Title: Non-invasive prediction mechanism for COVID-19 disease using machine learning algorithms

Authors: Arnav Bhardwaj; Hitesh Agarwal; Anuj Rani; Prakash Srivastava; Manoj Kumar; Sunil Gupta

Addresses: Department of Computer Science and Engineering, ASET, Amity University, Uttar Pradesh, India ' Department of Computer Science and Engineering, ASET, Amity University, Uttar Pradesh, India ' Department of Computer Science, GL Bajaj Institute of Technology and Management, Greater Noida, India ' Department of Computer Science and Engineering, Graphic Era (Deemed to be University), Dehradun, India ' Faculty of Engineering and Information Sciences, University of Wollongong in Dubai, Dubai Knowledge Park, Dubai, UAE ' School of Computer Science, University of Petroleum and Energy Studies, Dehradun, India

Abstract: This paper has focused on developing a model to detect non-diagnostically whether the person is infected with the COVID-19 disease using all relevant symptoms and details mentioned by the person and then comparing it with a pre-defined dataset of positive cases using machine learning. Different models have been developed to predict the same but none of them focused on the detection of COVID-19 based on symptoms. In a developing nation with a huge population, where the diagnostic availability is scarce, just scanning the body temperature will not help in detection of COVID-19 of a particular individual. This paper presents a model that can predict COVID-19 cases without any testing kit to an accuracy of 99.30%, performing better than other similar approaches with objective to put forward a method that can reduce the need of producing testing kits and also the need to wait for hours before we get the results.

Keywords: COVID-19; non-invasive; symptoms; machine learning.

DOI: 10.1504/IJCIS.2024.137406

International Journal of Critical Infrastructures, 2024 Vol.20 No.2, pp.111 - 124

Received: 21 Jun 2022
Accepted: 20 Jul 2022
Published online: 18 Mar 2024 *

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