The Heterogeneous Effect of High PEEP strategies on Survival in Acute Respiratory Distress Syndrome: preliminary results of a data-driven analysis of randomized trials
Smit, J. M.; Krijthe, J. H.; van Bommel, J.; Sulemanji, D. S.; Villar, J.; Suarez-Sipmann, F.; Fernandez, R. L.; Zampieri, F. G.; Maia, I. S.; Cavalcanti, A. B.; Briel, M.; Meade, M. O.; Zhou, Q.; Brower, R. B.; Sinha, P.; Bartek, B.; Calfee, C. S.; Mercat, A.; Richard, J.-C.; Brochard, L.; Serpa Neto, A.; Hodgson, C.; Baedorf-Kassis, E. N.; Talmor, D.; Gommers, D.; van Genderen, M. E.; Reinders, M. J. T.; Jonkman, A. H.
Show abstract
BackgroundMixed trial results suggest that some ventilated patients with acute respiratory distress syndrome (ARDS) benefit from high PEEP while others may be harmed, indicating heterogeneity of treatment effect (HTE). This study applies data-driven predictive approaches to uncover HTE and re-examines previously hypothesized HTE. This manuscript serves as a pre-registration of planned external validation of our trained models. MethodsWe identified eight randomized trials, and obtained individual patient data (IPD) from three of them (ALVEOLI, LOVS, EXPRESS), as our train cohort. We used effect modelling to predict individualized treatment effects (predicted 28-day mortality risk difference between PEEP strategies) across patient subgroups stratified by observed tertiles ([≤]8 cmH2O, 9-11 cmH2O, [≥]12 cmH2O). Candidate effect modelling methods included meta-learners and technique-specific methods. Optimal methods were selected through leave-one-trial-out cross-validation, evaluating the methods performances in each PEEP tertile using AUC-benefit. We trained final models using the best performing methods implemented with or without forward selection (which yielded sufficient AUC-benefit), and additional final models by selecting the variables that yielded consistency in the forward selections performed in the cross validation, if any. We further evaluated earlier hypothesized HTE comparing (1) patients with baseline PaO2/FiO2 [≤] 200 versus > 200 mmHg, and (2) patients with hypoinflammatory versus hyperinflammatory subphenotypes. Preliminary findingsIn the lower PEEP tertile ([≤]8 cmH2O), an X-learner implemented without, and an S-learner implemented with forward selection (both with flexible base learners), yielded the highest AUC benefits and were used to train final models. In the high PEEP tertile ([≥]12 cmH2O), only the causal forest implemented with forward selection yielded an AUC benefit exceeding zero. Respiratory-system compliance (CRS) was consistently selected in the forward selections of cross validation, and was used to train an extra final causal forest model, with predicted effects shifting from harm to benefit for CRS 26.5 mL/cmH2O or higher. Higher PEEP benefited patients with baseline PaO2/FiO2 [≤]200 mmHg (OR 0.80, 95% CI 0.66-0.98), incurred harm among those with PaO2/FiO2 >200 mmHg (OR 1.74, 95% CI 1.02-2.98; interaction P=0.01). This HTE was strongest when PaO2/FiO2 was measured at low PEEP ([≤]8 cmH2O), reduced at mid-level PEEP (9-11 cmH2O), and negligible at high PEEP ([≥]12 cmH2O). A second-order interaction showed significant heterogeneity of HTE (ie, second-order heterogeneity) across PEEP tertiles (P=0.03). Preliminary ConclusionsOur preliminary findings indicated that baseline CRS [≥] 26.5 mL/cmH2O predicts benefit, while CRS < 26.5 mL/cmH2O predicts harm from high PEEP when CRS is measured at high baseline PEEP ([≥]12 cmH2O). Similarly, baseline PaO2/FiO2 [≤] 200 mmHg predicts benefit, while PaO2/FiO2 > 200 mmHg predicts harm from high PEEP when PaO2/FiO2 is measured at a low baseline PEEP ([≤]8 cmH2O). Using data from the LOVS trial, we investigated HTE for high PEEP between hypo- and hyperinflammatory subphenotypes but found none, despite significant HTE observed earlier in the ALVEOLI trial.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.