Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Oct 24;15(1):37318.
doi: 10.1038/s41598-025-21366-y.

Prediction of advanced chronic kidney disease through retinal fundus images by deep learning

Chuan-Fan Hsu #  1 , Tung-Min Yu #  2   3   4 , Ya-Lun Wu  1 , Wei-Chun Wang  1   5   6   7 , Jun-Sing Wang  8 , Shih-Sheng Chang  9   10   11
Affiliations

Prediction of advanced chronic kidney disease through retinal fundus images by deep learning

Chuan-Fan Hsu et al. Sci Rep. .

Abstract

This study was developed and evaluated deep learning model for detecting chronic kidney disease (CKD) by retinal fundus images. This study included 42,963 clinical visits from 17,442 patients who underwent retinal fundus examination between October 19, 2006, and September 13, 2018, with estimated glomerular filtration rate (eGFR) measurements available within a 7-day interval of the imaging examination. We developed and compared three model configurations: using a single fundus image (Model A), combining a single image with demographic features (Model B), and integrating bilateral fundus images (Model C). We compared two base architectures, EfficientNet-B3 and EfficientNetV2-S, and evaluated the impact of different training strategies: a single model versus a 5-fold cross-validation (CV) ensemble. Model performance was assessed using the Area Under the Curve (AUC), sensitivity, specificity, Positive Predictive Value (PPV) and Negative Predictive Value (NPV). Among all evaluated models, the bilateral-image model (Model C) utilizing the EfficientNet-B3 architecture with a 5-fold CV ensemble strategy demonstrated the best overall performance, achieving an AUC of 0.868, with a sensitivity of 0.792 and a specificity of 0.788 on an independent test set. The performance of this ensemble strategy was statistically superior to its single-model counterpart trained on the full dataset (AUC 0.850, p < 0.001). Among single models, Model B yielded the highest AUC (0.857) and sensitivity (0.794), while Model C offered the highest specificity (0.799), revealing a clinical trade-off between the different approaches. Furthermore, benchmarking against the newer EfficientNetV2-S architecture did not yield a performance benefit in this study. The study exhibited a superior performance in detecting advanced chronic kidney disease in patients with diabetes mellitus through retinal fundus image.

Keywords: Chronic kidney disease; Deep learning; Retinal fundus image.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethics statement: This study was approved by the Ethics Committee of China Medical University Hospital [Approval number: CMUH114-REC3-054] and was conducted in accordance with the ethical principles of the Declaration of Helsinki. The dataset consists of previously de-identified data used for research purposes, with all personally identifiable information encrypted. Due to the retrospective nature of the study and the anonymization of all data prior to analysis, the requirement for informed consent was waived by the Ethics Committee of China Medical University Hospital [Approval number: CMUH114-REC3-054]. All methods were carried out in accordance with relevant guidelines and regulations. Guarantor statement: Shih-Sheng Chang is the guarantor of this work and, as such, had full access to all the data in the study and takes responsibility for the integrity of the data and the accuracy of the data analysis.

Figures

Fig. 1
Fig. 1
Overview of deep learning models for chronic kidney disease (CKD) classification in this study.
Fig. 2
Fig. 2
Confusion Matrix of the Best-Performing Model. The confusion matrix illustrates the classification results of the best-performing model in this study—Model C, which utilizes the EfficientNet-B3 architecture with a 5-fold CV ensemble strategy—on the independent test set comprising 8,520 cases.
Fig. 3
Fig. 3
(A) Fundus image. (B) Fundus image with saliency map. (C) Fundus image removed optic disc with saliency map. (D) Fundus image removed blood vessels with saliency map. (E) Fundus image removed optic disc and blood vessels with saliency map.
See this image and copyright information in PMC

References

    1. Vithian, K. & Hurel, S. Microvascular complications: pathophysiology and management. Clin. Med. (Lond). 10, 505–509 (2010). - PMC - PubMed
    1. Khalid, M., Petroianu, G. & Adem, A. Advanced glycation end products and diabetes mellitus: mechanisms and perspectives. Biomolecules12, 542 (2022). - PMC - PubMed
    1. Yang, J. & Liu, Z. Mechanistic pathogenesis of endothelial dysfunction in diabetic nephropathy and retinopathy. Front. Endocrinol. (Lausanne). 13, 816400 (2022). - PMC - PubMed
    1. Cheng, H. & Harris, R. C. Renal endothelial dysfunction in diabetic nephropathy. Cardiovasc. Hematol. Disord Drug Targets. 14, 22–33 (2014). - PMC - PubMed
    1. Fang, J., Luo, C., Zhang, D., He, Q. & Liu, L. Correlation between diabetic retinopathy and diabetic nephropathy: a two-sample Mendelian randomization study. Front. Endocrinol. (Lausanne). 14, 1265711 (2023). - PMC - PubMed