Short-term mortality prediction for acute lung injury patients: External validation of the Acute Respiratory Distress Syndrome Network prediction model*
Bibliographic record
Abstract
OBJECTIVE: An independent cohort of patients with acute lung injury was used to evaluate the external validity of a simple prediction model for short-term mortality previously developed using data from Acute Respiratory Distress Syndrome Network (ARDSNet) trials. DESIGN: Data for external validation were obtained from a prospective cohort study of patients with acute lung injury. SETTING: Thirteen intensive care units at four teaching hospitals in Baltimore, MD. PATIENTS: Five hundred and eight nontrauma patients with acute lung injury. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of the 508 patients eligible for this analysis, 234 (46%) died inhospital. Discrimination of the ARDSNet prediction model for inhospital mortality, evaluated by the area under the receiver operator characteristic curves, was 0.67 for our external validation data set vs. 0.70 and 0.68 using Acute Physiology and Chronic Health Evaluation II and the ARDSNet validation data set, respectively. In evaluating calibration of the model, predicted vs. observed inhospital mortality for the external validation data set was similar for both low-risk (ARDSNet model score = 0) and high-risk (score = 3 or 4+) patient strata. However, for intermediate-risk (score = 1 or 2) patients, observed inhospital mortality was substantially higher than predicted mortality (25.3% vs. 16.5% and 40.6% vs. 31.0% for score = 1 and 2, respectively). Sensitivity analyses limiting our external validation data set to only those patients meeting the ARDSNet trial eligibility criteria and to those who received mechanical ventilation in compliance with the ARDSNet ventilation protocol did not substantially change the model's discrimination or improve its calibration. CONCLUSIONS: Evaluation of the ARDSNet prediction model using an external acute lung injury cohort demonstrated similar discrimination of the model as was observed with the ARDSNet validation data set. However, there were substantial differences in observed vs. predicted mortality among intermediate-risk patients with acute lung injury. The ARDSNet model provided reasonable, but imprecise, estimates of predicted mortality when applied to our external validation cohort of patients with acute lung injury.
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 | 0.041 | 0.053 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".