Title: Methods of predicting coronary heart disease using machine learning

Authors: Rita Roy; Appa Rao Giduturi

Addresses: Department of Computer Science and Engineering, GITAM Institute of Technology GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, India ' Department of Computer Science and Engineering, GITAM Institute of Technology GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, India

Abstract: With the high speed in extensive grouping information medical services system, around 610,000 annual deaths, i.e., four in one death due to coronary artery disease (CAD), a total of 17.8 million deaths annually, and precise forecast in the discovery of cellular breakdown in the coronary artery disease at ahead of schedule symptoms, machine learning (ML) gives the most innovative possible solution. In this paper, we are aliening out of ML techniques to plan a design for effective classification of pictures and phases of cellular breakdown in coronary artery disease as far as possible. Here, we applied coronary artery disease diagnosed by exercise stress test and electrocardiogram image by combining binary classification (enhanced AdaBoost technique) and multi-class classification data gathered by connecting IoT sensor-based device in hand and blood profile levels. Our methodology shows different strategies by accomplishing strength even when expanding dataset size and error rate. It performs 88% exactness, and various measurements are AUC-0.88, a misclassification rate through which it was demonstrated that the Adabooster classifier beats other classifiers.

Keywords: machine learning; coronary artery disease; CAD; Adabooster; cellular breakdown.

DOI: 10.1504/IJCVR.2026.156255

International Journal of Computational Vision and Robotics, 2026 Vol.17 No.3, pp.316 - 337

Received: 16 Jan 2023
Accepted: 15 Nov 2023
Published online: 08 Sep 2026 *

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