Association of lifestyle with deep learning predicted electrocardiographic age
BackgroundPeople 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.MethodsThis study included participants from the UK Biobank who...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1160091/full |
| _version_ | 1827960911112962048 |
|---|---|
| author | Cuili Zhang Xiao Miao Biqi Wang Robert J. Thomas Antônio H. Ribeiro Luisa C. C. Brant Antonio L. P. Ribeiro Honghuang Lin |
| author_facet | Cuili Zhang Xiao Miao Biqi Wang Robert J. Thomas Antônio H. Ribeiro Luisa C. C. Brant Antonio L. P. Ribeiro Honghuang Lin |
| author_sort | Cuili Zhang |
| collection | DOAJ |
| description | BackgroundPeople 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.MethodsThis 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.ResultsThis 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, P < 0.001) and the mean Δage (absolute error of biological age and chronological age) was 9.8 ± 7.4 years. Δage was significantly associated with all of the four lifestyle factors, with the effect size ranging from 0.41 ± 0.11 for the healthy diet to 2.37 ± 0.30 for non-smoking. Compared with an ideal lifestyle, an unfavorable lifestyle was associated with an average of 2.50 ± 0.29 years of older predicted ECG-age.ConclusionIn 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. |
| first_indexed | 2024-04-09T16:17:21Z |
| format | Article |
| id | doaj.art-b8edf6ac3e5d4cf4b9cd5bb5c9b65a85 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-04-09T16:17:21Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-b8edf6ac3e5d4cf4b9cd5bb5c9b65a852023-04-24T04:30:44ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-04-011010.3389/fcvm.2023.11600911160091Association of lifestyle with deep learning predicted electrocardiographic ageCuili Zhang0Xiao Miao1Biqi Wang2Robert J. Thomas3Antônio H. Ribeiro4Luisa C. C. Brant5Antonio L. P. Ribeiro6Honghuang Lin7Department of Cardiology, The First Affiliated Hospital of Harbin Medical University, Harbin, ChinaInnovation Research Institute of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, ChinaDepartment of Medicine, University of Massachusetts Chan Medical School, Worcester, MA, United StatesDepartment of Medicine, Division of Pulmonary, Critical Care & Sleep Medicine, Beth Israel DeaconessMedical Center, Boston, MA, United StatesDepartment of Information Technology, Uppsala University, Uppsala, SwedenFaculty of Medicine and Telehealth Center, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, BrazilFaculty of Medicine and Telehealth Center, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, BrazilDepartment of Medicine, University of Massachusetts Chan Medical School, Worcester, MA, United StatesBackgroundPeople 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.MethodsThis 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.ResultsThis 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, P < 0.001) and the mean Δage (absolute error of biological age and chronological age) was 9.8 ± 7.4 years. Δage was significantly associated with all of the four lifestyle factors, with the effect size ranging from 0.41 ± 0.11 for the healthy diet to 2.37 ± 0.30 for non-smoking. Compared with an ideal lifestyle, an unfavorable lifestyle was associated with an average of 2.50 ± 0.29 years of older predicted ECG-age.ConclusionIn 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.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1160091/fullbiological agedeep learninglifestyleepidemiology—analytic (risk factors)electrocardiogram |
| spellingShingle | Cuili Zhang Xiao Miao Biqi Wang Robert J. Thomas Antônio H. Ribeiro Luisa C. C. Brant Antonio L. P. Ribeiro Honghuang Lin Association of lifestyle with deep learning predicted electrocardiographic age Frontiers in Cardiovascular Medicine biological age deep learning lifestyle epidemiology—analytic (risk factors) electrocardiogram |
| title | Association of lifestyle with deep learning predicted electrocardiographic age |
| title_full | Association of lifestyle with deep learning predicted electrocardiographic age |
| title_fullStr | Association of lifestyle with deep learning predicted electrocardiographic age |
| title_full_unstemmed | Association of lifestyle with deep learning predicted electrocardiographic age |
| title_short | Association of lifestyle with deep learning predicted electrocardiographic age |
| title_sort | association of lifestyle with deep learning predicted electrocardiographic age |
| topic | biological age deep learning lifestyle epidemiology—analytic (risk factors) electrocardiogram |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1160091/full |
| work_keys_str_mv | AT cuilizhang associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT xiaomiao associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT biqiwang associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT robertjthomas associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT antoniohribeiro associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT luisaccbrant associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT antoniolpribeiro associationoflifestylewithdeeplearningpredictedelectrocardiographicage AT honghuanglin associationoflifestylewithdeeplearningpredictedelectrocardiographicage |