Regular screening for the early detection of common chronic diseases might benefit from the use of deep-learning approaches, particularly in resource-poor or remote settings. Here we show that deep-learning models can be used to identify chronic kidney disease and type 2 diabetes solely from fundus images or in combination with clinical metadata (age, sex, height, weight, body-mass index and blood pressure) with areas under the receiver operating characteristic curve of 0.85–0.93. The models were trained and validated with a total of 115,344 retinal fundus photographs from 57,672 patients and can also be used to predict estimated glomerulal filtration rates and blood-glucose levels, with mean absolute errors of 11.1–13.4 ml min⁻¹ per 1.73 m² and 0.65–1.1 mmol l⁻¹, and to stratify patients according to disease-progression risk. We evaluated the generalizability of the models for the identification of chronic kidney disease and type 2 diabetes with population-based external validation cohorts and via a prospective study with fundus images captured with smartphones, and assessed the feasibility of predicting disease progression in a longitudinal cohort.

定期筛查以早期发现常见慢性病可能会受益于深度学习方法的使用，尤其是在资源匮乏或偏远地区。在这里，我们展示了深度学习模型可用于仅从眼底图像或与临床元数据（年龄、性别、身高、体重、体重指数和血压）相结合来识别慢性肾脏病和 2 型糖尿病。受试者工作特征曲线为 0.85-0.93。这些模型经过训练和验证，共使用来自 57,672 名患者的 115,344 张视网膜眼底照片，还可用于预测估计的肾小球滤过率和血糖水平，平均绝对误差为 11.1–13.4 ml min ^-1每 1.73 m ²和 0.65–1.1 mmol l ^-1，并根据疾病进展风险对患者进行分层。我们通过基于人群的外部验证队列和通过智能手机拍摄的眼底图像的前瞻性研究评估了用于识别慢性肾病和 2 型糖尿病的模型的普遍性，并评估了在纵向队列中预测疾病进展的可行性。