Improved 30-Day Survival Estimation in ICU Patients: A Comparative Analysis of Different Approaches With Real-World Data*
Authors' conclusion
The competing risk approach provides more accurate estimates of 30-day survival and is less biased compared with the other methods evaluated.
Study context
- Population
- ICU patients admitted to a university ICU, 2010–2020
- Participants
- 10,581 patients
- Exposure
- Kaplan-Meier/Cox vs competing risk (Fine and Gray) vs logistic regression for 30-day survival estimation with censoring at ICU discharge
- Includedn = 10,581reference
- Outcome
- 30-day survival estimation
- Follow-up
- 30 days
Methodological detailssingle-centre cohort, single university ICU, registry-linked mortality, All patients censored at ICU discharge
- Single-centre cohort
- Single university ICU
- Registry-linked mortality
- All patients censored at ICU discharge
Main finding
As reported in the abstract
30-day survival
Observational data: associations, not effects.
Further findings
Covariate effect estimates (regression analyses, 5 variables)
- Estimates not systematically biased; Cox and logistic regression showed greater bias than competing risk regression
Original publication
Improved 30-Day Survival Estimation in ICU Patients: A Comparative Analysis of Different Approaches With Real-World Data*. Crit Care Med. Published 26 October 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →