Abstract
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
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
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 https://github.com/pytorch/vision. 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.
References
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).
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).
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).
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).
Wong, T. Y. & Sabanayagam, C. The war on diabetic retinopathy: where are we now. Asia Pac. J. Ophthalmol. 8, 448–456 (2019).
Balakumar, P., Maung, U. K. & Jagadeesh, G. Prevalence and prevention of cardiovascular disease and diabetes mellitus. Pharmacol. Res. 113, 600–609 (2016).
From the Center of Disease Control and Prevention. Lower extremity amputation episodes among persons with diabetes–New Mexico, 2000. JAMA 289, 1502–1503 (2003).
American Diabetes Association. 11. Microvascular complications and foot care: standards of medical care in diabetes-2020. Diabetes Care 43, S135–S151 (2020).
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).
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).
Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24–29 (2019).
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).
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).
Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44–56 (2019).
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).
Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122–1131(2018).
Liang, H. et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence. Nat. Med. 25, 433–438 (2019).
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. https://doi.org/10.1038/s41551-021-00704-1 (2021).
Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158–164 (2018).
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).
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).
Liu, T. Y. A. Smartphone-based, artificial intelligence-enabled diabetic retinopathy screening. JAMA Ophthalmol. 137, 1188–1189 (2019).
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); https://doi.org/10.1109/SiPS.2016.31
Wu, Y., Lim, J. & Yang, M. H. Object Tracking Benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1834–1848 (2015).
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); https://doi.org/10.1109/CVPR.2015.7298682
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).
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).
Levey, A. S. & Coresh, J. Chronic kidney disease. Lancet 379, 165–180 (2012).
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).
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).
Tuttle, K. R. et al. Diabetic kidney disease: a report from an ADA Consensus Conference. Am. J. Kidney Dis. 64, 510–533 (2014).
Wang, Y. et al. China suboptimal health cohort study: rationale, design and baseline characteristics. J. Transl. Med. 14, 291 (2016).
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).
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).
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).
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).
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).
Liu, P. et al. Large-scale left and right eye classification in retinal images. Comput. Pathol. Ophthalmic Med. Image Anal. 11039, 261–268 (2018).
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); https://doi.org/10.1109/CVPR.2016.90
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).
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).
Giavarina, D. Understanding Bland Altman analysis. Biochemia Med. 25, 141–151 (2015).
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).
Acknowledgements
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
Contributions
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
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.
Rights and permissions
About this article
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). https://doi.org/10.1038/s41551-021-00745-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41551-021-00745-6
This article is cited by
-
Prognostic potentials of AI in ophthalmology: systemic disease forecasting via retinal imaging
Eye and Vision (2024)
-
Data encoding for healthcare data democratization and information leakage prevention
Nature Communications (2024)
-
Artificial intelligence-based prediction of neurocardiovascular risk score from retinal swept-source optical coherence tomography–angiography
Scientific Reports (2024)
-
Visual interpretability of image-based classification models by generative latent space disentanglement applied to in vitro fertilization
Nature Communications (2024)
-
AI-integrated ocular imaging for predicting cardiovascular disease: advancements and future outlook
Eye (2024)
