Prognostic Value and Reproducibility of AI-assisted Analysis of Lung Involvement in COVID-19 on Low-Dose Submillisievert Chest CT: Sample Size Implications for Clinical Trials.
Journal
Radiology. Cardiothoracic imaging
ISSN: 2638-6135
Titre abrégé: Radiol Cardiothorac Imaging
Pays: United States
ID NLM: 101748663
Informations de publication
Date de publication:
Oct 2020
Oct 2020
Historique:
entrez:
29
3
2021
pubmed:
30
3
2021
medline:
30
3
2021
Statut:
epublish
Résumé
To compare the prognostic value and reproducibility of visual versus AI-assisted analysis of lung involvement on submillisievert low-dose chest CT in COVID-19 patients. This was a HIPAA-compliant, institutional review board-approved retrospective study. From March 15 to June 1, 2020, 250 RT-PCR confirmed COVID-19 patients were studied with low-dose chest CT at admission. Visual and AI-assisted analysis of lung involvement was performed by using a semi-quantitative CT score and a quantitative percentage of lung involvement. Adverse outcome was defined as intensive care unit (ICU) admission or death. Cox regression analysis, Kaplan-Meier curves, and cross-validated receiver operating characteristic curve with area under the curve (AUROC) analysis was performed to compare model performance. Intraclass correlation coefficients (ICCs) and Bland- Altman analysis was used to assess intra- and interreader reproducibility. Adverse outcome occurred in 39 patients (11 deaths, 28 ICU admissions). AUC values from AI-assisted analysis were significantly higher than those from visual analysis for both semi-quantitative CT scores and percentages of lung involvement (all P<0.001). Intrareader and interreader agreement rates were significantly higher for AI-assisted analysis than visual analysis (all ICC ≥0.960 versus ≥0.885). AI-assisted variability for quantitative percentage of lung involvement was 17.2% (coefficient of variation) versus 34.7% for visual analysis. The sample size to detect a 5% change in lung involvement with 90% power and an α error of 0.05 was 250 patients with AI-assisted analysis and 1014 patients with visual analysis. AI-assisted analysis of lung involvement on submillisievert low-dose chest CT outperformed conventional visual analysis in predicting outcome in COVID-19 patients while reducing CT variability. Lung involvement on chest CT could be used as a reliable metric in future clinical trials.
Identifiants
pubmed: 33778634
doi: 10.1148/ryct.2020200441
pmc: PMC7586438
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e200441Informations de copyright
2020 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Conflicts of interest: none declared
Références
Lancet. 1986 Feb 8;1(8476):307-10
pubmed: 2868172
Ann ICRP. 2007;37(2-4):1-332
pubmed: 18082557
JAMA. 2020 Apr 28;323(16):1574-1581
pubmed: 32250385
N Engl J Med. 2020 Feb 6;382(6):503-513
pubmed: 31995683
Radiol Cardiothorac Imaging. 2020 Apr 21;2(2):e200196
pubmed: 33778576
Radiology. 2009 Jul;252(1):263-72
pubmed: 19561260
Lancet. 2020 Feb 15;395(10223):497-506
pubmed: 31986264
Radiology. 2020 Aug;296(2):E86-E96
pubmed: 32301647
Radiology. 2020 Aug;296(2):E32-E40
pubmed: 32101510
Med Phys. 2009 Oct;36(10):4592-9
pubmed: 19928090
JAMA. 2020 Apr 14;323(14):1401-1402
pubmed: 32167523
Lancet. 2020 Apr 11;395(10231):1189-1190
pubmed: 32224299
Radiology. 2017 Dec;285(3):980-989
pubmed: 28753389
JAMA. 2020 May 26;323(20):2052-2059
pubmed: 32320003
IEEE Trans Med Imaging. 2016 Nov;35(11):2369-2380
pubmed: 27046869
Adv Virus Res. 2018;100:163-188
pubmed: 29551135
J Appl Clin Med Phys. 2017 Mar;18(2):154-162
pubmed: 28300372
Stat Med. 2011 Aug 30;30(19):2409-21
pubmed: 21611958
IEEE Trans Med Imaging. 2016 May;35(5):1252-1261
pubmed: 27046893
Radiology. 2016 Dec;281(3):737-748
pubmed: 27636027
Intensive Care Med. 2020 May;46(5):846-848
pubmed: 32125452
J Am Med Dir Assoc. 2020 Jul;21(7):928-932.e1
pubmed: 32674821
Clin Radiol. 2020 Jul;75(7):554-556
pubmed: 32359867
Biom J. 2005 Aug;47(4):458-72
pubmed: 16161804
Eur Radiol. 2020 Aug;30(8):4407-4416
pubmed: 32215691