Precision of CT-derived alveolar recruitment assessed by human observers and a machine learning algorithm in moderate and severe ARDS.
Acute respiratory distress syndrome
Alveolar recruitment
Bias
Computed tomography
Machine learning
Measurement error
Repeatability
Reproducibility
Journal
Intensive care medicine experimental
ISSN: 2197-425X
Titre abrégé: Intensive Care Med Exp
Pays: Germany
ID NLM: 101645149
Informations de publication
Date de publication:
17 Feb 2023
17 Feb 2023
Historique:
received:
21
10
2022
accepted:
24
01
2023
entrez:
16
2
2023
pubmed:
17
2
2023
medline:
17
2
2023
Statut:
epublish
Résumé
Assessing measurement error in alveolar recruitment on computed tomography (CT) is of paramount importance to select a reliable threshold identifying patients with high potential for alveolar recruitment and to rationalize positive end-expiratory pressure (PEEP) setting in acute respiratory distress syndrome (ARDS). The aim of this study was to assess both intra- and inter-observer smallest real difference (SRD) exceeding measurement error of recruitment using both human and machine learning-made lung segmentation (i.e., delineation) on CT. This single-center observational study was performed on adult ARDS patients. CT were acquired at end-expiration and end-inspiration at the PEEP level selected by clinicians, and at end-expiration at PEEP 5 and 15 cmH Thirteen patients were included, of whom 11 (85%) presented a severe ARDS. Intra- and inter-observer measurements of recruitment were virtually unbiased, with 95% confidence intervals (CI The SRD exceeding intra-observer experimental error in the measurement of alveolar recruitment may be conservatively set to 5% (i.e., the upper value of the CI
Sections du résumé
BACKGROUND
BACKGROUND
Assessing measurement error in alveolar recruitment on computed tomography (CT) is of paramount importance to select a reliable threshold identifying patients with high potential for alveolar recruitment and to rationalize positive end-expiratory pressure (PEEP) setting in acute respiratory distress syndrome (ARDS). The aim of this study was to assess both intra- and inter-observer smallest real difference (SRD) exceeding measurement error of recruitment using both human and machine learning-made lung segmentation (i.e., delineation) on CT. This single-center observational study was performed on adult ARDS patients. CT were acquired at end-expiration and end-inspiration at the PEEP level selected by clinicians, and at end-expiration at PEEP 5 and 15 cmH
RESULTS
RESULTS
Thirteen patients were included, of whom 11 (85%) presented a severe ARDS. Intra- and inter-observer measurements of recruitment were virtually unbiased, with 95% confidence intervals (CI
CONCLUSIONS
CONCLUSIONS
The SRD exceeding intra-observer experimental error in the measurement of alveolar recruitment may be conservatively set to 5% (i.e., the upper value of the CI
Identifiants
pubmed: 36797424
doi: 10.1186/s40635-023-00495-6
pii: 10.1186/s40635-023-00495-6
pmc: PMC9934943
doi:
Types de publication
Journal Article
Langues
eng
Pagination
8Informations de copyright
© 2023. The Author(s).
Références
Crit Care Med. 2019 Sep;47(9):1177-1183
pubmed: 31419216
Front Physiol. 2022 Feb 04;12:725865
pubmed: 35185592
Med Image Anal. 2020 Feb;60:101592
pubmed: 31760194
Intensive Care Med. 2010 Nov;36(11):1836-44
pubmed: 20689909
JAMA. 2012 Jun 20;307(23):2526-33
pubmed: 22797452
Intensive Care Med. 2013 Jan;39(1):66-73
pubmed: 22990871
JAMA. 1993 Dec 22-29;270(24):2957-63
pubmed: 8254858
BMJ. 1996 Jun 29;312(7047):1654
pubmed: 8664723
N Engl J Med. 2000 May 4;342(18):1301-8
pubmed: 10793162
Intensive Care Med. 2022 Aug;48(8):995-1008
pubmed: 35833958
IEEE Trans Med Imaging. 2009 Aug;28(8):1251-65
pubmed: 19211338
Stat Methods Med Res. 2015 Feb;24(1):107-40
pubmed: 24919828
Am Rev Respir Dis. 1987 Sep;136(3):730-6
pubmed: 3307572
Am J Respir Crit Care Med. 2007 Jan 15;175(2):160-6
pubmed: 17038660
JAMA. 2016 Feb 23;315(8):788-800
pubmed: 26903337
N Engl J Med. 2004 Jul 22;351(4):327-36
pubmed: 15269312
Stat Methods Med Res. 1999 Jun;8(2):135-60
pubmed: 10501650
Front Physiol. 2021 Sep 14;12:676118
pubmed: 34594233
N Engl J Med. 2006 Apr 27;354(17):1775-86
pubmed: 16641394
Crit Care. 2022 Jul 2;26(1):195
pubmed: 35780154
Biom J. 2008 Jun;50(3):346-63
pubmed: 18481363
Intensive Care Med. 2012 Oct;38(10):1573-82
pubmed: 22926653
Crit Care. 2021 Feb 24;25(1):81
pubmed: 33627160
Acta Anaesthesiol Scand. 2004 Oct;48(9):1123-9
pubmed: 15352958
PLoS One. 2013 Sep 09;8(9):e73990
pubmed: 24040139
Intensive Care Med. 2008 Nov;34(11):2044-53
pubmed: 18537024
Anesthesiology. 1988 Dec;69(6):824-32
pubmed: 3057937
Intensive Care Med. 1996 Jul;22(7):707-10
pubmed: 8844239
Lancet Respir Med. 2019 Oct;7(10):870-880
pubmed: 31399381