Association of lifestyle with deep learning predicted electrocardiographic age.
biological age
deep learning
electrocardiogram
epidemiology—analytic (risk factors)
lifestyle
Journal
Frontiers in cardiovascular medicine
ISSN: 2297-055X
Titre abrégé: Front Cardiovasc Med
Pays: Switzerland
ID NLM: 101653388
Informations de publication
Date de publication:
2023
2023
Historique:
received:
06
02
2023
accepted:
04
04
2023
medline:
12
5
2023
pubmed:
12
5
2023
entrez:
11
5
2023
Statut:
epublish
Résumé
People age at different rates. Biological age is a risk factor for many chronic diseases independent of chronological age. A good lifestyle is known to improve overall health, but its association with biological age is unclear. This study included participants from the UK Biobank who had undergone 12-lead resting electrocardiography (ECG). Biological age was estimated by a deep learning model (defined as ECG-age), and the difference between ECG-age and chronological age was defined as Δage. Participants were further categorized into an ideal (score 4), intermediate (scores 2 and 3) or unfavorable lifestyle (score 0 or 1). Four lifestyle factors were investigated, including diet, alcohol consumption, physical activity, and smoking. Linear regression models were used to examine the association between lifestyle factors and Δage, and the models were adjusted for sex and chronological age. This study included 44,094 individuals (mean age 64 ± 8, 51.4% females). A significant correlation was observed between predicted biological age and chronological age (correlation coefficient = 0.54, In this large contemporary population, a strong association was observed between all four studied healthy lifestyle factors and deaccelerated aging. Our study underscores the importance of a healthy lifestyle to reduce the burden of aging-related diseases.
Sections du résumé
Background
UNASSIGNED
People age at different rates. Biological age is a risk factor for many chronic diseases independent of chronological age. A good lifestyle is known to improve overall health, but its association with biological age is unclear.
Methods
UNASSIGNED
This study included participants from the UK Biobank who had undergone 12-lead resting electrocardiography (ECG). Biological age was estimated by a deep learning model (defined as ECG-age), and the difference between ECG-age and chronological age was defined as Δage. Participants were further categorized into an ideal (score 4), intermediate (scores 2 and 3) or unfavorable lifestyle (score 0 or 1). Four lifestyle factors were investigated, including diet, alcohol consumption, physical activity, and smoking. Linear regression models were used to examine the association between lifestyle factors and Δage, and the models were adjusted for sex and chronological age.
Results
UNASSIGNED
This study included 44,094 individuals (mean age 64 ± 8, 51.4% females). A significant correlation was observed between predicted biological age and chronological age (correlation coefficient = 0.54,
Conclusion
UNASSIGNED
In this large contemporary population, a strong association was observed between all four studied healthy lifestyle factors and deaccelerated aging. Our study underscores the importance of a healthy lifestyle to reduce the burden of aging-related diseases.
Identifiants
pubmed: 37168659
doi: 10.3389/fcvm.2023.1160091
pmc: PMC10165078
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1160091Subventions
Organisme : NIA NIH HHS
ID : U01 AG068221
Pays : United States
Informations de copyright
© 2023 Zhang, Miao, Wang, Thomas, Ribeiro, Brant, Ribeiro and Lin.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Nat Commun. 2020 Apr 9;11(1):1760
pubmed: 32273514
N Engl J Med. 1995 May 4;332(18):1198-203
pubmed: 7700313
Nat Commun. 2021 Aug 25;12(1):5117
pubmed: 34433816
Nat Biotechnol. 2017 Apr 11;35(4):337-339
pubmed: 28398316
Int J Epidemiol. 2008 Apr;37(2):234-44
pubmed: 18381398
J Pers Med. 2014 Mar 07;4(1):65-78
pubmed: 25562143
BMJ. 2021 Apr 14;373:n604
pubmed: 33853828
Synapse. 2000 Dec 1;38(3):313-21
pubmed: 11020234
BMC Public Health. 2013 Nov 12;13:1067
pubmed: 24219513
Bull World Health Organ. 2007 Jan;85(1):19-26
pubmed: 17242754
J Gerontol A Biol Sci Med Sci. 2018 May 9;73(6):757-762
pubmed: 28977464
Lancet. 2019 Sep 7;394(10201):861-867
pubmed: 31378392
Lancet. 2012 Mar 31;379(9822):1173-4
pubmed: 22463865
Circ Arrhythm Electrophysiol. 2019 Sep;12(9):e007284
pubmed: 31450977
Sci Rep. 2022 Jul 27;12(1):12805
pubmed: 35896705
Nat Med. 2019 Jan;25(1):65-69
pubmed: 30617320
N Engl J Med. 2016 Dec 15;375(24):2349-2358
pubmed: 27959714
Circulation. 2016 Jan 12;133(2):187-225
pubmed: 26746178
Mol Cell. 2013 Jan 24;49(2):359-367
pubmed: 23177740
Circulation. 2022 Jan 11;145(2):122-133
pubmed: 34743566
Pharmacogenomics. 2005 Sep;6(6):639-46
pubmed: 16143003
J Gerontol A Biol Sci Med Sci. 2003 Mar;58(3):232-7
pubmed: 12634289
J Am Heart Assoc. 2021 Feb 2;10(3):e018656
pubmed: 33455414
Nat Rev Cardiol. 2021 Jul;18(7):465-478
pubmed: 33526938
Physiol Meas. 2020 Mar 06;41(2):025001
pubmed: 31978903
J Cardiovasc Electrophysiol. 2015 May;26(5):520-6
pubmed: 25651872
JAMA. 2019 Aug 06;322(5):430-437
pubmed: 31302669
Neurobiol Aging. 2019 Feb;74:112-120
pubmed: 30448611
JAMA Cardiol. 2018 Aug 1;3(8):693-702
pubmed: 29955826
Circulation. 2010 Feb 2;121(4):586-613
pubmed: 20089546
Genome Biol. 2015 Jan 30;16:25
pubmed: 25633388
Aging (Albany NY). 2016 Sep 28;8(9):1844-1865
pubmed: 27690265
Am J Public Health. 2011 Oct;101(10):1922-9
pubmed: 21852630
J Electrocardiol. 2019 Nov - Dec;57S:S75-S78
pubmed: 31526573
PLoS Med. 2015 Mar 31;12(3):e1001779
pubmed: 25826379
Am J Clin Nutr. 2003 Sep;78(3 Suppl):570S-578S
pubmed: 12936951
J Gerontol A Biol Sci Med Sci. 2017 Sep 1;72(9):1218-1225
pubmed: 28003373
Genome Biol. 2013;14(10):R115
pubmed: 24138928
Biomed Res Int. 2021 Feb 11;2021:1947928
pubmed: 33628774