ICU sedation, delirium & recovery
Individualised treatment effects of enhanced early mobilisation in mechanically ventilated patients: a secondary analysis of the TEAM trial
Authors' conclusion
Using baseline characteristics, a machine learning model identified patients with estimated benefit or harm with enhanced EM.
Study context
- Population
- Mechanically ventilated ICU patients in the TEAM trial
- Participants
- 687 participants · 40 sites
- Comparison
- Enhanced early mobilisation vs usual care early mobilisation
- Primary endpoint
- Death
- Follow-up
- Day 180
Methodological detailscausal inference approach, machine learning, train/test split by site, fivefold cross-validation
- Causal inference approach
- Machine learning
- Train/test split by site
- Fivefold cross-validation
Primary result
As reported in the abstract
Predicted individualised treatment effects on mortality (test cohort)
- Predicted individualised treatment effects (ITEs) ranged from an absolute reduction to an increase in mortality with enhanced early mobilisation (EM)
- 34.0% reduction to 39.3% increase
- Heterogeneity of treatment effect (interaction of model predictions and treatment assignment)
- p = 0.006
Further findings
Mortality, overall cohort · day 180
- Patients who died by day 180
- 141 (20.5%)
Characteristics of predicted poor responders · baseline
- Predicted poor responders to enhanced EM more likely to receive vasopressors, have diabetes and have lower RASS scores vs predicted benefit
Original publication
Individualised treatment effects of enhanced early mobilisation in mechanically ventilated patients: a secondary analysis of the TEAM trial. Intensive Care Med. Published 24 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →