Additional value of chest CT AI-based quantification of lung involvement in predicting death and ICU admission for COVID-19 patients.
AI
COVID-19
Chest-CT
ICU
Prognosis
Journal
Research in diagnostic and interventional imaging
ISSN: 2772-6525
Titre abrégé: Res Diagn Interv Imaging
Pays: France
ID NLM: 9918574385706676
Informations de publication
Date de publication:
Dec 2022
Dec 2022
Historique:
received:
26
06
2022
accepted:
15
11
2022
medline:
7
6
2023
pubmed:
7
6
2023
entrez:
7
6
2023
Statut:
ppublish
Résumé
We evaluated the contribution of lung lesion quantification on chest CT using a clinical Artificial Intelligence (AI) software in predicting death and intensive care units (ICU) admission for COVID-19 patients. For 349 patients with positive COVID-19-PCR test that underwent a chest CT scan at admittance or during hospitalization, we applied the AI for lung and lung lesion segmentation to obtain lesion volume (LV), and LV/Total Lung Volume (TLV) ratio. ROC analysis was used to extract the best CT criterion in predicting death and ICU admission. Two prognostic models using multivariate logistic regressions were constructed to predict each outcome and were compared using AUC values. The first model ("Clinical") was based on patients' characteristics and clinical symptoms only. The second model ("Clinical+LV/TLV") included also the best CT criterion. LV/TLV ratio demonstrated best performance for both outcomes; AUC of 67.8% (95% CI: 59.5 - 76.1) and 81.1% (95% CI: 75.7 - 86.5) respectively. Regarding death prediction, AUC values were 76.2% (95% CI: 69.9 - 82.6) and 79.9% (95%IC: 74.4 - 85.5) for the "Clinical" and the "Clinical+LV/TLV" models respectively, showing significant performance increase (+ 3.7%; p-value<0.001) when adding LV/TLV ratio. Similarly, for ICU admission prediction, AUC values were 74.9% (IC 95%: 69.2 - 80.6) and 84.8% (IC 95%: 80.4 - 89.2) respectively corresponding to significant performance increase (+ 10%: p-value<0.001). Using a clinical AI software to quantify the COVID-19 lung involvement on chest CT, combined with clinical variables, allows better prediction of death and ICU admission.
Identifiants
pubmed: 37284031
doi: 10.1016/j.redii.2022.100018
pii: S2772-6525(22)00018-7
pmc: PMC9716289
doi:
Types de publication
Journal Article
Langues
eng
Pagination
100018Informations de copyright
© 2022 The Authors. Published by Elsevier Masson SAS on behalf of Société française de radiologie.
Déclaration de conflit d'intérêts
The authors declare the following competing interest: Anna Vlachomitrou, Olivier Nempont, Heike Carolus, Alexander Schmidt-Richberg, Peng Jin, Pedro Rodrigues are Tobias Klinder are employees of Philips Healthcare.
Références
Am J Emerg Med. 2021 Jul;45:458-463
pubmed: 33039235
Radiology. 2020 Jul;296(1):172-180
pubmed: 32255413
N Engl J Med. 2020 Feb 20;382(8):727-733
pubmed: 31978945
JAMA Intern Med. 2020 Aug 1;180(8):1081-1089
pubmed: 32396163
Radiology. 2021 Jan;298(1):E18-E28
pubmed: 32729810
Radiology. 2020 Aug;296(2):E65-E71
pubmed: 32191588
Eur Radiol. 2021 Feb;31(2):795-803
pubmed: 32813105
Intensive Care Med. 2020 May;46(5):846-848
pubmed: 32125452
Eur Radiol. 2020 Aug;30(8):4381-4389
pubmed: 32193638
BMJ. 2020 Apr 7;369:m1328
pubmed: 32265220
Eur J Radiol. 2020 May;126:108961
pubmed: 32229322
Eur Radiol. 2020 Dec;30(12):6808-6817
pubmed: 32623505
J Clin Epidemiol. 2003 May;56(5):441-7
pubmed: 12812818
Radiology. 2020 Aug;296(2):E115-E117
pubmed: 32073353
J Clin Microbiol. 2020 May 26;58(6):
pubmed: 32245835
Comput Biol Med. 2020 Nov;126:104037
pubmed: 33065387
Comput Biol Med. 2021 May;132:104304
pubmed: 33691201
JAMA. 2020 Mar 17;323(11):1061-1069
pubmed: 32031570
Acad Radiol. 2020 May;27(5):603-608
pubmed: 32204987
Clin Chem Lab Med. 2020 Jun 25;58(7):1131-1134
pubmed: 32119647
IEEE J Biomed Health Inform. 2020 Dec;24(12):3576-3584
pubmed: 33108303
Nat Commun. 2021 Jan 27;12(1):634
pubmed: 33504775
J Thorac Imaging. 2020 Jul;35(4):219-227
pubmed: 32324653
Diabetes Metab Syndr. 2020 May - Jun;14(3):211-212
pubmed: 32172175
Invest Radiol. 2020 Jun;55(6):327-331
pubmed: 32118615
J Assoc Physicians India. 2020 Jul;68(7):34-42
pubmed: 32602679
Radiol Artif Intell. 2020 Dec 16;3(2):e200098
pubmed: 33928257
AJR Am J Roentgenol. 2020 Jun;214(6):1280-1286
pubmed: 32130038
IEEE Trans Med Imaging. 2020 Aug;39(8):2626-2637
pubmed: 32730213
Radiol Cardiothorac Imaging. 2020 Oct 22;2(5):e200441
pubmed: 33778634
Cell. 2020 Jun 11;181(6):1423-1433.e11
pubmed: 32416069
Radiol Artif Intell. 2020 Mar 25;2(2):e200029
pubmed: 33937821
IEEE Rev Biomed Eng. 2021;14:4-15
pubmed: 32305937
Med Image Anal. 2021 Jan;67:101860
pubmed: 33171345
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Stat Med. 2013 Apr 30;32(9):1467-82
pubmed: 23296397
Aging (Albany NY). 2020 Apr 8;12(7):6049-6057
pubmed: 32267833
Molecules. 2020 Dec 23;26(1):
pubmed: 33374759
Nat Commun. 2020 Oct 2;11(1):4968
pubmed: 33009413
Eur Radiol. 2021 Aug;31(8):6096-6104
pubmed: 33629156
Med Phys. 2011 Feb;38(2):915-31
pubmed: 21452728
Clin Infect Dis. 2020 Sep 12;71(6):1393-1399
pubmed: 32271369
Eur Respir J. 2020 Aug 6;56(2):
pubmed: 32444412
Lancet. 2020 Feb 15;395(10223):497-506
pubmed: 31986264
Lancet Respir Med. 2020 May;8(5):506-517
pubmed: 32272080
AJR Am J Roentgenol. 2020 May;214(5):1072-1077
pubmed: 32125873
Res Diagn Interv Imaging. 2022 Mar;1:100003
pubmed: 37520010
Radiology. 2021 Feb;298(2):E63-E69
pubmed: 32729811
Radiology. 2020 Apr;295(1):22-23
pubmed: 32049600
Radiology. 2020 Aug;296(2):E32-E40
pubmed: 32101510
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Lancet Respir Med. 2020 May;8(5):475-481
pubmed: 32105632
BMC Med. 2020 Feb 28;18(1):57
pubmed: 32106852
BMJ. 2020 Sep 9;370:m3339
pubmed: 32907855
Radiology. 2020 Jun;295(3):715-721
pubmed: 32053470
Radiology. 2020 Aug;296(2):E41-E45
pubmed: 32049601