Design and Development of Hybrid Optimization-Enabled Deep Learning Model for Myocardial Infarction

Design and Development of Hybrid Optimization-Enabled Deep Learning Model for Myocardial Infarction

Shamal Bulbule, Shridevi Soma
Copyright: © 2022 |Pages: 27
DOI: 10.4018/IJSKD.313589
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Myocardial infarction is the most hazardous cardiovascular disease for humans; generally, it is acknowledged as a heart attack, which may result in death. Thus, rapid and precise detection of myocardial infarction is essential to reduce the mortality rate. This paper proposes the Taylor-enhanced invasive weed sine cosine optimization algorithm-based deep convolutional neural network (Taylor IIWSCOA-enabled DCNN) model to classify myocardial infarction. Here, the DCNN classifier is used to predict and categorize myocardial infarction, and the classifier is tuned by the Taylor IIWSCOA to attain superior efficiency. The Taylor IIWSCOA is designed by integrating SCA, IIWO approach, and the Taylor series. The proposed Taylor IIWSCOA-based DCNN approach outperforms other conventional approaches with an accuracy of 0.9412, sensitivity of 0.9535, and specificity of 0.9485.
Article Preview
Top

1. Introduction

Generally, different Cardio Vascular Diseases (CVDs), including cardiomyopathy, Coronary Heart Disease (CHD), Rheumatic Heart Disease (RHD), strokes, as well as other heart diseases, lead to mortality globally (Celermajer et al. 2012; Halder et al. 2019). CVD is a common type of disease which usually affects the heart and blood vessels. Moreover, CVD contains coronary artery infections, like angina and myocardial infarction, typically termed heart attack. The familiar types of CVDs are cardiomyopathy, valvular heart disease, heart breakdown, hypertensive heart illness, abnormal heart rhythms, stroke, carditis, venous thrombosis, peripheral artery disease, thromboembolic disease, aortic aneurysms and congenital heart disease (Halder et al. 2019). Lingering COVID-19 (Dereso, et al., 2022 ; Burrell, et al., 2022 ; Sharma, et al., 2022 ; Chauhan, et al., 2022) heart problems can complicate their recover. Mainly, the heart is the most significant organ, and it is composed of muscle tissues. Therefore, the primary usage of a coronary artery is to provide arterialized blood to heart muscles. Therefore, coronary artery disease blocks arteries, and it decreases blood supply to the downstream muscle, which produces serious injury to the heart muscle and a chance to create myocardial infarction (Lüscher 2015; Sridhar et al. 2021).

Moreover, the weakly affected contracting wall segments may develop mechanical pressure on the heart ensuing in conformational and morphological variations in reaction to left ventricular remodelling. It grades in incompetent pump functioning and heart failure (Sridhar et al. 2021). Myocardial infarction is the classic category of CVD produced by the block of coronary arteries. Besides, these blocks direct the rigorous decreasing blood stream to the myocardium. Since oxygen blood contribute is inadequate, cardiac muscle injury may happen, resulting in heart attacks (Liu et al. 2019). The most common symptoms of acute myocardial infarction are nausea, feeling weak, feeling discomfort in the neck, arm and shoulder, breaking into cold sweats, breathing shortness, chest pain and so on (Setiawan et al. 2014; Sridhar et al. 2021).

The major risk aspects connected with myocardial infarction are physical inactivity, unhealthy diets, high blood pressure, obesity, high cholesterol and diabetes (Sridhar et al. 2021). Myocardial infarction mainly happens due to the lasting damage to the heart muscle caused by speed obstacles in coronary arteries through shortage of blood supply, which leads to acute infarction and unexpected deaths. Furthermore, this enlarges endemic and incessantly destroys heart muscles if not treated early. Therefore, early and precise myocardial infarction prediction and classification (Shylaja, et al., 2020) enhances the disease detection and classification level and decreases the death rate (Halder et al. 2019). The development of digitization enables to acquisition and method ECG data in digital structure (Manikandan and Dandapat 2007; Swain et al. 2020). CAD system (Ram, et al., 2019)(Shylaja and Anandan, 2019; Ram, 2018) commonly uses ECG signal to identify cardiac disorders because these models are robust, speedy, precise, and reliable compared with traditional approaches (Sharma et al. 2018). Besides, ECG (Haribaabu and Arun, 2020) is the most appropriate modality for the premature classification of myocardial infarction because it is a simple and non-invasive assessment of cardiac conditions (Swain et al. 2020).

Complete Article List

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