Predicting 90-day survival of patients with COVID-19: Survival of Severely Ill COVID (SOSIC) scores

• Published in: Annals of intensive care Vol. 11; no. 1; p. 170
• Main Authors: Schmidt, Matthieu, Guidet, Bertrand, Demoule, Alexandre, Ponnaiah, Maharajah, Fartoukh, Muriel, Puybasset, Louis, Combes, Alain, Hajage, David
• Format: Journal Article Web Resource
• Language: English
• Published: Cham Springer International Publishing 11.12.2021; Springer Nature B.V; SpringerOpen; Springer Science and Business Media Deutschland GmbH
• Subjects: Acute respiratory distress syndrome; Anesthesia & intensive care; Anesthesiology; Anesthésie & soins intensifs; Cardiology and cardiovascular system; Coronaviruses; COVID-19; Critical Care and Intensive Care Medicine; Critical Care Medicine; Emergency Medicine; Emerging diseases; Human health and pathology; Human health sciences; Infectious diseases; Intensive; Intensive care; Life Sciences; Mechanical ventilation; Medical prognosis; Medicine; Medicine & Public Health; Mortality; Outcome; Predictive survival model; Pulmonology and respiratory tract; Sciences de la santé humaine; Severe acute respiratory syndrome coronavirus 2; Toxicology; Acute respiratory distress syndrome; COVID-19; Predictive survival model; Mechanical ventilation; Outcome
• ISSN: 2110-5820; 2110-5820
• DOI: 10.1186/s13613-021-00956-9

Background Predicting outcomes of critically ill intensive care unit (ICU) patients with coronavirus-19 disease (COVID-19) is a major challenge to avoid futile, and prolonged ICU stays. Methods The objective was to develop predictive survival models for patients with COVID-19 after 1-to-2 weeks in ICU. Based on the COVID–ICU cohort, which prospectively collected characteristics, management, and outcomes of critically ill patients with COVID-19. Machine learning was used to develop dynamic, clinically useful models able to predict 90-day mortality using ICU data collected on day (D) 1, D7 or D14. Results Survival of Severely Ill COVID (SOSIC)-1, SOSIC-7, and SOSIC-14 scores were constructed with 4244, 2877, and 1349 patients, respectively, randomly assigned to development or test datasets. The three models selected 15 ICU-entry variables recorded on D1, D7, or D14. Cardiovascular, renal, and pulmonary functions on prediction D7 or D14 were among the most heavily weighted inputs for both models. For the test dataset, SOSIC-7’s area under the ROC curve was slightly higher (0.80 [0.74–0.86]) than those for SOSIC-1 (0.76 [0.71–0.81]) and SOSIC-14 (0.76 [0.68–0.83]). Similarly, SOSIC-1 and SOSIC-7 had excellent calibration curves, with similar Brier scores for the three models. Conclusion The SOSIC scores showed that entering 15 to 27 baseline and dynamic clinical parameters into an automatable XGBoost algorithm can potentially accurately predict the likely 90-day mortality post-ICU admission (sosic.shinyapps.io/shiny). Although external SOSIC-score validation is still needed, it is an additional tool to strengthen decisions about life-sustaining treatments and informing family members of likely prognosis.