Page 37 - AIH-1-3

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Predicting mortality outcomes in individual

COVID-19 patients using machine learning
algorithms

Nikolaos Kourmpanis* , Joseph Liaskos , Emmanouil Zoulias , and
John Mantas
Laboratory of Health Informatics, Department of Public Health, Faculty of Nursing, National and
Kapodistrian University of Athens, Athens, Greece

Abstract
In late 2019, the COVID-19 disease emerged, caused by the SARS-CoV-2 virus, and
has since spread worldwide, becoming a global pandemic and resulting in almost
seven million deaths to date. In addressing this global crisis, artificial intelligence
has played a crucial role, particularly through the development of predictive
models using machine learning algorithms, which have been successfully applied
to solving a multitude of problems across multiple scientific fields. The purpose of
this paper is to identify the model, or models, with the highest accuracy in predicting
a COVID-19 patient’s mortality outcome by comparing their performance metrics.
Different ML methods employed in model development include logistic regression,
decision trees, random forest, eXtreme gradient boosting (XGBoost), multi-layer
perceptrons, and the k-nearest neighbors. The metrics used for the comparison
*Corresponding author:
Nikolaos Kourmpanis of these models were accuracy, precision-recall, F1 score, area under the receiver
(nikos.kourbanis@gmail.com) operating characteristic curve (AUC-ROC), and runtime. The data used comprised the
clinical characteristics and histories of 12,425,179 individuals who attended health
Citation: Kourmpanis N, Liaskos J,
Zoulias E, Mantas J. Predicting facilities in Mexico. Following a comprehensive evaluation, the XGBoost model
mortality outcomes in individual achieved the highest overall score across all metrics. It scored 93.76% in precision,
COVID-19 patients using machine 95.47% in recall, 91.13% in F1-score, 97.86% in AUC-ROC, and had a runtime of
learning algorithms. Artif Intell
Health. 2024;1(3):31-52. 6.67306 s. Therefore, XGBoost was determined to be the preferred method for
doi: 10.36922/aih.2591 predicting the mortality outcome of COVID-19 patients.
Received: December 30, 2023
Accepted: May 9, 2024 Keywords: COVID-19; Pandemic; Machine learning; Classification algorithm
Published Online: July 22, 2024
Copyright: © 2024 Author(s).
This is an Open-Access article 1. Introduction
distributed under the terms of the
Creative Commons Attribution Coronavirus disease 2019 (COVID-19) was first identified in the Chinese city of Wuhan
1
License, permitting distribution,
and reproduction in any medium, in December 2019. On January 30, 2020, the World Health Organization (WHO)
provided the original work is classified this outbreak as a Public Health Emergency of International Concern, and on
properly cited. March 11, 2020, it declared COVID-19 a pandemic. As of December 13, 2023, there
2,3
Publisher’s Note: AccScience have been 772,386,069 confirmed cases of COVID-19 and 6,987,222 deaths reported
Publishing remains neutral with to the WHO. COVID-19 is caused by severe acute respiratory syndrome coronavirus
4
regard to jurisdictional claims in 5
published maps and institutional 2 (SARS-CoV-2), an RNA virus with a spherical shape and a genome composed of
6
affiliations. a positive-polarity single-stranded RNA. The virus enters human cells through the

Volume 1 Issue 3 (2024) 31 doi: 10.36922/aih.2591