Individualized Treatment Effects of Bougie versus Stylet for Tracheal Intubation in Critical Illness
Authors' conclusion
In this hypothesis-generating secondary analysis of a randomized trial with no average treatment effect and no treatment effect in any prespecified subgroups, a causal forest machine learning algorithm identified patients who appeared to benefit from the use of a bougie over a stylet and from the use of a stylet over a bougie using complex interactions between baseline patient and operator characteristics.
Study context
- Population
- Critically ill adults undergoing tracheal intubation in the BOUGIE trial544 validation cohort
- Participants
- 1,102 adults
- Comparison
- Bougie vs stylet for tracheal intubation
- Primary endpoint
- Modification of the effect of trial group assignment on the primary outcome (successful intubation on first attempt) by model-predicted individualized treatment effects
Methodological detailsmachine learning (causal forest), training and validation cohorts, hypothesis-generating, Causal forest trained on first half of trial (558 [50.6%]), validated on second half (544 [49.4%])
- Machine learning (causal forest)
- Training and validation cohorts
- Hypothesis-generating
- Causal forest trained on first half of trial (558 [50.6%]), validated on second half (544 [49.4%])
Primary result
As reported in the abstract
Effect modification by predicted individualized treatment effects (validation cohort)
Individualized treatment effects significantly modified effect of group assignment on primary outcome; P value for interaction
0.02
Adjusted qini coefficient
2.46
Further findings
Most important model variables
- Difficult airway characteristics, BMI, and APACHE II score
Original publication
Individualized Treatment Effects of Bougie versus Stylet for Tracheal Intubation in Critical Illness. Am J Respir Crit Care Med. Published 15 June 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →