Park Hyun-Woong, Kim Hae Ri, Nam Ki Yup, Kim Bum Jun, Kang Taeseen
Department of Cardiology, Chungnam National University Sejong Hospital, Sejong, Korea.
Division of Nephrology, Department of Internal Medicine, Chungnam National University Sejong Hospital, Sejong, Korea.
Korean J Intern Med. 2025 Mar;40(2):310-320. doi: 10.3904/kjim.2024.076. Epub 2025 Mar 1.
BACKGROUND/AIMS: The kidneys and retina are highly vascularized organs that frequently exhibit shared pathologies, with nephropathy often associated with retinopathy. Previous studies have successfully predicted estimated glomerular filtration rates (eGFRs) using fundus photographs. We evaluated the performance of the Modification of Diet in Renal Disease (MDRD) and Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) formulas in eGFR prediction.
We enrolled patients with fundus photographs and corresponding creatinine measurements taken on the same date. One photograph per eye was randomly selected, resulting in a final dataset of 45,108 patients (88,260 photographs). Data including sex, age, and blood creatinine levels were collected for eGFR calculation using the MDRD and CKD-EPI formulas. EfficientNet B3 models were used to predict each parameter.
Deep neural network models accurately predicted age and sex using fundus photographs. Sex was identified as a confounding variable in creatinine prediction. The MDRD formula was more susceptible to this confounding effect than the CKD-EPI formula. Notably, the CKD-EPI formula demonstrated superior performance compared to the MDRD formula (area under the curve 0.864 vs. 0.802).
Fundus photographs are a valuable tool for screening renal function using deep neural network models, demonstrating the role of noninvasive imaging in medical diagnostics. However, these models are susceptible to the influence of sex, a potential confounding factor. The CKD-EPI formula, less susceptible to sex bias, is recommended to obtain more reliable results.
背景/目的：肾脏和视网膜是血管高度丰富的器官，常表现出共同的病理变化，肾病通常与视网膜病变相关。以往的研究已成功地利用眼底照片预测估算肾小球滤过率（eGFR）。我们评估了肾脏病饮食改良（MDRD）公式和慢性肾脏病流行病学协作组（CKD-EPI）公式在预测eGFR方面的性能。
我们纳入了在同一天拍摄了眼底照片并进行了相应肌酐测量的患者。每只眼睛随机选择一张照片，最终数据集为45108例患者（88260张照片）。收集包括性别、年龄和血肌酐水平的数据，使用MDRD公式和CKD-EPI公式计算eGFR。使用EfficientNet B3模型预测每个参数。
深度神经网络模型利用眼底照片准确预测了年龄和性别。性别被确定为肌酐预测中的一个混杂变量。MDRD公式比CKD-EPI公式更容易受到这种混杂效应的影响。值得注意的是，与MDRD公式相比，CKD-EPI公式表现更优（曲线下面积分别为0.864和0.802）。
眼底照片是利用深度神经网络模型筛查肾功能的一种有价值的工具，证明了无创成像在医学诊断中的作用。然而，这些模型易受性别这一潜在混杂因素的影响。建议使用受性别偏倚影响较小的CKD-EPI公式以获得更可靠的结果。
