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
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

ofab275

Subventions

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

Auteurs

Alexander Goehler (A)

Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Boston, Massachusetts, USA.
Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Tzu-Ming Harry Hsu (TH)

Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Boston, Massachusetts, USA.

Jacqueline A Seiglie (JA)

Diabetes Unit, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Mark J Siedner (MJ)

Division of Infectious Diseases, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Medical Practice Evaluation Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Janet Lo (J)

Metabolism Unit, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Virginia Triant (V)

Division of Infectious Diseases, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

John Hsu (J)

Mongan Institute, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Department of Healthcare Policy, Harvard Medical School, Boston, Massachusetts, USA.

Andrea Foulkes (A)

The Biostatistics Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Ingrid Bassett (I)

Division of Infectious Diseases, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Medical Practice Evaluation Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Ramin Khorasani (R)

Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Deborah J Wexler (DJ)

Diabetes Unit, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Peter Szolovits (P)

Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Boston, Massachusetts, USA.

James B Meigs (JB)

Division of General Internal Medicine, Massachusetts General Hospital, Boston, Massachusetts, USA.
Program in Medical and Population Genetics, Broad Institute, Boston, Massachusetts, USA.

Jennifer Manne-Goehler (J)

Medical Practice Evaluation Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
Division of Infectious Diseases, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.

Classifications MeSH