COVID-19 ICU mortality prediction: a machine learning approach using SuperLearner algorithm

Abstract

Background Since the beginning of coronavirus disease 2019 (COVID-19), the development of predictive models has sparked relevant interest due to the initial lack of knowledge about diagnosis, treatment, and prognosis. The present study aimed at developing a model, through a machine learning approach, to predict intensive care unit (ICU) mortality in COVID-19 patients based on predefined clinical parameters. Results Observational multicenter cohort study. All COVID-19 adult patients admitted to 25 ICUs belonging to the VENETO ICU network (February 28th 2020-april 4th 2021) were enrolled. Patients admitted to the ICUs before 4th March 2021 were used for model training (“training set”), while patients admitted after the 5th of March 2021 were used for external validation (“test set 1”). A further group of patients (“test set 2”), admitted to the ICU of IRCCS Ca’ Granda Ospedale Maggiore Policlinico of Milan, was used for external validation. A SuperLearner machine learning algorithm was applied for model development, and both internal and external validation was performed. Clinical variables available for the model were (i) age, gender, sequential organ failure assessment score, Charlson Comorbidity Index score (not adjusted for age), Palliative Performance Score; (ii) need of invasive mechanical ventilation, non-invasive mechanical ventilation, O2 therapy, vasoactive agents, extracorporeal membrane oxygenation, continuous venous-venous hemofiltration, tracheostomy, re-intubation, prone position during ICU stay; and (iii) re-admission in ICU. One thousand two hundred ninety-three (80%) patients were included in the “training set”, while 124 (8%) and 199 (12%) patients were included in the “test set 1” and “test set 2,” respectively. Three different predictive models were developed. Each model included different sets of clinical variables. The three models showed similar predictive performances, with a training balanced accuracy that ranged between 0.72 and 0.90, while the cross-validation performance ranged from 0.75 to 0.85. Age was the leading predictor for all the considered models. Conclusions Our study provides a useful and reliable tool, through a machine learning approach, for predicting ICU mortality in COVID-19 patients. In all the estimated models, age was the variable showing the most important impact on mortality.

Secretory Phospholipase A2 and Interleukin-6 Levels as Predictive Markers of the Severity and Outcome of Patients with COVID-19 Infections

“…Secretion of PLA2-IIA aggravates damage to tissues and organs of the whole organism [ 17 , 22 , 30 ]. This may contribute to the severity and number of deaths due to COVID-19 infections [ 31 ].…”

Krebs von den Lungen 6 (KL-6) levels in COVID-19 ICU patients are associated with mortality

“…Lorenzoni et al [ 20 ], through a machine learning approach for predicting ICU mortality in COVID-19 patients, proved that age was the leading predictor, followed by total SOFA score at ICU admission, and the P/F used for SOFA calculation. In our previous experience [ 21 ] and in the present study too, patients’ characteristics at ICU admission severely conditionate the success of advanced therapeutic strategies.…”

The PROVENT-C19 registry: A study protocol for international multicenter SIAARTI registry on the use of prone positioning in mechanically ventilated patients with COVID-19 ARDS

“…Stratification for other confounding factors recorded in this registry (e.g., disease aetiology and/or clinical scoring system for organ dysfunction) may further increase the reliability of the overall treatment effectiveness. A clinical quality registry could be an opportunity to improve understanding of pathophysiologic mechanisms and to facilitate both predictive and prognostic enrichment [25,26].…”