Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
School of Computing, National University of Singapore, Singapore.
Lancet Digit Health. 2019 May;1(1):e35-e44. doi: 10.1016/S2589-7500(19)30004-4. Epub 2019 May 2.
Radical measures are required to identify and reduce blindness due to diabetes to achieve the Sustainable Development Goals by 2030. Therefore, we evaluated the accuracy of an artificial intelligence (AI) model using deep learning in a population-based diabetic retinopathy screening programme in Zambia, a lower-middle-income country.
We adopted an ensemble AI model consisting of a combination of two convolutional neural networks (an adapted VGGNet architecture and a residual neural network architecture) for classifying retinal colour fundus images. We trained our model on 76 370 retinal fundus images from 13 099 patients with diabetes who had participated in the Singapore Integrated Diabetic Retinopathy Program, between 2010 and 2013, which has been published previously. In this clinical validation study, we included all patients with a diagnosis of diabetes that attended a mobile screening unit in five urban centres in the Copperbelt province of Zambia from Feb 1 to June 31, 2012. In our model, referable diabetic retinopathy was defined as moderate non-proliferative diabetic retinopathy or worse, diabetic macular oedema, and ungradable images. Vision-threatening diabetic retinopathy comprised severe non-proliferative and proliferative diabetic retinopathy. We calculated the area under the curve (AUC), sensitivity, and specificity for referable diabetic retinopathy, and sensitivities of vision-threatening diabetic retinopathy and diabetic macular oedema compared with the grading by retinal specialists. We did a multivariate analysis for systemic risk factors and referable diabetic retinopathy between AI and human graders.
A total of 4504 retinal fundus images from 3093 eyes of 1574 Zambians with diabetes were prospectively recruited. Referable diabetic retinopathy was found in 697 (22·5%) eyes, vision-threatening diabetic retinopathy in 171 (5·5%) eyes, and diabetic macular oedema in 249 (8·1%) eyes. The AUC of the AI system for referable diabetic retinopathy was 0·973 (95% CI 0·969-0·978), with corresponding sensitivity of 92·25% (90·10-94·12) and specificity of 89·04% (87·85-90·28). Vision-threatening diabetic retinopathy sensitivity was 99·42% (99·15-99·68) and diabetic macular oedema sensitivity was 97·19% (96·61-97·77). The AI model and human graders showed similar outcomes in referable diabetic retinopathy prevalence detection and systemic risk factors associations. Both the AI model and human graders identified longer duration of diabetes, higher level of glycated haemoglobin, and increased systolic blood pressure as risk factors associated with referable diabetic retinopathy.
An AI system shows clinically acceptable performance in detecting referable diabetic retinopathy, vision-threatening diabetic retinopathy, and diabetic macular oedema in population-based diabetic retinopathy screening. This shows the potential application and adoption of such AI technology in an under-resourced African population to reduce the incidence of preventable blindness, even when the model is trained in a different population.
National Medical Research Council Health Service Research Grant, Large Collaborative Grant, Ministry of Health, Singapore; the SingHealth Foundation; and the Tanoto Foundation.
为了实现到 2030 年可持续发展目标而减少因糖尿病导致的失明，需要采取激进的措施。因此，我们评估了人工智能（AI）模型在赞比亚一个基于人群的糖尿病视网膜病变筛查项目中的准确性，赞比亚是一个中低收入国家。
我们采用了一种由两个卷积神经网络（一个改编的 VGGNet 架构和一个残差神经网络架构）组合而成的集成 AI 模型，用于对视网膜彩色眼底图像进行分类。我们在 2010 年至 2013 年期间参加新加坡综合糖尿病视网膜病变计划的 13099 名糖尿病患者的 76370 张视网膜眼底图像上对我们的模型进行了训练，这些图像已经发表过。在这项临床验证研究中，我们纳入了 2012 年 2 月 1 日至 6 月 31 日期间在赞比亚铜带省五个城市流动筛查单位就诊的所有被诊断为糖尿病的患者。在我们的模型中，可检出的糖尿病视网膜病变定义为中度非增生性糖尿病视网膜病变或更严重、糖尿病性黄斑水肿和不可分级的图像。视力威胁性糖尿病视网膜病变包括严重非增生性和增生性糖尿病视网膜病变。我们计算了可检出的糖尿病视网膜病变的曲线下面积（AUC）、敏感性和特异性，以及与视网膜专家分级相比的视力威胁性糖尿病视网膜病变和糖尿病性黄斑水肿的敏感性。我们对 AI 和人类分级员之间的系统危险因素和可检出的糖尿病视网膜病变进行了多变量分析。
我们前瞻性地招募了 3093 只眼中的 1574 名赞比亚糖尿病患者的 4504 张眼底图像。在 697 只（22.5%）眼中发现了可检出的糖尿病视网膜病变，在 171 只（5.5%）眼中发现了视力威胁性糖尿病视网膜病变，在 249 只（8.1%）眼中发现了糖尿病性黄斑水肿。AI 系统对可检出的糖尿病视网膜病变的 AUC 为 0.973（95%CI 0.969-0.978），相应的敏感性为 92.25%（90.10-94.12），特异性为 89.04%（87.85-90.28）。视力威胁性糖尿病视网膜病变的敏感性为 99.42%（99.15-99.68），糖尿病性黄斑水肿的敏感性为 97.19%（96.61-97.77）。AI 模型和人类分级员在可检出的糖尿病视网膜病变患病率检测和系统危险因素关联方面表现出相似的结果。AI 模型和人类分级员均发现糖尿病病程较长、糖化血红蛋白水平较高和收缩压升高与可检出的糖尿病视网膜病变有关。
AI 系统在基于人群的糖尿病视网膜病变筛查中对可检出的糖尿病视网膜病变、视力威胁性糖尿病视网膜病变和糖尿病性黄斑水肿的检测具有可接受的临床性能。这表明，即使在不同人群中进行训练，这种 AI 技术也有可能在资源匮乏的非洲人群中应用和采用，以降低可预防失明的发生率。
国家医学研究委员会卫生服务研究赠款、大型合作研究赠款、新加坡卫生部；新加坡保健集团；和陈嘉庚基金会。
