Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation

Michael W Sjoding, MD; Daniel Taylor, MS; Jonathan Motyka, MS; Elizabeth Lee, MD; Ivan Co, MD; Dru Claar, MD; Jakob I McSparron, MD; Sardar Ansari, PhD; Meeta Prasad Kerlin, MD; John P Reilly, MD; Michael G S Shashaty, MD; Brian J Anderson, MD; Tiffanie K Jones, MD; Harrison M Drebin, MD; Caroline A G Ittner, MD; Nuala J Meyer, MD; Theodore J Iwashyna, ProfMD; Kevin R Ward, ProfMD; Christopher E Gillies, PhD

The Lancet: Digital Health (Jun 2021)

Deep learning to detect acute respiratory distress syndrome on chest radiographs: a retrospective study with external validation

Michael W Sjoding, MD,
Daniel Taylor, MS,
Jonathan Motyka, MS,
Elizabeth Lee, MD,
Ivan Co, MD,
Dru Claar, MD,
Jakob I McSparron, MD,
Sardar Ansari, PhD,
Meeta Prasad Kerlin, MD,
John P Reilly, MD,
Michael G S Shashaty, MD,
Brian J Anderson, MD,
Tiffanie K Jones, MD,
Harrison M Drebin, MD,
Caroline A G Ittner, MD,
Nuala J Meyer, MD,
Theodore J Iwashyna, ProfMD,
Kevin R Ward, ProfMD,
Christopher E Gillies, PhD

Affiliations

Michael W Sjoding, MD: Division 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; Correspondence to: Dr Michael W Sjoding, University of Michigan, Ann Arbor, MI 48109, USA
Daniel Taylor, MS: Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Jonathan Motyka, MS: Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Elizabeth Lee, MD: Department of Radiology, University of Michigan Medical School, Ann Arbor, MI, USA
Ivan Co, MD: Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Dru Claar, MD: Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, USA
Jakob I McSparron, MD: Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Sardar Ansari, PhD: Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Meeta Prasad Kerlin, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
John P Reilly, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA; Center for Translational Lung Biology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Michael G S Shashaty, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Brian J Anderson, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Tiffanie K Jones, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA; Center for Translational Lung Biology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Harrison M Drebin, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA; Center for Translational Lung Biology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Caroline A G Ittner, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA; Center for Translational Lung Biology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Nuala J Meyer, MD: Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA; Center for Translational Lung Biology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
Theodore J Iwashyna, ProfMD: Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; VA Center for Clinic Management Research, Ann Arbor, MI, USA; Institute for Social Research, Ann Arbor, MI, USA
Kevin R Ward, ProfMD: Center for Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI, USA; Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA
Christopher E Gillies, PhD: Department of Emergency Medicine, University of Michigan Medical School, Ann Arbor, MI, USA; Michigan Center for Integrative Research in Critical Care; Ann Arbor, MI, USA; Michigan Institute for Data Science, University of Michigan, Ann Arbor, MI, USA

Journal volume & issue: Vol. 3, no. 6
pp. e340 – e348

Abstract

Read online

Summary: 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.

Published in The Lancet: Digital Health

ISSN: 2589-7500 (Online)
Publisher: Elsevier
Country of publisher: United Kingdom
LCC subjects: Medicine: Medicine (General): Computer applications to medicine. Medical informatics
Website: https://www.thelancet.com/journals/landig/home

About the journal