Cardiovascular disease prognosis and severity analysis using hybrid heuristic methods

Cardiovascular Disease (CVD) prediction is one of the difficult tasks in the medical industry because the attained Magnetic Resonance Imaging (MRI) contains more noise. Also, the classification of disease types in imbalanced data is more complex. To overcome these issues, this research developed a n...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2021-02, Vol.80 (5), p.7939-7965
Main Authors: Kumar, Mikkili Dileep, Ramana, K. V.
Format: Article
Language:English
Subjects:
Algorithms
Ant colony optimization
Arrhythmia
Artificial neural networks
Cardiovascular disease
Classification
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Fuzzy logic
Heart diseases
Heuristic methods
Magnetic resonance imaging
Multimedia Information Systems
Special Purpose and Application-Based Systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cardiovascular Disease (CVD) prediction is one of the difficult tasks in the medical industry because the attained Magnetic Resonance Imaging (MRI) contains more noise. Also, the classification of disease types in imbalanced data is more complex. To overcome these issues, this research developed a new approach for classifying CVD and severity analysis. Initially, the MRI is taken for several CVD patients and the unwanted effects are removed using a novel Hannmean filter. Subsequently, an innovative Cat Fuzzy Neural Model (CFuNM) is developed for classifying CVD diseases such as heart attack, angina, stroke, arrhythmia, and coronary heart diseases. Also, a novel Hybrid Ant Colony African Buffalo Optimization (HAC-ABO) is introduced for analyzing severity and segment the affected part from the MRI. Moreover, the simulation of this research is done by MATLAB R2018b and the simulation outcomes illustrate the performance of the proposed algorithm by obtaining high classification accuracy. Finally, the parameters of the proposed approach are evaluated and compared with existing methods.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-020-10000-w