Automated Muscle Measurement on Chest CT Predicts All-Cause Mortality in Older Adults From the National Lung Screening Trial.
Computed tomography
Machine learning
Mortality
Myosteatosis
Sarcopenia
Journal
The journals of gerontology. Series A, Biological sciences and medical sciences
ISSN: 1758-535X
Titre abrégé: J Gerontol A Biol Sci Med Sci
Pays: United States
ID NLM: 9502837
Informations de publication
Date de publication:
18 01 2021
18 01 2021
Historique:
received:
30
10
2019
pubmed:
7
6
2020
medline:
15
7
2021
entrez:
7
6
2020
Statut:
ppublish
Résumé
Muscle metrics derived from computed tomography (CT) are associated with adverse health events in older persons, but obtaining these metrics using current methods is not practical for large datasets. We developed a fully automated method for muscle measurement on CT images. This study aimed to determine the relationship between muscle measurements on CT with survival in a large multicenter trial of older adults. The relationship between baseline paraspinous skeletal muscle area (SMA) and skeletal muscle density (SMD) and survival over 6 years was determined in 6,803 men and 4,558 women (baseline age: 60-69 years) in the National Lung Screening Trial (NLST). The automated machine learning pipeline selected appropriate CT series, chose a single image at T12, and segmented left paraspinous muscle, recording cross-sectional area and density. Associations between SMA and SMD with all-cause mortality were determined using sex-stratified Cox proportional hazards models, adjusted for age, race, height, weight, pack-years of smoking, and presence of diabetes, chronic lung disease, cardiovascular disease, and cancer at enrollment. After a mean 6.44 ± 1.06 years of follow-up, 635 (9.33%) men and 265 (5.81%) women died. In men, higher SMA and SMD were associated with a lower risk of all-cause mortality, in fully adjusted models. A one-unit standard deviation increase was associated with a hazard ratio (HR) = 0.85 (95% confidence interval [CI] = 0.79, 0.91; p < .001) for SMA and HR = 0.91 (95% CI = 0.84, 0.98; p = .012) for SMD. In women, the associations did not reach significance. Higher paraspinous SMA and SMD, automatically derived from CT exams, were associated with better survival in a large multicenter cohort of community-dwelling older men.
Sections du résumé
BACKGROUND
Muscle metrics derived from computed tomography (CT) are associated with adverse health events in older persons, but obtaining these metrics using current methods is not practical for large datasets. We developed a fully automated method for muscle measurement on CT images. This study aimed to determine the relationship between muscle measurements on CT with survival in a large multicenter trial of older adults.
METHOD
The relationship between baseline paraspinous skeletal muscle area (SMA) and skeletal muscle density (SMD) and survival over 6 years was determined in 6,803 men and 4,558 women (baseline age: 60-69 years) in the National Lung Screening Trial (NLST). The automated machine learning pipeline selected appropriate CT series, chose a single image at T12, and segmented left paraspinous muscle, recording cross-sectional area and density. Associations between SMA and SMD with all-cause mortality were determined using sex-stratified Cox proportional hazards models, adjusted for age, race, height, weight, pack-years of smoking, and presence of diabetes, chronic lung disease, cardiovascular disease, and cancer at enrollment.
RESULTS
After a mean 6.44 ± 1.06 years of follow-up, 635 (9.33%) men and 265 (5.81%) women died. In men, higher SMA and SMD were associated with a lower risk of all-cause mortality, in fully adjusted models. A one-unit standard deviation increase was associated with a hazard ratio (HR) = 0.85 (95% confidence interval [CI] = 0.79, 0.91; p < .001) for SMA and HR = 0.91 (95% CI = 0.84, 0.98; p = .012) for SMD. In women, the associations did not reach significance.
CONCLUSION
Higher paraspinous SMA and SMD, automatically derived from CT exams, were associated with better survival in a large multicenter cohort of community-dwelling older men.
Identifiants
pubmed: 32504466
pii: 5854128
doi: 10.1093/gerona/glaa141
pmc: PMC7812435
doi:
Types de publication
Clinical Trial
Journal Article
Multicenter Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
277-285Subventions
Organisme : NIA NIH HHS
ID : K25 AG058804
Pays : United States
Organisme : NIA NIH HHS
ID : P30 AG021332
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001420
Pays : United States
Informations de copyright
Published by Oxford University Press on behalf of The Gerontological Society of America 2020.
Références
N Engl J Med. 2011 Aug 4;365(5):395-409
pubmed: 21714641
Ann Intern Med. 2014 Mar 4;160(5):330-8
pubmed: 24378917
Radiology. 2015 Jul;276(1):82-90
pubmed: 25759972
J Gerontol A Biol Sci Med Sci. 2014 Jun;69(6):751-8
pubmed: 24013673
Acad Radiol. 2019 Dec;26(12):1695-1706
pubmed: 31405724
JAMA. 2011 Oct 26;306(16):1775-81
pubmed: 22028353
Int J Med Sci. 2017 Sep 3;14(11):1054-1064
pubmed: 29104458
J Am Geriatr Soc. 2000 Apr;48(4):381-6
pubmed: 10798463
J Trauma Acute Care Surg. 2016 May;80(5):805-11
pubmed: 26885997
World J Surg. 2017 Sep;41(9):2266-2279
pubmed: 28386715
Prev Med. 2007 Mar;44(3):272-8
pubmed: 17184831
J Gerontol A Biol Sci Med Sci. 2006 Oct;61(10):1059-64
pubmed: 17077199
Am J Epidemiol. 2007 Mar 15;165(6):696-703
pubmed: 17194749
AJR Am J Roentgenol. 2017 Jun;208(6):W208-W215
pubmed: 28267356
AJR Am J Roentgenol. 2015 Sep;205(3):W255-66
pubmed: 26102307
Acad Radiol. 2019 Dec;26(12):1686-1694
pubmed: 31326311
J Am Geriatr Soc. 2009 Oct;57(10):1850-5
pubmed: 19694870
J Orthop Trauma. 2019 Jan;33(1):e1-e7
pubmed: 30277981
Clin Nutr. 2019 Dec;38(6):2875-2880
pubmed: 30612853
Am J Epidemiol. 2016 Jan 1;183(1):53-60
pubmed: 26643983
J Gerontol A Biol Sci Med Sci. 2016 Jan;71(1):90-5
pubmed: 26273021
Ann R Coll Surg Engl. 2016 Feb;98(2):80-5
pubmed: 26741674
J Gerontol A Biol Sci Med Sci. 2015 Sep;70(9):1133-40
pubmed: 25838547
Clin Transplant. 2017 Mar;31(3):
pubmed: 28075034
J Am Geriatr Soc. 2015 Nov;63(11):2247-59
pubmed: 26502831
J Gerontol A Biol Sci Med Sci. 2005 Mar;60(3):324-33
pubmed: 15860469
J Thorac Cardiovasc Surg. 2016 Mar;151(3):745-751
pubmed: 26896357
J Am Geriatr Soc. 2014 Aug;62(8):1476-1483
pubmed: 25039391
Age Ageing. 2016 Jul;45(4):529-34
pubmed: 27076522
J Bone Miner Res. 2018 Sep;33(9):1612-1621
pubmed: 29701926
J Gerontol A Biol Sci Med Sci. 2020 Jun 18;75(7):1317-1323
pubmed: 30869772
Osteoporos Int. 2015 Jan;26(1):93-102
pubmed: 25297891
JAMA Surg. 2017 Feb 15;152(2):e164604
pubmed: 28030710
Radiology. 2011 Jan;258(1):243-53
pubmed: 21045183
Semin Musculoskelet Radiol. 2018 Jul;22(3):307-322
pubmed: 29791959
J Gerontol A Biol Sci Med Sci. 2019 Oct 4;74(11):1821-1827
pubmed: 30778518
J Gerontol A Biol Sci Med Sci. 2019 Jun 18;74(7):1063-1069
pubmed: 30124775
J Gerontol A Biol Sci Med Sci. 2006 Jan;61(1):72-7
pubmed: 16456196
J Gerontol A Biol Sci Med Sci. 2017 Apr 1;72(4):513-519
pubmed: 27567109
J Thorac Oncol. 2017 Aug;12(8):1210-1222
pubmed: 28499861
J Am Geriatr Soc. 2009 Aug;57(8):1411-9
pubmed: 19682143
J Gerontol A Biol Sci Med Sci. 2000 Nov;55(11):M691-7
pubmed: 11078100
J Bone Miner Res. 2008 Jul;23(7):1037-44
pubmed: 18302496
J Am Coll Surg. 2016 Apr;222(4):397-407.e2
pubmed: 26803743
Eur Radiol. 2015 Jan;25(1):132-9
pubmed: 25323601
J Bone Miner Res. 2018 Sep;33(9):1622-1629
pubmed: 29701911
J Intensive Care. 2017 Jan 11;5:8
pubmed: 28096999
BMC Nephrol. 2014 Jul 08;15:108
pubmed: 25005601
J Frailty Aging. 2019;8(2):72-78
pubmed: 30997919
Am J Transplant. 2016 Aug;16(8):2277-92
pubmed: 26813115
Crit Care. 2013 Sep 19;17(5):R206
pubmed: 24050662
JAMA Cardiol. 2017 Nov 1;2(11):1236-1246
pubmed: 28975197
J Diabetes Complications. 2018 Jun;32(6):558-564
pubmed: 29627372
J Bone Joint Surg Am. 2017 Feb 1;99(3):200-206
pubmed: 28145950
J Gerontol A Biol Sci Med Sci. 2020 Apr 17;75(5):899-905
pubmed: 31086986
Cardiology. 2019;142(1):28-36
pubmed: 30893691
J Gerontol A Biol Sci Med Sci. 2019 Sep 15;74(10):1671-1678
pubmed: 30726878
Age (Dordr). 2015 Dec;37(6):121
pubmed: 26607157
Biol Sex Differ. 2019 Aug 28;10(1):43
pubmed: 31462271
Front Endocrinol (Lausanne). 2016 Jun 20;7:69
pubmed: 27379021
J Am Geriatr Soc. 2003 Sep;51(9):1237-43
pubmed: 12919235