automated system needs a comparative study of various available techniques. Indeed, most hospitals today employ some kinds of hospital information systems to manage their healthcare or patient data (Obenshain, 2004; Usher, Laakso, James & Rowlands, 2013). These systems typically generate huge amounts of data which take the form of numbers, text, charts and images. Unfortunately, these data are rarely used to support clinical decision making. There is a wealth of hidden information in these data that is largely untapped. The main motivation of our research is to process data in order to get useful information that enables healthcare practitioners to make intelligent clinical decisions.

Complete Chapter List

Search this Book:
Reset