Respiratory failure & ventilation
Early Use of a Risk-Adjusted Mechanical Ventilation Digital Quality Measure Bundle in a Large Health System
Authors' conclusion
A dQM bundle proved useful for efficiently tracking process measures related to a ventilator management QI program in a large health system, although risk-adjusted information differed depending on model constructs.
Study context
- Population
- Mechanically ventilated patients older than 16 years in 37 ICUs across 14 US hospitals37 ICUs · 14 hospitals
- Comparison
- Post-implementation vs Pre-implementation
- Outcome
- Compliance with Spontaneous Breathing Trials (SBTs), LTVV and Spontaneous Awakening Trials (SATs) (all ICUs)
Methodological detailsquality improvement program, multicentre
- Quality improvement program
- Multicentre
Main finding
As reported in the abstract
- SBT compliance improved from 81 to 97%
- Low-tidal volume ventilation (LTVV) compliance improved from 80 to 90%
- SAT compliance improved from 27 to 65%
Further findings
Unadjusted DMV
Risk model performance: hospital and ICU mortality models (C-statistic)
- Hospital mortality model C-statistic
- 0.85 (95% CI 0.84-0.85)
- ICU mortality model C-statistic
- 0.94 (95% CI 0.93-0.94)
Risk model performance: Duration of mechanical ventilation (DMV) models
- 14-d DMV model mean se (MSE)
- 0.63
- 14-d DMV model CCC
- 0.97
- Multiple classifier DMV models F1-scores range
- 0.42 to 0.59
Actual vs predicted ventilator days
- Stable pre vs post-implementation with the multiple classifier models; decreased post-implementation with the 14-d model
Risk-adjusted mortality
- Remained stable
Original publication
Early Use of a Risk-Adjusted Mechanical Ventilation Digital Quality Measure Bundle in a Large Health System. Crit Care Med. Published 12 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →