Title: A novel deep learning-based cardiac disease classification

Authors: M. Chitra Devi; M. Ramaswami; C. Sundar

Addresses: Department of Computer Applications, Madurai Kamaraj University, Madurai, India ' Department of Computer Applications, Madurai Kamaraj University, Madurai, India ' Department of Computer Science and Engineering, Christian College of Engineering and Technology, Oddanchatram, India

Abstract: A fist-sized organ that pumps blood throughout the human body is the heart or cardiac. Cardiac disease (CAD) is one of the deadliest diseases, threatening the lives of millions of people worldwide. Nowadays, several machine learning and deep learning techniques are used for the diagnosis of cardiac disease in its early stages. The availability of large amounts of cardiac disease related medical data has aided in the development of automated machine learning and deep learning-based diagnosis systems. To overcome the limitations of traditional approaches, this paper proposes a novel deep learning PCA-1D ConvNet (one-dimensional convolution neural network) architecture for the classification of cardiac disease and non-cardiac disease and predicting the cardiac disease. The planned network achieves over 99.87% training accuracy and 99% check accuracy at the dataset along with 100% precision, 98% recall and 98.98% F1-score.

Keywords: cardiac disease; classification; deep learning; 1D ConvNet; overfitting.

DOI: 10.1504/IJBRA.2023.139124

International Journal of Bioinformatics Research and Applications, 2023 Vol.19 No.5/6, pp.412 - 429

Received: 13 Jul 2023
Accepted: 06 Nov 2023
Published online: 14 Jun 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article