A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations
A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations
复制标题
DOI：
10.1016/s2589-7500(20)30063-7
复制
发表时间：
2020-06-01
影响因子：
30.8
通讯作者：
Wong, Tien Y.
中科院分区：
文献类型：
--
作者：
Sabanayagam, Charumathi;Xu, Dejiang;Wong, Tien Y.
慢性肾脏病筛查在社区和初级保健环境中是一项挑战，即使在高收入国家也是如此。我们开发了一种人工智能深度学习算法（DLA），从视网膜图像中检测慢性肾脏疾病，这可以添加到现有的慢性肾脏疾病筛查strategies.Methods我们使用了来自新加坡和中国的三项基于人群的多种族横断面研究的数据。新加坡眼病流行病学研究（SEED，患者年龄≥ 40岁）用于开发（5188例患者）和验证（1297例患者）DLA。外部测试在两个独立的数据集上进行：新加坡前瞻性研究项目（SP2，3735名年龄>= 25岁的患者）和北京眼科研究（BES，1538名年龄>= 40岁的患者）。慢性肾病的定义是估计的肾小球滤过率低于60 mL/min/1.73 m（2）。训练了三个模型：1）图像DLA; 2）危险因素（RF），包括年龄、性别、种族、糖尿病和高血压;和3）结合图像和RF的混合DLA。结果在SEED验证数据集中，图像DLA的AUC为0.911（95%CI 0.886-0.936），RF为0.916（0.891-0.941），混合DLA为0.938（0.917-0.959）。SP2测试数据集中图像DLA的相应估计值为0.733（95% CI 0.696-0.770），RF为0.829（0.797-0.861），混合DLA为0.810在BES测试数据集中，图像DLA的估计值为0.835（0.767-0.903），RF为0.887（0.828-0.946），混合DLA为0.858（0.794-0.922）。AUC估计值在糖尿病患者亚组中相似（图像DLA 0.889 [95% CI 0.850-0.928]，RF 0.899 [0.862-0.936]，混合0.925 [0.893-0.957]）和高血压（图像DLA 0.889 [95%CI 0.860-0.918]，RF 0.889 [0.860-0.918]，混合0.918 [0.893-0.943]）。潜在的可行性，使用视网膜摄影作为一种预防性或机会性筛查工具，慢性肾脏疾病在社区人口。版权所有（C）2020作者。爱思唯尔有限公司出版
Background Screening for chronic kidney disease is a challenge in community and primary care settings, even in high-income countries. We developed an artificial intelligence deep learning algorithm (DLA) to detect chronic kidney disease from retinal images, which could add to existing chronic kidney disease screening strategies.Methods We used data from three population-based, multiethnic, cross-sectional studies in Singapore and China. The Singapore Epidemiology of Eye Diseases study (SEED, patients aged >= 40 years) was used to develop (5188 patients) and validate (1297 patients) the DLA. External testing was done on two independent datasets: the Singapore Prospective Study Program (SP2, 3735 patients aged >= 25 years) and the Beijing Eye Study (BES, 1538 patients aged >= 40 years). Chronic kidney disease was defined as estimated glomerular filtration rate less than 60 mL/min per 1.73m(2). Three models were trained: 1) image DLA; 2) risk factors (RF) including age, sex, ethnicity, diabetes, and hypertension; and 3) hybrid DLA combining image and RF. Model performances were evaluated using the area under the receiver operating characteristic curve (AUC).Findings In the SEED validation dataset, the AUC was 0.911 for image DLA (95% CI 0.886-0.936), 0.916 for RF (0.891-0.941), and 0.938 for hybrid DLA (0.917-0.959). Corresponding estimates in the SP2 testing dataset were 0.733 for image DLA (95% CI 0.696-0.770), 0.829 for RF (0.797-0.861), and 0.810 for hybrid DLA (0.776-0.844); and in the BES testing dataset estimates were 0.835 for image DLA (0.767-0.903), 0.887 for RF (0.828-0.946), and 0.858 for hybrid DLA (0.794-0.922). AUC estimates were similar in subgroups of people with diabetes (image DLA 0.889 [95% CI 0.850-0.928], RF 0.899 [0.862-0.936], hybrid 0.925 [0.893-0.957]) and hypertension (image DLA 0.889 [ 95% CI 0.860-0.918], RF 0.889 [0.860-0.918], hybrid 0.918 [0.893-0.943]).Interpretation A retinal image DLA shows good performance for estimating chronic kidney disease, underlying the feasibility of using retinal photography as an adjunctive or opportunistic screening tool for chronic kidney disease in community populations. Copyright (C) 2020 The Author(s). Published by Elsevier Ltd.