Predictive Models for Intensive Care Admission and Death of COVID-19

Overview

To build simple and reliable predictive scores for intensive care admissions and deaths in COVID19 patients. These scores adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guidelines. The outcomes of the study are (i) admission in the Intensive Care Unit admission and (ii) death. All patients admitted in the Emergency Department with a positive reverse transcription-polymerase chain reaction SARS-COV2 test were included in the study. Routine clinical and laboratory data were collected at their admission and during their stay. Chest X-Rays and CT-Scans were performed and analyzed by a senior radiologist. Generalized Linear Models using a binomial distribution with a logit link function (R software version X) were used to develop predictive scores for (i) admission to ICU among emergency ward patients; (ii) death among ICU patients. A first panel of Number Models with the highest AIC (BIC) was preselected. Ten-fold cross-validation was then used to estimate the out-of-sample prediction error among these preselected models. The one with the smallest prediction error was in the end singled out .

Conditions

Interventions