Home|Journals|Articles by Year|Audio Abstracts
 

Research Article

EEO. 2021; 20(3): 4156-4162


Ensemble Genetic Algorithms For Blood Covid-19 Diagnosis

Devvret Verma, Kumud Pant, Poonam Verma.




Abstract

The state of the world is urgent at this time. The recently discovered corona virus causes Covid-19, a devastating pandemic disease. To date, there are 3.23 million ongoing cases in India, with 59,449 fatalities. There is a lot of effort being put in by scientists and doctors to find a cure and vaccination for this. Medical advancements are being aided by research in the areas of machine learning and artificial intelligence, which are being used to forecast the development of disease and to detect the existence of the virus in the human body. The researchers here hope to learn more about COVID-19 by examining the virus in human blood samples. The study's blood samples have more than a hundred different characteristics. Therefore, the genetic algorithm has been used for feature reduction in high-dimensional data processing. This research will use a genetic algorithm to predict the presence of COVID-19 in a blood sample. About 5,644 patients' records with 111 different characteristics are included in the sample. The dimensionality reduction technique will be based on a genetic algorithm, similar to that utilised in the optimization algorithm for ant colonies for disaster relief. The programming language python is used throughout this study, and the metrics sensitivity, specificity, accuracy, and area under the curve (AUC) are used to assess the model's efficacy. The applied model has a 92% AUC, a sensitivity of 96.76 percent, a specificity of 98.80 percent, and an accuracy of 98.7 percent. The results showed that the custom algorithm was superior to the best existing solutions.

Key words: Genetic , Algorithms , Blood , Covid






Full-text options


Share this Article


Online Article Submission
• ejmanager.com




ejPort - eJManager.com
Refer & Earn
JournalList
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under Creative Commons Attribution 4.0 International License (CC BY), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.