The Heterogeneous Effect of High PEEP strategies on Survival in Acute Respiratory Distress Syndrome: preliminary results of a data-driven analysis of randomized trials
Bibliographic record
Abstract
Background: Some ARDS patients benefit from high PEEP while others may be harmed, indicating heterogeneity of treatment effect (HTE). We applied data-driven approaches to uncover HTE and re-examined HTE previously hypothesized in literature. Methods: We identified 8 RCTs, and obtained individual patient data from 3 (ALVEOLI, LOVS, EXPRESS = train cohort). We used effect modelling to predict individualized treatment effects (28-day mortality risk difference between PEEP strategies) across subgroups stratified by observed PEEP tertiles (≤8 cmH2O, 9–11 cmH2O, ≥12 cmH2O). We also evaluated HTEs earlier hypothesized in the literature, comparing 1) patients with baseline PaO2/FiO2 (P/F) below vs. above 200 mmHg, and 2) patients with hypo- vs. hyper-inflammatory phenotypes. Results: In low PEEP tertile (≤8 cmH2O), an X-learner and S-learner were used to train final models. In the high PEEP tertile (≥12 cmH₂O), only a causal forest with forward selection was sufficient. Respiratory-system compliance (Crs) was selected during cross validation, and used to train an extra model, with predicted effects shifting from harm to benefit of high PEEP for Crs >26.5 mL/cmH2O. High PEEP benefited patients with baseline P/F ≤200 mmHg (OR 0.80, 95% CI 0.66–0.98) more than those with P/F >200 mmHg (OR 1.74, 95% CI 1.02–2.98; interaction P=0.01). This HTE was significant only when P/F was measured at low PEEP (≤8 cmH₂O). A 2nd-order interaction confirmed heterogeneity of the HTE (ie, second-order HTE) across PEEP tertiles (P=0.03). In LOVS, no HTE for high PEEP between phenotypes was found, despite earlier observed HTE in ALVEOLI trial. Preliminary conclusion: Baseline P/F predicts benefit from high PEEP if measured at low PEEP. Findings will be externally validated using 5 other RCTs (test cohort).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.135 | 0.265 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.021 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".