Respiratory failure & ventilation

Association of Acute Respiratory Distress Syndrome Radiographic Findings Identified by Machine Learning and Outcomes of Patients Receiving Invasive Mechanical Ventilation

Crit Care MedPublished Retrospective cohort study

Authors' conclusion

A deep learning-derived ARDS-CXR score quantifying radiographic findings of ARDS independently predicted mortality and ventilator outcomes beyond hypoxemia and illness severity. Algorithmically derived markers of lung injury severity from chest imaging could be used to support clinical care decisions, predictive enrichment in research studies, or incorporated into a future ARDS definition.

Study context

Population
Adult patients with CXRs performed at the time of invasive mechanical ventilation initiationpatients receiving invasive mechanical ventilation
Participants
6,591 patients
Exposure
Positive score vs Negative score
  • Positive scoren = 1,089
Outcome
ARDS-CXR score distribution
Methodological detailsSingle academic medical center
  • Single academic medical center

Main finding

As reported in the abstract

Median ARDS-CXR score (acute respiratory distress syndrome (ARDS) probability of 15%)

−2.09

Patients with a positive score (ARDS probability above 50%)

1089

17%

Observational data: associations, not effects.

Further findings

Twenty-eight-day mortality · 28 days

Mortality by ARDS-CXR score below the ARDS threshold

Mortality at a score of −2
12.8%
Mortality at a score of −1
19.9%
Mortality at a score of 0
27.5%

Discrimination of 28-day mortality (area under the receiver operating characteristic (AUROC))

ARDS-CXR score AUROC
0.68 (95% CI, 0.66-0.70)
Pao2/Fio2 AUROC
0.64 (95% CI, 0.62-0.66)

28-day mortality or time to extubation per 1-point increase in ARDS-CXR score, adjusted for Pao2/Fio2 or Acute Physiology and Chronic Health Evaluation-IV

Significantly associated with higher 28-day mortality or prolonged time to extubation
  • Adjusted for either Pao2/Fio2 or Acute Physiology and Chronic Health Evaluation-IV

Original publication

Association of Acute Respiratory Distress Syndrome Radiographic Findings Identified by Machine Learning and Outcomes of Patients Receiving Invasive Mechanical Ventilation. Crit Care Med. Published 23 October 2026. doi:10.1097/ccm.0000000000007384

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.