Home|Journals|Articles by Year|Audio Abstracts RSS - TOC
 

Original Research

JPAS. 2022; 22(1): 1-10


A Classification Approach for Predicting COVID-19 Patient’s Survival Outcome with Machine Learning Techniques

Abdulhameed Ado Osi, Mannir Abdu, Hussaini Garba Dikko, Usman Muhammad, Auwalu Ibrahim, Lawan Adamu Ismail, Ahamd Abubakar Suleiman, Safiya Sani Sada, Muftahu Zubairu Ringim.




Abstract

COVID-19 is an infectious disease discovered after the outbreak began in Wuhan, China, in December 2019. COVID-19 is still becoming an increasing global threat to public health. The virus has been escalated to many countries across the globe. This paper analyzed and compared the performance of three different supervised machine learning techniques; Linear Discriminant Analysis (LDA), Random Forest (RF), and Support Vector Machine (SVM) on COVID-19 dataset. The best level of accuracy between these three algorithms was determined by comparison of some metrics for assessing predictive performance such as accuracy, sensitivity, specificity, F-score, Kappa index, and ROC. From the analysis results, RF was found to be the best algorithm with 100% prediction accuracy in comparison with LDA and SVM with 95.2% and 90.9% respectively. Our analysis shows that out of these three classification models RF predicts COVID-19 patient's survival outcome with the highest accuracy. Chi-square test reveals that all the seven features except sex were significantly correlated with the COVID-19 patient's outcome (P-value < 0.005). Therefore, RF was recommended for COVID-19 patient’s outcome prediction that will help in early identification of possible sensitive cases for quick provision of quality health care, support and supervision.

Key words: COVID-19, Survival outcomes, Random Forest, Linear Discriminant Analysis, Support Vector Machine






Full-text options


Share this Article



Online Article Submission
• ejmanager.com
• ojshosting.net




eJManager.com
Review(er)s Central
JournalList
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (https://creativecommons.org/licenses/by-nc-sa/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.