Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external
Michael W Sjoding1, Daniel Taylor2, Jonathan Motyka2
1Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Center for Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA; Institute for Healthcare Policy and Innovation, University of Michigan, Ann Arbor, MI, USA.
Background:
Acute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs.
Methods:
CNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist and physicians trained in intensive care medicine. Chest radiograph data were acquired from four US hospitals.
Findings:
In an internal test set of 1560 chest radiographs from 455 patients with acute hypoxaemic respiratory failure, a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89-0·94). In the subgroup of 413 images reviewed by at least six physicians, its AUROC was 0·93 (95% CI 0·88-0·96), sensitivity 83·0% (95% CI 74·0-91·1), and specificity 88·3% (95% CI 83·1-92·8). Among images with zero of six ARDS annotations (n=155), the median CNN probability was 11%, with six (4%) assigned a probability above 50%. Among images with six of six ARDS annotations (n=27), the median CNN probability was 91%, with two (7%) assigned a probability below 50%. In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85-0·91). When radiographs annotated as equivocal were excluded, the AUROC was 0·93 (0·92-0·95).
Interpretation:
A CNN can be trained to achieve expert physician-level performance in ARDS detection on chest radiographs. Further research is needed to evaluate the use of these algorithms to support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research.
Funding:
National Institutes of Health, Department of Defense, and Department of Veterans Affairs.
More Related Videos
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
07:53Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
Related Concept Videos
01:30Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
01:30Respiratory System Abnormal Finding I: Inspection and Percussion
Inspection Findings
During an inspection, several findings may suggest the presence of respiratory distress or disease. Pursed-lip breathing, where exhalation is slowed by...
01:23Assessment of Respiration
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...
01:27Physical Assessment of the Respiratory Tract II: Inspection
Chest Configuration
The chest configuration...
01:29Assessment of Ventilation II: Respiratory Depth and Rhythm
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement:
01:23Acute Respiratory Failure-IV