Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/25033
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCheung, Carol Y-
dc.contributor.authorXu, Dejiang-
dc.contributor.authorCheng, Ching-Yu-
dc.contributor.authorSabanayagam, Charumathi-
dc.contributor.authorTham, Yih-Chung-
dc.contributor.authorYu, Marco-
dc.contributor.authorRim, Tyler Hyungtaek-
dc.contributor.authorChai, Chew Yian-
dc.contributor.authorGopinath, Bamini-
dc.contributor.authorMitchell, Paul L R-
dc.contributor.authorPoulton, Richie-
dc.contributor.authorMoffitt, Terrie E-
dc.contributor.authorCaspi, Avshalom-
dc.contributor.authorYam, Jason C-
dc.contributor.authorTham, Clement C-
dc.contributor.authorJonas, Jost B-
dc.contributor.authorWang, Ya Xing-
dc.contributor.authorSong, Su Jeong-
dc.contributor.authorBurrell, Louise Men
dc.contributor.authorFarouque, Omar-
dc.contributor.authorLi, Ling Jun-
dc.contributor.authorTan, Gavin-
dc.contributor.authorTing, Daniel S W-
dc.contributor.authorHsu, Wynne-
dc.contributor.authorLee, Mong Li-
dc.contributor.authorWong, Tien Y-
dc.date2020-10-12-
dc.date.accessioned2020-10-15T03:15:14Z-
dc.date.available2020-10-15T03:15:14Z-
dc.date.issued2020-10-12-
dc.identifier.citationNature Biomedical Engineering 2020; online first: 12 Octoberen
dc.identifier.urihttps://ahro.austin.org.au/austinjspui/handle/1/25033-
dc.description.abstractRetinal 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.en
dc.language.isoeng
dc.titleA deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre.en
dc.typeJournal Articleen
dc.identifier.journaltitleNature Biomedical Engineeringen
dc.identifier.affiliationSingapore Eye Research Institute, Singapore National Eye Center, Singapore, Singaporeen
dc.identifier.affiliationSchool of Computing, National University of Singapore, Singapore, Singaporeen
dc.identifier.affiliationOphthalmology and Visual Sciences Academic Clinical Programme, Duke-NUS Medical School, Singapore, Singaporeen
dc.identifier.affiliationDepartment of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, Chinaen
dc.identifier.affiliationEmergency Medicine Department, National University Hospital, Singapore, Singaporeen
dc.identifier.affiliationSingapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore Ophthalmology and Visual Sciences Academic Clinical Programme, Duke-NUS Medical School, Singapore, Singaporeen
dc.identifier.affiliationDepartment of Surgery, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singaporeen
dc.identifier.affiliationCentre for Vision Research, Westmead Institute for Medical Research, Westmead, New South Wales, Australiaen
dc.identifier.affiliationDunedin Multidisciplinary Health and Development Research Unit, Department of Psychology, University of Otago, Dunedin, New Zealanden
dc.identifier.affiliationDepartment of Psychology and Neuroscience, Duke University, Durham, NC, USAen
dc.identifier.affiliationMedicine (University of Melbourne)en
dc.identifier.affiliationDepartment of Ophthalmology, Medical Faculty Mannheim, Ruprecht-Karls-University, Heidelberg, Germanyen
dc.identifier.affiliationBeijing Ophthalmology & Visual Science Key Lab, Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, Chinaen
dc.identifier.affiliationDepartment of Ophthalmology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Republic of Koreaen
dc.identifier.affiliationDepartment of Cardiology, Austin Health, Austin Hospital, and Department of Medicine, University of Melbourne, Heidelberg, Victoria, Australiaen
dc.identifier.affiliationCardiologyen
dc.identifier.affiliationDivision of Obstetrics and Gynaecology, KK Women's and Children's Hospital, Singapore, Singaporeen
dc.identifier.affiliationSchool of Computing, National University of Singapore, Singapore, Singaporeen
dc.identifier.doi10.1038/s41551-020-00626-4en
dc.type.contentTexten
dc.identifier.orcid0000-0003-0655-885Xen
dc.identifier.orcid0000-0002-4042-4719en
dc.identifier.orcid0000-0002-6752-797Xen
dc.identifier.orcid0000-0002-1052-4583en
dc.identifier.orcid0000-0003-4407-6907en
dc.identifier.orcid0000-0003-2972-5227en
dc.identifier.orcid0000-0003-2749-7793en
dc.identifier.orcid0000-0003-1863-7539en
dc.identifier.orcid0000-0003-2821-1451en
dc.identifier.orcid0000-0002-4142-8893en
dc.identifier.orcid0000-0002-9636-388Xen
dc.identifier.orcid0000-0002-8448-1264en
dc.identifier.pubmedid33046867
Appears in Collections:Journal articles
Show simple item record

Page view(s)

30
checked on Apr 23, 2021

Google ScholarTM

Check


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