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

医学 队列 回顾性队列研究 危险系数 眼底(子宫) 接收机工作特性 置信区间 弗雷明翰风险评分 冠状动脉疾病 内科学 眼科 心脏病学 疾病
作者
Jooyoung Chang,Ahryoung Ko,Sang Min Park,Seulggie Choi,Kyuwoong Kim,Sung Min Kim,Jae Moon Yun,Ук Канг,Il Hyung Shin,Joo Young Shin,Taehoon Ko,Jinho Lee,Baek‐Lok Oh,Ki Ho Park
出处
期刊:American Journal of Ophthalmology [Elsevier BV]
卷期号:217: 121-130 被引量:82
标识
DOI:10.1016/j.ajo.2020.03.027
摘要

•Retinal fundus imaging and deep learning may be used for stratification of CVD risk. •Deep learning added predictive value compared with conventional CVD risk scoring methods. •The developed model was verified in a large cohort of 30,000 Koreans. Purpose 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. Design Retrospective cohort study. Methods 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. Results 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 <0.33 (hazard ratio: 8.33; 95% confidence interval [CI], 3.16-24.7). Risk association was significant among intermediate and high Framingham risk score (FRS) subgroups. The DL-FAS improved the concordance by 0.0266 (95% CI, 0.0043-0.0489) over the FRS-only model. The relative integrated discrimination index was 20.45% and net reclassification index was 29.5%. Conclusions A deep learning model was developed which could predict atherosclerosis from retinal fundus images. The resulting DL-FAS was an independent predictor of CVD deaths when adjusted for FRS and added predictive value over FRS. 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 <0.33 (hazard ratio: 8.33; 95% confidence interval [CI], 3.16-24.7). Risk association was significant among intermediate and high Framingham risk score (FRS) subgroups. The DL-FAS improved the concordance by 0.0266 (95% CI, 0.0043-0.0489) over the FRS-only model. The relative integrated discrimination index was 20.45% and net reclassification index was 29.5%. A deep learning model was developed which could predict atherosclerosis from retinal fundus images. The resulting DL-FAS was an independent predictor of CVD deaths when adjusted for FRS and added predictive value over FRS.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
方块块完成签到,获得积分10
2秒前
2秒前
xanderxue完成签到,获得积分20
3秒前
Hayley完成签到,获得积分10
3秒前
4秒前
北林完成签到,获得积分10
4秒前
健忘的寒荷关注了科研通微信公众号
6秒前
7秒前
乐乐应助舒心的初兰采纳,获得10
9秒前
大喵发布了新的文献求助10
9秒前
9秒前
9秒前
10秒前
10秒前
10秒前
汉堡包应助cyw采纳,获得10
12秒前
runner发布了新的文献求助10
13秒前
害怕的冷雪完成签到,获得积分10
14秒前
范灵玥完成签到,获得积分10
15秒前
wjx发布了新的文献求助10
15秒前
16秒前
隐形曼青应助Ing采纳,获得10
17秒前
17秒前
lyn发布了新的文献求助10
17秒前
pluto应助lewe采纳,获得10
18秒前
lixoii发布了新的文献求助10
19秒前
19秒前
20秒前
晓晓完成签到,获得积分10
20秒前
20秒前
21秒前
Hello应助淡淡绮琴采纳,获得10
21秒前
HotnessK完成签到,获得积分10
22秒前
皮皮发布了新的文献求助10
22秒前
棒棒糖发布了新的文献求助30
23秒前
24秒前
传奇3应助moyue采纳,获得10
24秒前
24秒前
zjx发布了新的文献求助10
25秒前
Tiinsiin完成签到,获得积分10
25秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3974943
求助须知:如何正确求助?哪些是违规求助? 3519467
关于积分的说明 11198482
捐赠科研通 3255728
什么是DOI,文献DOI怎么找? 1797904
邀请新用户注册赠送积分活动 877261
科研通“疑难数据库(出版商)”最低求助积分说明 806224