Respiratory failure & ventilation
Individualized Treatment Effects of Oxygen Targets in Mechanically Ventilated Critically Ill Adults
Authors' conclusion
Oxygenation targets that are individualized using machine learning analyses of randomized trials may reduce mortality for critically ill adults.
Study context
- Population
- Critically ill adults receiving invasive mechanical ventilation in intensive care unit (ICU) (US for PILOT; 21 ICUs in Australia and New Zealand for ICU-ROX)PILOT n = 1682
- Comparison
- Lower vs higher SpO2 target
- Primary endpoint
- 28-Day mortality
- Follow-up
- 28 days
Methodological detailsmachine learning model, derivation in PILOT, external validation in ICU-ROX
- Machine learning model
- Derivation in PILOT
- External validation in ICU-ROX
Primary result
As reported in the abstract
28-Day mortality: individualized treatment effect of lower vs higher SpO2 target (ICU-ROX validation cohort)
- Predicted effect of lower vs higher SpO2 target for individual patients, absolute change in 28-day mortality
- 27.2% absolute reduction to 34.4% absolute increase
- Patients predicted to benefit from lower SpO2 target had lower mortality when randomized to lower SpO2; those predicted to benefit from higher SpO2 target had lower mortality when randomized to higher SpO2 (likelihood ratio test for effect modification)
- P = .02
- Use of the SpO2 target predicted to be best for each patient, instead of the randomized SpO2 target, would have reduced absolute overall mortality by
- 6.4% (95% CI, 1.9%-10.9%)
Further findings
Characteristics of predicted benefit subgroups
- Predicted benefit from lower SpO2 target: higher prevalence of acute brain injury; from higher SpO2 target: higher prevalence of sepsis and abnormally elevated vital signs
Original publication
Individualized Treatment Effects of Oxygen Targets in Mechanically Ventilated Critically Ill Adults. JAMA. Published 9 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →