Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images


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.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: AI system for the detection and incidence prediction of systemic diseases using retinal fundus images.
Fig. 2: Performance of the AI models in the identification of CKD and early CKD.
Fig. 3: Model performance in assessing eGFR from retinal fundus images.
Fig. 4: KaplanMeier plots for the prediction of CKD and advanced+ CKD development.
Fig. 5: Performance of the AI system in the identification and incidence prediction of T2DM.
Fig. 6: Gradient visualizations of AI predictions of CKD staging and T2DM using the integrated gradient algorithm.

Similar content being viewed by others

Data availability

Restrictions apply to the availability of the developmental and validation datasets, which were used with permission of the participants for the current study. De-identified data may be available for research purposes from the corresponding authors on reasonable request.

Code availability

The deep-learning models were developed and deployed using standard model libraries and the PyTorch framework. The models can be trained via the publicly available ResNet-50 architecture starting from the pretrained models, available at Custom codes were specific to our development environment and used primarily for data input/output and parallelization across computers and graphics processors. The codes may be available for research purposes from the corresponding authors on reasonable request.


  1. GBD Chronic Kidney Disease Collaboration. Global, regional, and national burden of chronic kidney disease, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet 395, 709–733 (2020).

    Article  Google Scholar 

  2. Levin, A. et al. Global kidney health 2017 and beyond: a roadmap for closing gaps in care, research, and policy. Lancet 390, 1888–1917 (2017).

    Article  Google Scholar 

  3. Kooman, J. P., Kotanko, P., Schols, A. M., Shiels, P. G. & Stenvinkel, P. Chronic kidney disease and premature ageing. Nat. Rev. Nephrol. 10, 732–742 (2014).

    Article  CAS  Google Scholar 

  4. Saeedi, P. et al. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the International Diabetes Federation Diabetes Atlas, 9(th) edition. Diabetes Res. Clin. Pract. 157, 107843 (2019).

    Article  Google Scholar 

  5. Wong, T. Y. & Sabanayagam, C. The war on diabetic retinopathy: where are we now. Asia Pac. J. Ophthalmol. 8, 448–456 (2019).

    Article  Google Scholar 

  6. Balakumar, P., Maung, U. K. & Jagadeesh, G. Prevalence and prevention of cardiovascular disease and diabetes mellitus. Pharmacol. Res. 113, 600–609 (2016).

    Article  Google Scholar 

  7. From the Center of Disease Control and Prevention. Lower extremity amputation episodes among persons with diabetes–New Mexico, 2000. JAMA 289, 1502–1503 (2003).

    Article  Google Scholar 

  8. American Diabetes Association. 11. Microvascular complications and foot care: standards of medical care in diabetes-2020. Diabetes Care 43, S135–S151 (2020).

    Article  Google Scholar 

  9. Luk, A. O. et al. Quality of care in patients with diabetic kidney disease in Asia: The Joint Asia Diabetes Evaluation (JADE) Registry. Diabet. Med. 33, 1230–1239 (2016).

    Article  CAS  Google Scholar 

  10. Wu, B., Zhang, S., Lin, H. & Mou, S. Prevention of renal failure in Chinese patients with newly diagnosed type 2 diabetes: a cost-effectiveness analysis. J. Diabetes Investig. 9, 152–161 (2018).

    Article  CAS  Google Scholar 

  11. Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24–29 (2019).

    Article  CAS  Google Scholar 

  12. Cheung, C. Y., Tang, F., Ting, D. S. W., Tan, G. S. W. & Wong, T. Y. Artificial intelligence in diabetic eye disease screening. Asia Pac. J. Ophthalmol. 8, 158–164 (2019).

    Google Scholar 

  13. Ravizza, S. et al. Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data. Nat. Med. 25, 57–59 (2019).

    Article  CAS  Google Scholar 

  14. Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44–56 (2019).

    Article  CAS  Google Scholar 

  15. Wang, K., Liu, X., Zhang, K., Chen, T. & Wang, G. Anterior segment eye lesion segmentation with advanced fusion strategies and auxiliary tasks. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 12265, 656–664 (Springer, 2020).

  16. Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122–1131(2018).

    Article  CAS  Google Scholar 

  17. Liang, H. et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence. Nat. Med. 25, 433–438 (2019).

    Article  CAS  Google Scholar 

  18. Wang, G. et al. A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images. Nat. Biomed. Eng. (2021).

  19. Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158–164 (2018).

    Article  Google Scholar 

  20. Rim, T. H. et al. Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms. Lancet Digit. Health 2, e526–e536 (2020).

    Article  Google Scholar 

  21. Sabanayagam, C. et al. A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations. Lancet Digit. Health 2, e295–e302 (2020).

    Article  Google Scholar 

  22. Liu, T. Y. A. Smartphone-based, artificial intelligence-enabled diabetic retinopathy screening. JAMA Ophthalmol. 137, 1188–1189 (2019).

    Article  Google Scholar 

  23. Chen, C., Lee, G. G., Sritapan, V. & Lin, C. Deep convolutional neural network on iOS mobile devices. In 2016 IEEE International Workshop on Signal Processing Systems (SiPS) 130–135 (IEEE, 2016);

  24. Wu, Y., Lim, J. & Yang, M. H. Object Tracking Benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1834–1848 (2015).

    Article  Google Scholar 

  25. Schroff, F., Kalenichenko, D. & Philbin, J. FaceNet: A unified embedding for face recognition and clustering. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 815–823 (IEEE, 2015);

  26. Vos, T. et al. Global, regional, and national incidence, prevalence, and years lived with disability for 310 diseases and injuries, 1990–2015: a systematic analysis for the Global Burden of Disease Study 2015. Lancet 388, 1545–1602 (2016).

    Article  Google Scholar 

  27. Gansevoort, R. T. et al. Lower estimated GFR and higher albuminuria are associated with adverse kidney outcomes. A collaborative meta-analysis of general and high-risk population cohorts. Kidney Int. 80, 93–104 (2011).

    Article  CAS  Google Scholar 

  28. Levey, A. S. & Coresh, J. Chronic kidney disease. Lancet 379, 165–180 (2012).

    Article  Google Scholar 

  29. Group, E. T. D. R. S. R. Grading diabetic retinopathy from stereoscopic color fundus photographs—an extension of the modified Airlie House classification: ETDRS report number 10. Ophthalmology 98, 786–806 (1991).

    Article  Google Scholar 

  30. Tuot, D. S. et al. Chronic kidney disease awareness among individuals with clinical markers of kidney dysfunction. Clin. J. Am. Soc. Nephrol.6, 1838–1844 (2011).

    Article  Google Scholar 

  31. Tuttle, K. R. et al. Diabetic kidney disease: a report from an ADA Consensus Conference. Am. J. Kidney Dis. 64, 510–533 (2014).

    Article  Google Scholar 

  32. Wang, Y. et al. China suboptimal health cohort study: rationale, design and baseline characteristics. J. Transl. Med. 14, 291 (2016).

    Article  Google Scholar 

  33. Levin, A. et al. Kidney disease: Improving global outcomes (KDIGO) CKD work group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease. Kidney Int. Suppl. 3, 1–150 (2013).

    Google Scholar 

  34. Levey, A. S., Becker, C. & Inker, L. A. Glomerular filtration rate and albuminuria for detection and staging of acute and chronic kidney disease in adults: a systematic review. JAMA 313, 837–846 (2015).

    Article  CAS  Google Scholar 

  35. Bikbov, B. et al. Global, regional, and national burden of chronic kidney disease, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet 395, 709–733 (2020).

    Article  Google Scholar 

  36. Liao, Y., Liao, W., Liu, J., Xu, G. & Zeng, R. Assessment of the CKD-EPI equation to estimate glomerular filtration rate in adults from a Chinese CKD population. J. Int. Med. Res. 39, 2273–2280 (2011).

    Article  CAS  Google Scholar 

  37. Pisano, E. D. et al. Contrast limited adaptive histogram equalization image processing to improve the detection of simulated spiculations in dense mammograms. J. Digital Imaging 11, 193–200 (1998).

    Article  CAS  Google Scholar 

  38. Liu, P. et al. Large-scale left and right eye classification in retinal images. Comput. Pathol. Ophthalmic Med. Image Anal. 11039, 261–268 (2018).

    Article  Google Scholar 

  39. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (2016);

  40. Kamarudin, A. N., Cox, T. & Kolamunnage-Donà, R. Time-dependent ROC curve analysis in medical research: current methods and applications. BMC Med. Res. Method. 17, 53 (2017).

    Article  Google Scholar 

  41. Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. of the 34th International Conference on Machine Learning-Volume 70 3319 (2017).

  42. Giavarina, D. Understanding Bland Altman analysis. Biochemia Med. 25, 141–151 (2015).

    Article  Google Scholar 

  43. Breslow, N. & Day, N. Statistical Methods in Cancer Research. Volume II–The Design and Analysis of Cohort Studies 82, 1–406 (IARC Scientific Publications, 1987).

Download references


This study was funded by the National Natural Science Foundation of China (61906105, 61872218 and 61721003), National Key Research and Development Program of China (2019YFB1404804, 2017YFC1104600, 2017YFC0112402), 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University (ZYJC20001, ZYJC18010), Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Macau University of Science and Technology, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University Initiative Scientific Research Program, and Guoqiang Institute, Tsinghua University, Wellcome Trust (216593/Z/19/Z). We thank members of the Zhang, Yuan and Wang groups for their assistance. We thank many volunteers and physicians for grading retinal photographs.

Author information

Authors and Affiliations



K. Zhang, X.L., J.X., J.Y., W.C., K.W., T.C., Y.G., S.N., X.X., X.Q., Y. Su, W.X., A.O., K.X., Z.L., M.Z., X. Zeng, C.Z., O.L., E.Z., J.Z., Y.X., D.K., K. Zhou, Y.P., S.L., I.L., Y.C., C.W., M.P., G.Z, Q.Z., J.L., D.L., X. Zou, A.W., J.W., Y. Shen, F.F.H., P.Z., T.X., Y.Z. and G.W. collected and analysed the data. K. Zhang and G.W. conceived and supervised the project. K. Zhang and G.W. wrote the manuscript with assistance from K.X. All authors discussed the results and reviewed the manuscript.

Corresponding authors

Correspondence to Kang Zhang, Ting Chen, Tao Xu, Yong Zhou or Guangyu Wang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review information Nature Biomedical Engineering thanks Sebastian Waldstein and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary methods, figures and tables.

Reporting Summary

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, K., Liu, X., Xu, J. et al. Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images. Nat Biomed Eng 5, 533–545 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

This article is cited by


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing