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

Panagiotis G Asteris; Amir H Gandomi; Danial J Armaghani; Styliani Kokoris; Anastasia T Papandreadi; Anna Roumelioti; Stefanos Papanikolaou; Markos Z Tsoukalas; Leonidas Triantafyllidis; Evangelos I Koutras; Abidhan Bardhan; Ahmed Salih Mohammed; Hosein Naderpour; Satish Paudel; Pijush Samui; Ioannis Ntanasis-Stathopoulos; Meletios A Dimopoulos; Evangelos Terpos

doi:10.1016/j.ejim.2024.02.037

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

Eur J Intern Med. 2024 Mar 7:S0953-6205(24)00094-3. doi: 10.1016/j.ejim.2024.02.037. Online ahead of print.

Authors

Panagiotis G Asteris¹, Amir H Gandomi², Danial J Armaghani³, Styliani Kokoris⁴, Anastasia T Papandreadi⁵, Anna Roumelioti⁶, Stefanos Papanikolaou⁷, Markos Z Tsoukalas¹, Leonidas Triantafyllidis¹, Evangelos I Koutras¹, Abidhan Bardhan⁸, Ahmed Salih Mohammed⁹, Hosein Naderpour¹⁰, Satish Paudel¹¹, Pijush Samui⁸, Ioannis Ntanasis-Stathopoulos¹², Meletios A Dimopoulos¹², Evangelos Terpos¹³

Affiliations

¹ Computational Mechanics Laboratory, School of Pedagogical and Technological Education, Athens, Greece.
² Faculty of Engineering & IT, University of Technology Sydney, Sydney, NSW 2007, Australia; University Research and Innovation Center (EKIK), Óbuda University, 1034 Budapest, Hungary.
³ School of Civil and Environmental Engineering, University of Technology Sydney, NSW 2007, Australia.
⁴ Laboratory of Hematology and Hospital Blood Transfusion Department, University General Hospital "Attikon", National and Kapodistrian University of Athens, Medical School, Greece.
⁵ Software and Applications Department, University General Hospital "Attikon", National and Kapodistrian University of Athens, Medical School, Greece.
⁶ Department of Hematology and Lymphoma BMTU, Evangelismos General Hospital, Athens, Greece.
⁷ NOMATEN Centre of Excellence, National Center for Nuclear Research, ulica A. Sołtana 7, 05-400 Swierk/Otwock, Poland.
⁸ Civil Engineering Department, National Institute of Technology Patna, Bihar, India.
⁹ Engineering Department, American University of Iraq, Sulaimani, Kurdistan-Region, Iraq.
¹⁰ Institute of Industrial Science, University of Tokyo, Tokyo, Japan.
¹¹ Department of Civil and Environmental Engineering, University of Nevada, Reno, US.
¹² Department of Clinical Therapeutics, Medical School, Faculty of Medicine, National Kapodistrian University of Athens, Athens, Greece.
¹³ Department of Clinical Therapeutics, Medical School, Faculty of Medicine, National Kapodistrian University of Athens, Athens, Greece. Electronic address: eterpos@med.uoa.gr.

PMID: 38458880
DOI: 10.1016/j.ejim.2024.02.037

Abstract

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.

Keywords: Artificial intelligence; COVID-19; Classification algorithms; DERGA; Genetic; SARS-CoV2; hematological markers.