Application of Machine Learning in Hospitalized Patients with Severe COVID-19 Treated with Tocilizumab

Abstract

Among the IL-6 inhibitors, tocilizumab is the most widely used therapeutic option in patients with SARS-CoV-2-associated severe respiratory failure (SRF). The aim of our study was to provide evidence on predictors of poor outcome in patients with COVID-19 treated with tocilizumab, using machine learning (ML) techniques. We conducted a retrospective study, analyzing the clinical, laboratory and sociodemographic data of patients admitted for severe COVID-19 with SRF, treated with tocilizumab. The extreme gradient boost (XGB) method had the highest balanced accuracy (93.16%). The factors associated with a worse outcome of tocilizumab use in terms of mortality were: baseline situation at the start of tocilizumab treatment requiring invasive mechanical ventilation (IMV), elevated ferritin, lactate dehydrogenase (LDH) and glutamate-pyruvate transaminase (GPT), lymphopenia, and low PaFi [ratio between arterial oxygen pressure and inspired oxygen fraction (PaO₂/FiO₂)] values. The factors associated with a worse outcome of tocilizumab use in terms of hospital stay were: baseline situation at the start of tocilizumab treatment requiring IMV or supplemental oxygen, elevated levels of ferritin, glutamate-oxaloacetate transaminase (GOT), GPT, C-reactive protein (CRP), LDH, lymphopenia, and low PaFi values. In our study focused on patients with severe COVID-19 treated with tocilizumab, the factors that were weighted most strongly in predicting worse clinical outcome were baseline status at the start of tocilizumab treatment requiring IMV and hyperferritinemia.

Keywords: COVID-19; SARS-CoV-2; cytokine release syndrome; machine learning; tocilizumab.

Figure 1

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

Figure 2

ROC curves for the five assessed machine learning predictors. Abbreviations: ROC: receiver operating characteristic, XGB: extreme gradient boost, KNN: K-nearest neighbour, DT: decision tree, SVM: support vector machine, BLDA: Bayesian linear discriminant analysis.

Figure 3

The figure shows the radar plot of the training phase (left) and validation (right) for the prediction of mortality in COVID-19 patients treat to tocilizumab. Abbreviations: AUC: area under curve, MCC: Matthew’s correlation coefficient, XGB: extreme gradient boost, KNN: K-nearest neighbour, DT: decision tree, SVM: support vector machine, BLDA: Bayesian linear discriminant analysis.