Deep Learning–Based Detection of Early Renal Function Impairment Using Retinal Fundus Images: Model Development and Validation

Abstract

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.

A Multimodal Imaging–Based Deep Learning Model for Detecting Treatment-Requiring Retinal Vascular Diseases: Model Development and Validation Study

“…The efficacy during application to a real-world clinical setting may be affected by the patient’s condition and the image quality [ 39 ]. Additionally, some ocular diseases affecting image signal transmission could affect image quality and retinal disease diagnosis [ 40 , 41 ]. Third, images from different machine manufacturers not included in our study might have affected the model accuracy.…”

Artificial Intelligence in Predicting Systemic Parameters and Diseases From Ophthalmic Imaging

“…This lacked external validation ( 80 ). Kang et al ( 28 ) sought to predict early renal impairment from RFP, defined as eGFR < 90 ml/min/1.73 m 2 , but observed poor specificity. They noted false positives arising from RFP with retinal scarring, subretinal fluid, or optic disc swelling.…”

“…Hence, clinical utility might be limited as many concomitant ophthalmic pathologies can cause such retinal structural manifestations. Features used to identify CKD or predict eGFR are unclear—saliency maps ( 28 , 39 ) have highlighted changes in retinal vasculature (dilatation of venules, rarefaction of vessels) and abnormal lesions characteristic of retinopathy (hemorrhages and exudations). A model by Rim et al ( 38 ) showed moderate performance in predicting creatinine levels ( R 2 : 0.38) when trained and tested on a South Korean dataset but was unable to generalize to a European dataset (UK Biobank, R 2 : 0.01).…”

Heart Rate Modeling and Prediction Using Autoregressive Models and Deep Learning

“…The fields of application range from classification [ 19 , 20 , 21 ] to prediction [ 22 , 23 ]. Furthermore, generative adversarial networks (GANs) have been used for efficient data augmentation and to solve data privacy concerns [ 24 , 25 ].…”