A Systematic Review on Prediction Techniques for Cardiac Disease

A Systematic Review on Prediction Techniques for Cardiac Disease

Savita Wadhawan, Raman Maini
DOI: 10.4018/IJITSA.290001
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Mortality rate can be lowered with early prediction of cardiac diseases, which is one of the major issue in healthcare industry. In comparison of traditional methods, intelligent systems have potential to predict these diseases accurately at early stage even with complex data. Various intelligent DSS are presented by researchers for predicting this disease. To study the trends of these intelligent systems, to find the effective techniques for predicting cardiac disease and to find the future directions are the objective of this study. Therefore this paper presents a systematic review on state-of-art techniques based on ML, NN and FL. For analysis, we follow PRISMA statement and considered the studies presented from 2010 to 2020 from different databases. Analysis concluded that ML based techniques are broadly used for feature selection and classification and have the potential for the prediction of cardiac diseases. The future directions are to evaluate the rarely used prediction techniques and finding the way of improving them for model generalization with better prediction accuracy.
Article Preview
Top

1. Introduction

Health is one of society's most pressing issues, as it is continually threatened by numerous diseases and illnesses. Some diseases are incurable, while others are treatable or avoidable if caught early enough. In general, diseases are divided into two types: communicable and noncommunicable. Covid-19, Hepatitis A, Hepatitis B, and other communicable diseases spread from one person to another through a variety of routes, including blood contact, virus transmission, physical contact with an infected person, insect or animal bites, and so on. Noncommunicable diseases, on the other hand, are diseases that are not transmitted directly between humans, such as coronary heart disease. Cardiovascular illnesses are rapidly becoming the primary cause of death among non-communicable diseases. According to the Indian Heart Association, four persons between the ages of 30 - 50 die every minute in India due to heart disease. Every day, nine hundred persons under the age of 30 die from various heart conditions. One-fourth of all heart failure cases occur in people under the age of 40. According to the American Heart Association (https://www.medicalnewstoday.com/articles/237191), HD is responsible for one out of every four deaths in the United States. As a result, it has become one of the world's top causes of death.

Different types of the cardiac disease include coronary heart disease (CHD), coronary artery disease (CAD), cardiovascular diseases (CVD), arrhythmia, heart valve diseases, and heart failure. High blood pressure, elevated blood lipids, obesity, an unhealthy diet, elevated blood glucose, physical inactivity, and smoking are the leading causes of heart disease. Cardiovascular illnesses have long-term consequences if they are not treated properly. As a result, it is recommended that everyone should be examined by a heart specialist twice a year to avoid any type of cardiac trouble. Doctors recommend many medical tests such as ECG, X-rays, blood tests, MRI, and others to forecast any type of cardiac condition. Following that, these test reports are examined by experts. Because of the enormous number of patients and the scarcity of qualified physicians/experts and technicians, intelligent systems may be able to assist in the interpretation and act as a second opinion for clinicians. Researchers have presented several sophisticated DSS for the diagnosis of heart disorders. Machine learning, deep learning, evolutionary approaches, fuzzy systems, artificial neural networks, and other computational techniques are used in these systems. It has also been observed that retrieving records and making decisions from medical data is tough for humans because it contains a variety of facts such as clinical facts and EHR data.

As a result, these healthcare systems aid in better decision-making through data analysis. Machine learning algorithms offer the ability to construct such systems for the early and accurate prediction of cardiac problems based on routinely obtained medical data. Furthermore, early detection and prediction, followed by treatment, may help to lessen the severity of the condition. As a result, this work examines current state-of-the-art methodologies for detecting cardiac illness using ML, NN, and FL to identify future prospects. Data preparation, feature reductions, classification approaches, and performance matrices are all examined to see what trends and techniques exist.

The following is how the paper is structured: Section2 discusses the methods and materials, as well as the systematic review procedure. Section 3 describes the work done using several methodologies, followed by an analysis in section 4. The review comes to a close with Section 5.

Complete Article List

Search this Journal:
Reset
Volume 17: 1 Issue (2024)
Volume 16: 3 Issues (2023)
Volume 15: 3 Issues (2022)
Volume 14: 2 Issues (2021)
Volume 13: 2 Issues (2020)
Volume 12: 2 Issues (2019)
Volume 11: 2 Issues (2018)
Volume 10: 2 Issues (2017)
Volume 9: 2 Issues (2016)
Volume 8: 2 Issues (2015)
Volume 7: 2 Issues (2014)
Volume 6: 2 Issues (2013)
Volume 5: 2 Issues (2012)
Volume 4: 2 Issues (2011)
Volume 3: 2 Issues (2010)
Volume 2: 2 Issues (2009)
Volume 1: 2 Issues (2008)
View Complete Journal Contents Listing