Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/25033
Title: A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre.
Austin Authors: Cheung, Carol Y;Xu, Dejiang;Cheng, Ching-Yu;Sabanayagam, Charumathi;Tham, Yih-Chung;Yu, Marco;Rim, Tyler Hyungtaek;Chai, Chew Yian;Gopinath, Bamini;Mitchell, Paul L R ;Poulton, Richie;Moffitt, Terrie E;Caspi, Avshalom;Yam, Jason C;Tham, Clement C;Jonas, Jost B;Wang, Ya Xing;Song, Su Jeong;Burrell, Louise M ;Farouque, Omar ;Li, Ling Jun;Tan, Gavin;Ting, Daniel S W;Hsu, Wynne;Lee, Mong Li;Wong, Tien Y
Affiliation: Singapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore
School of Computing, National University of Singapore, Singapore, Singapore
Ophthalmology and Visual Sciences Academic Clinical Programme, Duke-NUS Medical School, Singapore, Singapore
Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, China
Emergency Medicine Department, National University Hospital, Singapore, Singapore
Singapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore Ophthalmology and Visual Sciences Academic Clinical Programme, Duke-NUS Medical School, Singapore, Singapore
Department of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
Centre for Vision Research, Westmead Institute for Medical Research, Westmead, New South Wales, Australia
Dunedin Multidisciplinary Health and Development Research Unit, Department of Psychology, University of Otago, Dunedin, New Zealand
Department of Psychology and Neuroscience, Duke University, Durham, NC, USA
Medicine (University of Melbourne)
Department of Ophthalmology, Medical Faculty Mannheim, Ruprecht-Karls-University, Heidelberg, Germany
Beijing Ophthalmology & Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China
Department of Ophthalmology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
Department of Cardiology, Austin Health, Austin Hospital, and Department of Medicine, University of Melbourne, Heidelberg, Victoria, Australia
Cardiology
Division of Obstetrics and Gynaecology, KK Women's and Children's Hospital, Singapore, Singapore
School of Computing, National University of Singapore, Singapore, Singapore
Issue Date: 12-Oct-2020
metadata.dc.date: 2020-10-12
Publication information: Nature Biomedical Engineering 2020; online first: 12 October
Abstract: 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.
URI: https://ahro.austin.org.au/austinjspui/handle/1/25033
DOI: 10.1038/s41551-020-00626-4
ORCID: 0000-0003-0655-885X
0000-0002-4042-4719
0000-0002-6752-797X
0000-0002-1052-4583
0000-0003-4407-6907
0000-0003-2972-5227
0000-0003-2749-7793
0000-0003-1863-7539
0000-0003-2821-1451
0000-0002-4142-8893
0000-0002-9636-388X
0000-0002-8448-1264
PubMed URL: 33046867
Type: Journal Article
Appears in Collections:Journal articles

Show full item record

Page view(s)

26
checked on Mar 8, 2021

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.