Cover Image

A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre

Retinal blood vessels provide information on the risk of cardiovascular disease (CVD). Here, we report the development and validation of deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs, using diverse multiethnic multicountry datasets that comprise...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheung, Carol Y. (Author) , Xu, Dejiang (Author) , Cheng, Ching-Yu (Author) , Sabanayagam, Charumathi (Author) , Tham, Yih-Chung (Author) , Yu, Marco (Author) , Rim, Tyler Hyungtaek (Author) , Chai, Chew Yian (Author) , Gopinath, Bamini (Author) , Mitchell, Paul (Author) , Poulton, Richie (Author) , Moffitt, Terrie E. (Author) , Caspi, Avshalom (Author) , Yam, Jason C. (Author) , Tham, Clement C. (Author) , Jonas, Jost B. (Author) , Wang, Ya Xing (Author) , Song, Su Jeong (Author) , Burrell, Louise M. (Author) , Farouque, Omar (Author) , Li, Ling Jun (Author) , Tan, Gavin (Author) , Ting, Daniel S. W. (Author) , Hsu, Wynne (Author) , Lee, Mong Li (Author) , Wong, Tien Y. (Author)
Format: Article (Journal)
Language:English
Published: 2021
In: Nature biomedical engineering
Year: 2021, Volume: 5, Issue: 6, Pages: 498-508
ISSN:2157-846X
DOI:10.1038/s41551-020-00626-4
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41551-020-00626-4
Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41551-020-00626-4
Get full text
Author Notes:Carol Y. Cheung, Dejiang Xu, Ching-Yu Cheng, Charumathi Sabanayagam, Yih-Chung Tham, Marco Yu, Tyler Hyungtaek Rim, Chew Yian Chai, Bamini Gopinath, Paul Mitchell, Richie Poulton, Terrie E. Moffitt, Avshalom Caspi, Jason C. Yam, Clement C. Tham, Jost B. Jonas, Ya Xing Wang, Su Jeong Song, Louise M. Burrell, Omar Farouque, Ling Jun Li, Gavin Tan, Daniel S. W. Ting, Wynne Hsu, Mong Li Lee & Tien Y. Wong
Description
Summary:Retinal blood vessels provide information on the risk of cardiovascular disease (CVD). Here, we report the development and validation of deep-learning models for the automated measurement of retinal-vessel calibre in retinal photographs, using diverse multiethnic multicountry datasets that comprise more than 70,000 images. Retinal-vessel calibre measured by the models and by expert human graders showed high agreement, with overall intraclass correlation coefficients of between 0.82 and 0.95. The models performed comparably to or better than expert graders in associations between measurements of retinal-vessel calibre and CVD risk factors, including blood pressure, body-mass index, total cholesterol and glycated-haemoglobin levels. In retrospectively measured prospective datasets from a population-based study, baseline measurements performed by the deep-learning system were associated with incident CVD. Our findings motivate the development of clinically applicable explainable end-to-end deep-learning systems for the prediction of CVD on the basis of the features of retinal vessels in retinal photographs.
Item Description:"Published: 12 October 2020".- Artikel-Frontdoor
Gesehen am 07.10.2024
Physical Description:Online Resource
ISSN:2157-846X
DOI:10.1038/s41551-020-00626-4

Similar Items