Background Retinal imaging has been applied for detecting eye diseases and cardiovascular risks using deep learning–based methods. Furthermore, retinal microvascular and structural changes were found in renal function impairments. However, a deep learning–based method using retinal images for detecting early renal function impairment has not yet been well studied. Objective This study aimed to develop and evaluate a deep learning model for detecting early renal function impairment using retinal fundus images. Methods This retrospective study enrolled patients who underwent renal function tests with color fundus images captured at any time between January 1, 2001, and August 31, 2019. A deep learning model was constructed to detect impaired renal function from the images. Early renal function impairment was defined as estimated glomerular filtration rate <90 mL/min/1.73 m2. Model performance was evaluated with respect to the receiver operating characteristic curve and area under the curve (AUC). Results In total, 25,706 retinal fundus images were obtained from 6212 patients for the study period. The images were divided at an 8:1:1 ratio. The training, validation, and testing data sets respectively contained 20,787, 2189, and 2730 images from 4970, 621, and 621 patients. There were 10,686 and 15,020 images determined to indicate normal and impaired renal function, respectively. The AUC of the model was 0.81 in the overall population. In subgroups stratified by serum hemoglobin A1c (HbA1c) level, the AUCs were 0.81, 0.84, 0.85, and 0.87 for the HbA1c levels of ≤6.5%, >6.5%, >7.5%, and >10%, respectively. Conclusions The deep learning model in this study enables the detection of early renal function impairment using retinal fundus images. The model was more accurate for patients with elevated serum HbA1c levels.

BACKGROUND Retinal imaging has been applied for detecting eye diseases and cardiovascular risks using deep learning–based methods. Furthermore, retinal microvascular and structural changes were found in renal function impairment. However, a deep learning–based method for detecting early renal function impairment from retinal images has not yet been well studied. OBJECTIVE This study aimed to establish and evaluate a deep learning model for detecting early renal function impairment from retinal fundus images. METHODS This retrospective study enrolled patients who underwent renal function tests with color fundus images at any time between 2001 and 2019. A deep learning model was constructed to detect impaired renal function from the images. Early renal function impairment was defined as estimated glomerular filtration rate < 90 mL/min/1.73 m2. Model performance was evaluated with respect to receiver operating characteristic curve and area under the curve (AUC). RESULTS In total, 25 706 retinal fundus images were obtained from 6212 patients for the study period. The images were divided at an 8:1:1 ratio. The training, validation, and testing data sets respectively, contained 20 787, 2189, and 2730 images from 4970, 621, and 621 patients. There were 10 686 and 15 020 images determined to indicate normal and impaired renal function, respectively. The AUC of the model was 0.81 in the overall population. In subgroups stratified by serum hemoglobin A1c (HbA1c) level, AUCs were 0.81, 0.84, 0.85, and 0.87 for the HbA1c levels of ≤6.5%, >6.5%, >7.5%, and >10%, respectively. CONCLUSIONS This study’s deep learning model allows for early renal function impairment to be detected using retinal fundus images. The model was more accurate for patients with elevated serum HbA1c levels.