Objective: We aimed to develop and evaluate a non-invasive deep learning algorithm for screening type 2 diabetes in UK Biobank participants using retinal images. Research Design and Methods: The deep learning model for prediction of type 2 diabetes was trained on retinal images from 50,077 UK Biobank participants and tested on 12,185 participants. We evaluated its performance in terms of predicting traditional risk factors (TRFs) and genetic risk for diabetes. Next, we compared the performance of three models in predicting type 2 diabetes using 1) an image-only deep learning algorithm, 2) TRFs, 3) the combination of the algorithm and TRFs. Assessing net reclassification improvement (NRI) allowed quantification of the improvement afforded by adding the algorithm to the TRF model. Results: When predicting TRFs with the deep learning algorithm, the areas under the curve (AUCs) obtained with the validation set for age, sex, and HbA1c status were 0.931 (0.928-0.934), 0.933 (0.929-0.936), and 0.734 (0.715-0.752), respectively. When predicting type 2 diabetes, the AUC of the composite logistic model using non-invasive TRFs was 0.810 (0.790-0.830), and that for the deep learning model using only fundus images was 0.731 (0.707-0.756). Upon addition of TRFs to the deep learning algorithm, discriminative performance was improved to 0.844 (0.826-0.861). The addition of the algorithm to the TRFs model improved risk stratification with an overall NRI of 50.8%. Conclusions: Our results demonstrate that this deep learning algorithm can be a useful tool for stratifying individuals at high risk of type 2 diabetes in the general population.

中文翻译：

---

从视网膜照片中筛查 2 型糖尿病的深度学习模型

目标：我们旨在开发和评估一种非侵入性深度学习算法，用于使用视网膜图像在英国生物银行参与者中筛查 2 型糖尿病。研究设计和方法：用于预测 2 型糖尿病的深度学习模型在来自 50,077 名英国生物银行参与者的视网膜图像上进行了训练，并在 12,185 名参与者中进行了测试。我们评估了其在预测糖尿病的传统风险因素 (TRF) 和遗传风险方面的表现。接下来，我们使用 1) 仅图像深度学习算法，2) TRF，3) 算法和 TRF 的组合，比较了三种模型在预测 2 型糖尿病方面的性能。评估净重分类改进 (NRI) 允许量化通过将算法添加到 TRF 模型所提供的改进。结果：在使用深度学习算法预测 TRF 时，使用年龄、性别和 HbA1c 状态的验证集获得的曲线下面积 (AUC) 分别为 0.931 (0.928-0.934)、0.933 (0.929-0.936) 和 0.734 (0.715-0.752)。在预测2型糖尿病时，使用无创TRFs的复合logistic模型的AUC为0.810（0.790-0.830），仅使用眼底图像的深度学习模型的AUC为0.731（0.707-0.756）。将 TRF 添加到深度学习算法后，判别性能提高到 0.844 (0.826-0.861)。将算法添加到 TRFs 模型改进了风险分层，整体 NRI 为 50.8%。结论：我们的结果表明，这种深度学习算法可以成为对一般人群中 2 型糖尿病高危个体进行分层的有用工具。