Back to Search Start Over

Prognosis of COVID-19 severity using DERGA, a novel machine learning algorithm.

Authors :
Asteris, Panagiotis G.
Gandomi, Amir H.
Armaghani, Danial J.
Kokoris, Styliani
Papandreadi, Anastasia T.
Roumelioti, Anna
Papanikolaou, Stefanos
Tsoukalas, Markos Z.
Triantafyllidis, Leonidas
Koutras, Evangelos I.
Bardhan, Abidhan
Mohammed, Ahmed Salih
Naderpour, Hosein
Paudel, Satish
Samui, Pijush
Ntanasis-Stathopoulos, Ioannis
Dimopoulos, Meletios A.
Terpos, Evangelos
Source :
European Journal of Internal Medicine. Jul2024, Vol. 125, p67-73. 7p.
Publication Year :
2024

Abstract

• Determining the risk for intensive care in COVID-19 patients is essential. • Artificial neural networks may provide reliable predictions. • We used a data ensemble refinement greedy algorithm (DERGA) on data from 1596 patients. • The optimal prediction model was based on only four hematological parameters. • The best prediction corresponded to a particularly high accuracy of 97.12 %. It is important to determine the risk for admission to the intensive care unit (ICU) in patients with COVID-19 presenting at the emergency department. Using artificial neural networks, we propose a new Data Ensemble Refinement Greedy Algorithm (DERGA) based on 15 easily accessible hematological indices. A database of 1596 patients with COVID-19 was used; it was divided into 1257 training datasets (80 % of the database) for training the algorithms and 339 testing datasets (20 % of the database) to check the reliability of the algorithms. The optimal combination of hematological indicators that gives the best prediction consists of only four hematological indicators as follows: neutrophil-to-lymphocyte ratio (NLR), lactate dehydrogenase, ferritin, and albumin. The best prediction corresponds to a particularly high accuracy of 97.12 %. In conclusion, our novel approach provides a robust model based only on basic hematological parameters for predicting the risk for ICU admission and optimize COVID-19 patient management in the clinical practice. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
09536205
Volume :
125
Database :
Academic Search Index
Journal :
European Journal of Internal Medicine
Publication Type :
Academic Journal
Accession number :
178045773
Full Text :
https://doi.org/10.1016/j.ejim.2024.02.037