Citation: Pezoulas, V.C.; Kourou,
K.D.; Papaloukas, C.; Triantafyllia, V.;
Lampropoulou, V.; Siouti, E.;
Papadaki, M.; Salagianni, M.;
Koukaki, E.; Rovina, N.; et al. A
Multimodal Approach for the Risk
Prediction of Intensive Care and
Mortality in Patients with COVID-19.
Diagnostics 2022, 12, 56. https://
doi.org/10.3390/diagnostics12010056
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 26 November 2021
Accepted: 26 December 2021
Published: 28 December 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Multimodal Approach for the Risk Prediction of Intensive
Care and Mortality in Patients with COVID-19
Vasileios C. Pezoulas
1
, Konstantina D. Kourou
1
, Costas Papaloukas
1,2
, Vassiliki Triantafyllia
3
,
Vicky Lampropoulou
3
, Eleni Siouti
3
, Maria Papadaki
3
, Maria Salagianni
3
, Evangelia Koukaki
4
,
Nikoletta Rovina
4
, Antonia Koutsoukou
4
, Evangelos Andreakos
3
and Dimitrios I. Fotiadis
1,5,
*
1
Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and
Engineering, University of Ioannina, GR45110 Ioannina, Greece; bpezoulas@gmail.com (V.C.P.);
Konstadina.Kourou@gmail.com (K.D.K.); papalouk@uoi.gr (C.P.)
2
Department of Biological Applications and Technology, University of Ioannina, GR45100 Ioannina, Greece
3
Laboratory of Immunobiology, Center for Clinical, Experimental Surgery and Translational Research,
Biomedical Research Foundation of the Academy of Athens, GR11527 Athens, Greece;
vtriantafyllia@bioacademy.gr (V.T.); vickylampro@gmail.com (V.L.); esiouti@bioacademy.gr (E.S.);
mpapadaki@bioacademy.gr (M.P.); msalagianni@bioacademy.gr (M.S.); vandreakos@bioacademy.gr (E.A.)
4
Intensive Care Unit (ICU), 1st Department of Respiratory Medicine, Medical School, National and
Kapodistrian University of Athens, ‘Sotiria’ General Hospital of Chest Diseases, GR11527 Athens, Greece;
e.koukaki@yahoo.gr (E.K.); nikrovina@med.uoa.gr (N.R.); koutsoukou@yahoo.gr (A.K.)
5
Department of Biomedical Research, Foundation for Research and Technology-Hellas, Institute of Molecular
Biology and Biotechnology (FORTH-IMBB), GR45110 Ioannina, Greece
* Correspondence: fotiadis@uoi.gr; Tel.: +30-265-100-9006
Abstract:
Background: Although several studies have been launched towards the prediction of
risk factors for mortality and admission in the intensive care unit (ICU) in COVID-19, none of
them focuses on the development of explainable AI models to define an ICU scoring index using
dynamically associated biological markers. Methods: We propose a multimodal approach which
combines explainable AI models with dynamic modeling methods to shed light into the clinical
features of COVID-19. Dynamic Bayesian networks were used to seek associations among cytokines
across four time intervals after hospitalization. Explainable gradient boosting trees were trained to
predict the risk for ICU admission and mortality towards the development of an ICU scoring index.
Results: Our results highlight LDH, IL-6, IL-8, Cr, number of monocytes, lymphocyte count, TNF
as risk predictors for ICU admission and survival along with LDH, age, CRP, Cr, WBC, lymphocyte
count for mortality in the ICU, with prediction accuracy 0.79 and 0.81, respectively. These risk factors
were combined with dynamically associated biological markers to develop an ICU scoring index
with accuracy 0.9. Conclusions: to our knowledge, this is the first multimodal and explainable AI
model which quantifies the risk of intensive care with accuracy up to 0.9 across multiple timepoints.
Keywords: COVID-19; artificial intelligence; dynamic modeling; risk predictors; ICU scoring index
1. Introduction
The most severe pandemic of our time known as coronavirus disease 2019 (COVID-19),
is consistently yielding grievous impacts in the global healthcare system. COVID-19 is
caused by severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) which
was officially confirmed in January 2020 after the initial COVID-19 outbreak that took
place in November 2019. Recent studies have shown that SARS-CoV-2 shares genetic
similarities with its predecessor, the SARS-CoV [
1
], where genome sequence analysis has
indicated that SARS-CoV-2 belongs to the Betacoronavirus genus, which includes the SARS-
CoV, and the Middle East respiratory syndrome coronavirus (MERS-CoV) [
2
]. However,
phylogenetic tree analysis has shown that SARS-CoV-2 is more related to Bat SARS-like
coronaviruses, such as SARS-CoV and less related to MERS-CoV [
3
]. The uniqueness of
Diagnostics 2022, 12, 56. https://doi.org/10.3390/diagnostics12010056 https://www.mdpi.com/journal/diagnostics
