Association of retinal image-based, deep learning cardiac BioAge with telomere length and cardiovascular biomarkers.

IF 1.6 4区医学 Q3 OPHTHALMOLOGY

Optometry and Vision Science Pub Date : 2024-07-01 Epub Date: 2024-06-28 DOI:10.1097/OPX.0000000000002158

Ehsan Vaghefi, Songyang An, Rini Corbett, David Squirrell

{"title":"Association of retinal image-based, deep learning cardiac BioAge with telomere length and cardiovascular biomarkers.","authors":"Ehsan Vaghefi, Songyang An, Rini Corbett, David Squirrell","doi":"10.1097/OPX.0000000000002158","DOIUrl":null,"url":null,"abstract":"Significance: Our retinal image-based deep learning (DL) cardiac biological age (BioAge) model could facilitate fast, accurate, noninvasive screening for cardiovascular disease (CVD) in novel community settings and thus improve outcome with those with limited access to health care services.Purpose: This study aimed to determine whether the results issued by our DL cardiac BioAge model are consistent with the known trends of CVD risk and the biomarker leukocyte telomere length (LTL), in a cohort of individuals from the UK Biobank.Methods: A cross-sectional cohort study was conducted using those individuals in the UK Biobank who had LTL data. These individuals were divided by sex, ranked by LTL, and then grouped into deciles. The retinal images were then presented to the DL model, and individual's cardiac BioAge was determined. Individuals within each LTL decile were then ranked by cardiac BioAge, and the mean of the CVD risk biomarkers in the top and bottom quartiles was compared. The relationship between an individual's cardiac BioAge, the CVD biomarkers, and LTL was determined using traditional correlation statistics.Results: The DL cardiac BioAge model was able to accurately stratify individuals by the traditional CVD risk biomarkers, and for both males and females, those issued with a cardiac BioAge in the top quartile of their chronological peer group had a significantly higher mean systolic blood pressure, hemoglobin A 1c , and 10-year Pooled Cohort Equation CVD risk scores compared with those individuals in the bottom quartile (p<0.001). Cardiac BioAge was associated with LTL shortening for both males and females (males: -0.22, r2 = 0.04; females: -0.18, r2 = 0.03).Conclusions: In this cross-sectional cohort study, increasing CVD risk whether assessed by traditional biomarkers, CVD risk scoring, or our DL cardiac BioAge, CVD risk model, was inversely related to LTL. At a population level, our data support the growing body of evidence that suggests LTL shortening is a surrogate marker for increasing CVD risk and that this risk can be captured by our novel DL cardiac BioAge model.","PeriodicalId":19649,"journal":{"name":"Optometry and Vision Science","volume":" ","pages":"464-469"},"PeriodicalIF":1.6000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11462873/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optometry and Vision Science","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/OPX.0000000000002158","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/28 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Significance: Our retinal image-based deep learning (DL) cardiac biological age (BioAge) model could facilitate fast, accurate, noninvasive screening for cardiovascular disease (CVD) in novel community settings and thus improve outcome with those with limited access to health care services.

Purpose: This study aimed to determine whether the results issued by our DL cardiac BioAge model are consistent with the known trends of CVD risk and the biomarker leukocyte telomere length (LTL), in a cohort of individuals from the UK Biobank.

Methods: A cross-sectional cohort study was conducted using those individuals in the UK Biobank who had LTL data. These individuals were divided by sex, ranked by LTL, and then grouped into deciles. The retinal images were then presented to the DL model, and individual's cardiac BioAge was determined. Individuals within each LTL decile were then ranked by cardiac BioAge, and the mean of the CVD risk biomarkers in the top and bottom quartiles was compared. The relationship between an individual's cardiac BioAge, the CVD biomarkers, and LTL was determined using traditional correlation statistics.

Results: The DL cardiac BioAge model was able to accurately stratify individuals by the traditional CVD risk biomarkers, and for both males and females, those issued with a cardiac BioAge in the top quartile of their chronological peer group had a significantly higher mean systolic blood pressure, hemoglobin A 1c , and 10-year Pooled Cohort Equation CVD risk scores compared with those individuals in the bottom quartile (p<0.001). Cardiac BioAge was associated with LTL shortening for both males and females (males: -0.22, r2 = 0.04; females: -0.18, r2 = 0.03).

Conclusions: In this cross-sectional cohort study, increasing CVD risk whether assessed by traditional biomarkers, CVD risk scoring, or our DL cardiac BioAge, CVD risk model, was inversely related to LTL. At a population level, our data support the growing body of evidence that suggests LTL shortening is a surrogate marker for increasing CVD risk and that this risk can be captured by our novel DL cardiac BioAge model.

查看原文本刊更多论文

基于视网膜图像的深度学习心脏 BioAge 与端粒长度和心血管生物标志物的关联。

意义重大：目的：本研究旨在确定我们基于视网膜图像的深度学习（DL）心脏生物年龄（BioAge）模型得出的结果是否与已知的心血管疾病风险趋势和生物标志物白细胞端粒长度（LTL）一致：利用英国生物库中有LTL数据的个体进行了一项横断面队列研究。这些人按性别、LTL 排名，然后分成十分位数。然后将视网膜图像呈现给 DL 模型，并确定个人的心脏生物年龄。然后按心脏生物年龄对每个LTL十分位数中的个体进行排名，并比较最高和最低四分位数中心血管疾病风险生物标志物的平均值。采用传统的相关统计方法确定个人的心脏生物年龄、心血管疾病生物标志物和LTL之间的关系：结果：DL心脏生物年龄模型能够根据传统的心血管疾病风险生物标志物对个体进行准确分层，对于男性和女性而言，心脏生物年龄位于其年代同龄组前四分之一的个体与后四分之一的个体相比，其平均收缩压、血红蛋白A1c和10年集合队列方程心血管疾病风险评分显著更高（p结论：DL心脏生物年龄模型能够根据传统的心血管疾病风险生物标志物对个体进行准确分层：在这项横断面队列研究中，无论是通过传统的生物标志物、心血管疾病风险评分，还是通过我们的 DL cardiac BioAge 心血管疾病风险模型来评估，心血管疾病风险的增加都与长轴寿命成反比。在人群水平上，我们的数据支持了越来越多的证据，这些证据表明，LTL缩短是心血管疾病风险增加的替代标志物，而我们新颖的DL心脏生物年龄模型可以捕捉到这种风险。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Optometry and Vision Science 医学-眼科学

CiteScore

2.80

自引率

7.10%

发文量

210

审稿时长

3-6 weeks

期刊介绍： Optometry and Vision Science is the monthly peer-reviewed scientific publication of the American Academy of Optometry, publishing original research since 1924. Optometry and Vision Science is an internationally recognized source for education and information on current discoveries in optometry, physiological optics, vision science, and related fields. The journal considers original contributions that advance clinical practice, vision science, and public health. Authors should remember that the journal reaches readers worldwide and their submissions should be relevant and of interest to a broad audience. Topical priorities include, but are not limited to: clinical and laboratory research, evidence-based reviews, contact lenses, ocular growth and refractive error development, eye movements, visual function and perception, biology of the eye and ocular disease, epidemiology and public health, biomedical optics and instrumentation, novel and important clinical observations and treatments, and optometric education.