Literature DB >> 33893070

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

Michael W Sjoding1, Daniel Taylor2, Jonathan Motyka2, Elizabeth Lee3, Ivan Co4, Dru Claar5, Jakob I McSparron6, Sardar Ansari7, Meeta Prasad Kerlin8, John P Reilly9, Michael G S Shashaty8, Brian J Anderson8, Tiffanie K Jones9, Harrison M Drebin9, Caroline A G Ittner9, Nuala J Meyer9, Theodore J Iwashyna10, Kevin R Ward11, Christopher E Gillies12.   

Abstract

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.
Copyright © 2021 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.

Entities:  

Year:  2021        PMID: 33893070     DOI: 10.1016/S2589-7500(21)00056-X

Source DB:  PubMed          Journal:  Lancet Digit Health        ISSN: 2589-7500


  4 in total

1.  Diagnostic performance of artificial intelligence approved for adults for the interpretation of pediatric chest radiographs.

Authors:  Hyun Joo Shin; Nak-Hoon Son; Min Jung Kim; Eun-Kyung Kim
Journal:  Sci Rep       Date:  2022-06-17       Impact factor: 4.996

Review 2.  Digital health competencies in medical school education: a scoping review and Delphi method study.

Authors:  Mark P Khurana; Daniel E Raaschou-Pedersen; Jørgen Kurtzhals; Jakob E Bardram; Sisse R Ostrowski; Johan S Bundgaard
Journal:  BMC Med Educ       Date:  2022-02-26       Impact factor: 2.463

3.  Barriers to and Facilitators for Acceptance of Comprehensive Clinical Decision Support System-Driven Care Maps for Patients With Thoracic Trauma: Interview Study Among Health Care Providers and Nurses.

Authors:  Emma K Jones; Alyssa Banks; Genevieve B Melton; Carolyn M Porta; Christopher J Tignanelli
Journal:  JMIR Hum Factors       Date:  2022-03-16

4.  Artificial intelligence-aided diagnosis model for acute respiratory distress syndrome combining clinical data and chest radiographs.

Authors:  Kai-Chih Pai; Wen-Cheng Chao; Yu-Len Huang; Ruey-Kai Sheu; Lun-Chi Chen; Min-Shian Wang; Shau-Hung Lin; Yu-Yi Yu; Chieh-Liang Wu; Ming-Cheng Chan
Journal:  Digit Health       Date:  2022-08-15
  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.