Predictive Model for Mortality in Severe COVID-19 Patients across the Six Pandemic Waves

Abstract

The impact of SARS-CoV-2 infection remains substantial on a global scale, despite widespread vaccination efforts, early therapeutic interventions, and an enhanced understanding of the disease's underlying mechanisms. At the same time, a significant number of patients continue to develop severe COVID-19, necessitating admission to intensive care units (ICUs). This study aimed to provide evidence concerning the most influential predictors of mortality among critically ill patients with severe COVID-19, employing machine learning (ML) techniques. To accomplish this, we conducted a retrospective multicenter investigation involving 684 patients with severe COVID-19, spanning from 1 June 2020 to 31 March 2023, wherein we scrutinized sociodemographic, clinical, and analytical data. These data were extracted from electronic health records. Out of the six supervised ML methods scrutinized, the extreme gradient boosting (XGB) method exhibited the highest balanced accuracy at 96.61%. The variables that exerted the greatest influence on mortality prediction encompassed ferritin, fibrinogen, D-dimer, platelet count, C-reactive protein (CRP), prothrombin time (PT), invasive mechanical ventilation (IMV), PaFi (PaO₂/FiO₂), lactate dehydrogenase (LDH), lymphocyte levels, activated partial thromboplastin time (aPTT), body mass index (BMI), creatinine, and age. These findings underscore XGB as a robust candidate for accurately classifying patients with COVID-19.

Keywords: COVID-19; SARS-CoV-2; XGB; coagulation disorder; cytokine release syndrome; machine learning.

Figure 1

The figure shows the scheme followed in the learning and testing process of this work.

Figure 2

Graphical representation of balanced accuracy (BA), recall, precision, and F1 score values (top), and Kappa index, MCC, AUC, and DYI (bottom) in percentages. Abbreviations: AUC: area under curve; BLDA: Bayesian linear discriminant analysis; DT: decision tree; DYI: degenerated Younden index; GNB: Gaussian naïve Bayes; KNN: K-nearest neighbors; MCC: Matthew’s correlation coefficient; SVM: support vector machine; XGB: extreme gradient boost.

Figure 3

ROC curves for the six assessed machine learning predictors. Abbreviations: BLDA: Bayesian linear discriminant analysis; DT: decision tree; GNB: Gaussian naïve Bayes; KNN: K-nearest neighbors; ROC: receiver operating characteristic; SVM: support vector machine; XGB: extreme gradient boost.

Figure 4

Radar plot of the training phase (top) and test (bottom) for prediction of mortality in patients with severe COVID-19. AUC: area under curve; BA: balanced accuracy; BLDA: Bayesian linear discriminant analysis; DT: decision tree; DYI: degenerated Younden index; GNB: Gaussian naïve Bayes; KNN: K-nearest neighbors; MCC: Matthew’s correlation coefficient; SVM: support vector machine; XGB: extreme gradient boost.

Figure 5

Graphical representation of the predictive variables with the most significant impact on classifying severe COVID-19 patients in terms of mortality. Abbreviations: CRP: C-reactive protein; PT: prothrombin time; IMV: invasive mechanical ventilation; PaFi: ratio between arterial oxygen pressure and the fraction of inspired oxygen (PaO₂/FiO₂); LDH: lactate dehydrogenase; aPTT: activated partial thromboplastin time; BMI: body mass index.

Figure 6

Graphical representation of the number of patients included in the study according to dates throughout the six pandemic waves and until the end of the study.