Visceral Adiposity and Severe COVID-19 Disease: Application of an Artificial Intelligence Algorithm to Improve Clinical Risk Prediction.
COVID-19 disease
artificial intelligence
visceral adiposity
Journal
Open forum infectious diseases
ISSN: 2328-8957
Titre abrégé: Open Forum Infect Dis
Pays: United States
ID NLM: 101637045
Informations de publication
Date de publication:
Jul 2021
Jul 2021
Historique:
received:
01
03
2021
accepted:
26
05
2021
entrez:
14
7
2021
pubmed:
15
7
2021
medline:
15
7
2021
Statut:
epublish
Résumé
Obesity has been linked to severe clinical outcomes among people who are hospitalized with coronavirus disease 2019 (COVID-19). We tested the hypothesis that visceral adipose tissue (VAT) is associated with severe outcomes in patients hospitalized with COVID-19, independent of body mass index (BMI). We analyzed data from the Massachusetts General Hospital COVID-19 Data Registry, which included patients admitted with polymerase chain reaction-confirmed severe acute respiratory syndrome coronavirus 2 infection from March 11 to May 4, 2020. We used a validated, fully automated artificial intelligence (AI) algorithm to quantify VAT from computed tomography (CT) scans during or before the hospital admission. VAT quantification took an average of 2 ± 0.5 seconds per patient. We dichotomized VAT as high and low at a threshold of ≥100 cm A total of 378 participants had CT imaging. Kaplan-Meier curves showed that participants with high VAT had a greater risk of the outcome compared with those with low VAT ( High VAT is associated with a greater risk of severe disease or death in COVID-19 and can offer more precise information to risk-stratify individuals beyond BMI. AI offers a promising approach to routinely ascertain VAT and improve clinical risk prediction in COVID-19.
Sections du résumé
BACKGROUND
BACKGROUND
Obesity has been linked to severe clinical outcomes among people who are hospitalized with coronavirus disease 2019 (COVID-19). We tested the hypothesis that visceral adipose tissue (VAT) is associated with severe outcomes in patients hospitalized with COVID-19, independent of body mass index (BMI).
METHODS
METHODS
We analyzed data from the Massachusetts General Hospital COVID-19 Data Registry, which included patients admitted with polymerase chain reaction-confirmed severe acute respiratory syndrome coronavirus 2 infection from March 11 to May 4, 2020. We used a validated, fully automated artificial intelligence (AI) algorithm to quantify VAT from computed tomography (CT) scans during or before the hospital admission. VAT quantification took an average of 2 ± 0.5 seconds per patient. We dichotomized VAT as high and low at a threshold of ≥100 cm
RESULTS
RESULTS
A total of 378 participants had CT imaging. Kaplan-Meier curves showed that participants with high VAT had a greater risk of the outcome compared with those with low VAT (
CONCLUSIONS
CONCLUSIONS
High VAT is associated with a greater risk of severe disease or death in COVID-19 and can offer more precise information to risk-stratify individuals beyond BMI. AI offers a promising approach to routinely ascertain VAT and improve clinical risk prediction in COVID-19.
Identifiants
pubmed: 34258315
doi: 10.1093/ofid/ofab275
pii: ofab275
pmc: PMC8244656
doi:
Types de publication
Journal Article
Langues
eng
Pagination
ofab275Subventions
Organisme : NIGMS NIH HHS
ID : R01 GM127862
Pays : United States
Organisme : NIDDK NIH HHS
ID : T32 DK007028
Pays : United States
Organisme : NIDDK NIH HHS
ID : R01 DK085070
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL132786
Pays : United States
Organisme : NIA NIH HHS
ID : R01 AG062282
Pays : United States
Organisme : NIAID NIH HHS
ID : K24 AI141036
Pays : United States
Organisme : NIA NIH HHS
ID : R01 AG062393
Pays : United States
Informations de copyright
© The Author(s) 2021. Published by Oxford University Press on behalf of Infectious Diseases Society of America.
Références
Obes Med. 2020 Sep;19:100283
pubmed: 32835126
Diabetes Care. 2020 Jul;43(7):e72-e74
pubmed: 32409499
Adv Exp Med Biol. 2017;1043:9-27
pubmed: 29224088
Metabolism. 2020 Jul;108:154262
pubmed: 32422233
Obesity (Silver Spring). 2006 Feb;14(2):336-41
pubmed: 16571861
Diabetes Care. 2020 Dec;43(12):2938-2944
pubmed: 32847827
Metabolism. 2020 Sep;110:154317
pubmed: 32673651
Radiology. 2018 Aug;288(2):318-328
pubmed: 29944078
Diabetes Care. 2003 May;26(5):1413-20
pubmed: 12716798
Eur J Radiol. 2021 Sep;142:109834
pubmed: 34252866
Diabetes Care. 2021 Apr 15;:
pubmed: 33858854
J Nutr. 2016 Oct;146(10):2143-2148
pubmed: 27581576
Diabetes Care. 2020 Oct;43(10):e129-e130
pubmed: 32753457
Diabetes Care. 2020 Jul;43(7):1392-1398
pubmed: 32409502
Metabolism. 2020 Oct;111:154319
pubmed: 32712222
Obesity (Silver Spring). 2020 Nov;28(11):2040-2048
pubmed: 32677752
AJR Am J Roentgenol. 2012 May;198(5):1100-7
pubmed: 22528899
Lancet Diabetes Endocrinol. 2019 Sep;7(9):715-725
pubmed: 31301983
Front Physiol. 2018 Oct 10;9:1370
pubmed: 30364113
Am J Clin Nutr. 2015 Jul;102(1):58-65
pubmed: 26016860
PLoS One. 2020 Dec 22;15(12):e0244270
pubmed: 33351826