NCT04401228

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

Status unknown Last updated 26 May 2020

What this trial tests

trial testing predict admission of covid-19 patients to ICU and death with routine and quickly avalaible clinical, biological and radiological variables? in COVID19 in 60 participants. Status unknown.

Timeline

1 March 2020

Primary endpoint
1 May 2020

1 January 2021

Quick facts

Lead sponsor	Clinique Saint Pierre Ottignies
Status	Status unknown
Study type	OBSERVATIONAL
Enrollment	60
Start date	1 March 2020
Primary completion	1 May 2020
Estimated completion	1 January 2021
Sites	1 location across Belgium

Drugs / interventions tested

• predict admission of covid-19 patients to ICU and death with routine and quickly avalaible clinical, biological and radiological variables?

Conditions studied

• COVID19 — all drugs for COVID19 →
• Pneumonia, Viral — all drugs for Pneumonia, Viral →
• Inflammatory Response — all drugs for Inflammatory Response →

Sponsor

Clinique Saint Pierre Ottignies — full company profile →

Who can join

18 and older, any sex, with COVID19 or Pneumonia, Viral. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

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 .

Publications & conference data

1 peer-reviewed publication reference this trial (live from Europe PMC):

1. Decoding mechanisms and protein markers in lung-brain axis.
   Huang S, Zhou Y, Ji H, Zhang T, et al · · 2025 · cited 7× · PMID 40390067 · DOI 10.1186/s12931-025-03272-z