Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 1;53(6):e1224-e1234.
doi: 10.1097/CCM.0000000000006662. Epub 2025 Apr 8.

Development and External Validation of a Detection Model to Retrospectively Identify Patients With Acute Respiratory Distress Syndrome

Elizabeth Levy  1   2   3 , Dru Claar  4 , Ivan Co  4   5 , Barry D Fuchs  1 , Jennifer Ginestra  2   6 , Rachel Kohn  1   2   3 , Jakob I McSparron  4 , Bhavik Patel  1   2   3 , Gary E Weissman  1   2   3 , Meeta Prasad Kerlin  1   2   3 , Michael W Sjoding  4
Affiliations

Development and External Validation of a Detection Model to Retrospectively Identify Patients With Acute Respiratory Distress Syndrome

Elizabeth Levy et al. Crit Care Med. .

Abstract

Objective: The aim of this study was to develop and externally validate a machine-learning model that retrospectively identifies patients with acute respiratory distress syndrome (acute respiratory distress syndrome [ARDS]) using electronic health record (EHR) data.

Design: In this retrospective cohort study, ARDS was identified via physician-adjudication in three cohorts of patients with hypoxemic respiratory failure (training, internal validation, and external validation). Machine-learning models were trained to classify ARDS using vital signs, respiratory support, laboratory data, medications, chest radiology reports, and clinical notes. The best-performing models were assessed and internally and externally validated using the area under receiver-operating curve (AUROC), area under precision-recall curve, integrated calibration index (ICI), sensitivity, specificity, positive predictive value (PPV), and ARDS timing.

Patients: Patients with hypoxemic respiratory failure undergoing mechanical ventilation within two distinct health systems.

Interventions: None.

Measurements and main results: There were 1,845 patients in the training cohort, 556 in the internal validation cohort, and 199 in the external validation cohort. ARDS prevalence was 19%, 17%, and 31%, respectively. Regularized logistic regression models analyzing structured data (EHR model) and structured data and radiology reports (EHR-radiology model) had the best performance. During internal and external validation, the EHR-radiology model had AUROC of 0.91 (95% CI, 0.88-0.93) and 0.88 (95% CI, 0.87-0.93), respectively. Externally, the ICI was 0.13 (95% CI, 0.08-0.18). At a specified model threshold, sensitivity and specificity were 80% (95% CI, 75%-98%), PPV was 64% (95% CI, 58%-71%), and the model identified patients with a median of 2.2 hours (interquartile range 0.2-18.6) after meeting Berlin ARDS criteria.

Conclusions: Machine-learning models analyzing EHR data can retrospectively identify patients with ARDS across different institutions.

Keywords: ARDS; acute lung injury; hypoxemic respiratory failure; machine learning; mechanical ventilation.

PubMed Disclaimer

Conflict of interest statement

Michael Sjoding previously received royalties for a software technology that processes chest radiograph images to detect acute respiratory distress syndrome. This software was previously licensed to AirStrip Technologies, Inc. Meeta Kerlin is a member of a data safety monitoring board unrelated to this article. Dr. Levy received funding from the National Institutes of Health (NIH). Drs. Levy, Ginestra, Kohn, Patel, and Sjoding received support for article research from the NIH. Dr. Ginestra’s institution received funding from the National Heart, Lung, and Blood Institute. Dr. McSparron received funding from UpToDate and Springer. Drs. Kerlin’s and Sjoding’s institutions received funding from the NIH. Dr. Sjoding received funding from Airstrip. The remaining authors have disclosed that they do not have any potential conflicts of interest.

Figures

Figure 1.
Figure 1.
Performance characteristics of internal validation and external validation cohorts. Model performance: A, Receiver operator curve and precision-recall curve for internal validation cohort. B, Receiver operator curve and precision-recall curve for external validation cohort.
See this image and copyright information in PMC

References

    1. Sjoding MW, Cooke CR, Iwashyna TJ, et al. : Acute respiratory distress syndrome measurement error. Potential effect on clinical study results. Ann Am Thorac Soc 2016; 13:1123–1128 - PMC - PubMed
    1. Sjoding MW, Hofer TP, Co I, et al. : Interobserver reliability of the Berlin ARDS definition and strategies to improve the reliability of ARDS diagnosis. Chest 2018; 153:361–367 - PMC - PubMed
    1. Sjoding MW, Hyzy RC: Recognition and appropriate treatment of the acute respiratory distress syndrome remains unacceptably low. Crit Care Med 2016; 44:1611–1612 - PMC - PubMed
    1. Ranieri VM, Rubenfeld GD, Thompson BT, et al. ; ARDS Definition Task Force: Acute respiratory distress syndrome: The Berlin definition. JAMA 2012; 307:2526–2533 - PubMed
    1. Bellani G, Laffey JG, Pham T, et al. ; LUNG SAFE Investigators: Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries. JAMA 2016; 315:788–800 - PubMed

Publication types

LinkOut - more resources