Association of Cardiovascular Mortality and Deep Learning-Funduscopic Atherosclerosis Score derived from Retinal Fundus Images

The prediction of atherosclerosis using retinal fundus images and deep learning has not been shown possible. The purpose of this study was to develop a deep learning model which predicted atherosclerosis by using retinal fundus images and to verify its clinical implications by conducting a retrospec...

Full description

Saved in:
Bibliographic Details
Published in:American journal of ophthalmology 2020-09, Vol.217, p.121-130
Main Authors: Chang, Jooyoung, Ko, Ahryoung, Park, Sang Min, Choi, Seulggie, Kim, Kyuwoong, Kim, Sung Min, Yun, Jae Moon, Kang, Uk, Shin, Il Hyung, Shin, Joo Young, Ko, Taehoon, Lee, Jinho, Oh, Baek-Lok, Park, Ki Ho
Format: Article
Language:English
Subjects:
Atherosclerosis
Carotid arteries
Deep learning
Diabetes
Hypertension
Mortality
Patients
Risk factors
Ultrasonic imaging
Veins & arteries
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The prediction of atherosclerosis using retinal fundus images and deep learning has not been shown possible. The purpose of this study was to develop a deep learning model which predicted atherosclerosis by using retinal fundus images and to verify its clinical implications by conducting a retrospective cohort analysis. Retrospective cohort study. The database at the Health Promotion Center of Seoul National University Hospital (HPC-SNUH) was used. The deep learning model was trained using 15,408 images to predict carotid artery atherosclerosis, which was named the deep-learning funduscopic atherosclerosis score (DL-FAS). A retrospective cohort was constructed of participants 30-80 years old who had completed elective health examinations at HPC-SNUH. Using DL-FAS as the main exposure, participants were followed for the primary outcome of death due to CVD until Dec. 31, 2017. For predicting carotid artery atherosclerosis among subjects, the model achieved an area under receiver operating curve (AUROC) and area under the precision-recall curve (AUPRC), accuracy, sensitivity, specificity, positive and negative predictive values of 0.713, 0.569, 0.583, 0.891, 0.404, 0.465, and 0.865 respectively. The cohort consisted of 32,227 participants, 78 cardiovascular disease (CVD) deaths, and 7.6-year median follow-up visits. Those with DL-FAS greater than 0.66 had an increased risk of CVD deaths compared to those with DL-FAS
ISSN:0002-9394
1879-1891
DOI:10.1016/j.ajo.2020.03.027