COVID-19, Mechanical Ventilation, Pneumonia
Conditions
Keywords
machine learning, COVID-19, mortality, prediction, pneumonia, mechanical ventilation
Brief summary
The objective of this study is to develop and evaluate an algorithm which accurately predicts mortality in COVID-19, pneumonia and mechanically ventilated ICU patients.
Detailed description
Retrospective study of 53,001 total ICU patients, including 9,166 patients with pneumonia and 25,895 mechanically ventilated patients, performed on the MIMIC dataset. The NPH patient dataset includes 114 patients positive for SARS-COV-2 by PCR test.
Interventions
DEVICECOViage
The COViage machine learning algorithm is designed to predict mortality in COVID-19, pneumonia and mechanically ventilated ICU patients.
Sponsors
Dascena
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Patients aged 18 years or older * Record of ICU stay
Exclusion criteria
* Patients aged less than 18 years * Patients for which there were no records of raw data or no discharge or death dates.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Mortality outcome in COVID-19 ICU patients | Through study completion, an average of 2 months | Deceased or not deceased |
| Mortality outcome in mechanically ventilated ICU patients | Through study completion, an average of 2 months | Deceased or not deceased |
| Mortality outcome in pneumonia ICU patients | Through study completion, an average of 2 months | Deceased or not deceased |
Countries
United States
Outcome results
None listed