Related Experiment Video
Updated: May 15, 2025
Surfactant Depletion Combined with Injurious Ventilation Results in a Reproducible Model of the Acute Respiratory Distress Syndrome ARDS
Published on: April 7, 2021
Development and External Validation of a Detection Model to Retrospectively Identify Patients With Acute Respiratory
Elizabeth Levy1,2,3, Dru Claar4, Ivan Co4,5
1Division of Pulmonary, Allergy and Critical Care, Department of Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA.
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.
Related Concept Videos
01:23Acute Respiratory Failure-IV
01:29Acute Respiratory Failure-V
Ensure that patients are monitored continuously for their response to therapy, including changes in...
01:19Respiratory Assessment: Purpose and Indications
Objectives and Importance:
The primary goal of respiratory assessment is to evaluate patients at early risk of clinical deterioration. Since respiratory distress often precedes other signs of declining health, breathing patterns and sounds become a...
01:30Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
01:21Acute Respiratory Failure-II
The underlying physiological abnormalities that contribute to hypoxemic respiratory failure include:
01:21Acute Respiratory Failure-I
Definition: It is defined by specific criteria based on blood gas measurements. Hypoxemia happens when the partial pressure of oxygen (PaO2) falls below 60 mmHg. At the same time,...