Back to Search Start Over

Data science and the role of Artificial Intelligence in achieving the fast diagnosis of Covid-19.

Authors :
Vinod, Dasari Naga
Prabaharan, S.R.S.
Source :
Chaos, Solitons & Fractals. Nov2020, Vol. 140, pN.PAG-N.PAG. 1p.
Publication Year :
2020

Abstract

• Chest X-ray and CT scan images amalgamating with AI to identify the Covid-19. • Image diagnosis tool utilizing decision tree classifier for faster prediction. • AI innovation which provides faster results during both training and inference. • Recommended approach achieved an accuracy of 93% in CT scan images. • The present study yielded 88% precision score for chest x-ray images. The rapid spread of novel coronavirus (namely Covid-19) worldwide has alarmed a pandemic since its outbreak in the city of Wuhan, China in December 2019. While the world still tries to wrap its head around as to how to contain the rapid spread of the novel coronavirus, the pandemic has already claimed several thousand lives throughout the world. Yet, the diagnosis of virus spread in humans has proven complexity. A blend of computed tomography imaging, entire genome sequencing, and electron microscopy have been at first adapted to screen and distinguish SARS-CoV-2, the viral etiology of Covid-19. There are a less number of Covid-19 test kits accessible in hospitals because of the expanding cases every day. Accordingly, it is required to utensil a self-exposure framework as a fast substitute analysis to contain Covid-19 spreading among individuals considering the world at large. In the present work, we have elaborated a prudent methodology that helps identify Covid-19 infected people among the normal individuals by utilizing CT scan and chest x-ray images using Artificial Intelligence (AI). The strategy works with a dataset of Covid-19 and normal chest x-ray images. The image diagnosis tool utilizes decision tree classifier for finding novel corona virus infected person. The percentage accuracy of an image is analyzed in terms of precision, recall score and F1 score. The outcome depends on the information accessible in the store of Kaggle and Open-I according to their approved chest X-ray and CT scan images. Interestingly, the test methodology demonstrates that the intended algorithm is robust, accurate and precise. Our technique accomplishes the exactness focused on the AI innovation which provides faster results during both training and inference. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
09600779
Volume :
140
Database :
Academic Search Index
Journal :
Chaos, Solitons & Fractals
Publication Type :
Periodical
Accession number :
147252366
Full Text :
https://doi.org/10.1016/j.chaos.2020.110182