CoChat

A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations

Open access

The DOI matches its Crossref record; 31 of the 32 references it cites were found in a registry or an index.

Abstract

Background Screening for chronic kidney disease is a challenge in community and primary care settings, even in high-income countries. We developed an artificial intelligence deep learning algorithm (DLA) to detect chronic kidney disease from retinal images, which could add to existing chronic kidney disease screening strategies. Methods We used data from three population-based, multiethnic, cross-sectional studies in Singapore and China. The Singapore Epidemiology of Eye Diseases study (SEED, patients aged ≥40 years) was used to develop (5188 patients) and validate (1297 patients) the DLA. External testing was done on two independent datasets: the Singapore Prospective Study Program (SP2, 3735 patients aged ≥25 years) and the Beijing Eye Study (BES, 1538 patients aged ≥40 years). Chronic kidney disease was defined as estimated glomerular filtration rate less than 60 mL/min per 1·73m 2 . Three models were trained: 1) image DLA; 2) risk factors (RF) including age, sex, ethnicity, diabetes, and hypertension; and 3) hybrid DLA combining image and RF. Model performances were evaluated using the area under the receiver operating characteristic curve (AUC). Findings In the SEED validation dataset, the AUC was 0·911 for image DLA (95% CI 0·886 −0·936), 0·916 for RF (0·891–0·941), and 0·938 for hybrid DLA (0·917–0·959). Corresponding estimates in the SP2 testing dataset were 0·733 for image DLA (95% CI 0·696–0·770), 0·829 for RF (0·797–0·861), and 0·810 for hybrid DLA (0·776–0·844); and in the BES testing dataset estimates were 0·835 for image DLA (0·767–0·903), 0·887 for RF (0·828–0·946), and 0·858 for hybrid DLA (0·794–0·922). AUC estimates were similar in subgroups of people with diabetes (image DLA 0·889 [95% CI 0·850–0·928], RF 0·899 [0·862–0·936], hybrid 0·925 [0·893–0·957]) and hypertension (image DLA 0·889 [95% CI 0·860–0·918], RF 0·889 [0·860–0·918], hybrid 0·918 [0·893–0·943]). Interpretation A retinal image DLA shows good performance for estimating chronic kidney disease, underlying the feasibility of using retinal photography as an adjunctive or opportunistic screening tool for chronic kidney disease in community populations. Funding National Medical Research Council, Singapore.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/s2589-7500(20)30063-7

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Convolutional neural network architecture for chronic kidney disease from retinal images
Figure 1 Convolutional neural network architecture for chronic kidney disease from retinal imagesCC-BY · From the PDF
Figure 2 RoC curves for prediction of chronic kidney disease in image-only, risk factors, and hybrid models
Figure 2 RoC curves for prediction of chronic kidney disease in image-only, risk factors, and hybrid modelsCC-BY · From the PDF
Figure 3 Heatmaps of chronic kidney disease controls and cases (A) Control: no chronic kidney disease (eGFR 108 mL/min per 1·73 m²); (B) Control: no Chronic kidney disease (eGFR 100 mL/min per 1·73 m²). (C) Chronic kidney disease (eGFR 30 mL/min per 1·73 m²) in a person with hypertension (systolic blood pressure 155 mm Hg). (D) Chronic kidney disease (eGFR 45 mL/min per 1·73 m²) in a person with uncontrolled diabetes (HbA 1c 12·7%). (E) Chronic kidney disease (eGFR 30 mL/min per 1·73 m²), in a person with hypertension (systolic blood pressure 150 mm Hg), diabetes (HbA 1c 7·4%), and moderate diabetic retinopathy. eGFR=estimated glomerular filtration rate. HbA 1c =glycated haemoglobin.
Figure 3 Heatmaps of chronic kidney disease controls and cases (A) Control: no chronic kidney disease (eGFR 108 mL/min per 1·73 m²); (B) Control: no Chronic kidney disease (eGFR 100 mL/min per 1·73 m²). (C) Chronic kidney disease (eGFR 30 mL/min per 1·73 m²) in a person with hypertension (systolic blood pressure 155 mm Hg). (D) Chronic kidney disease (eGFR 45 mL/min per 1·73 m²) in a person with uncontrolled diabetes (HbA 1c 12·7%). (E) Chronic kidney disease (eGFR 30 mL/min per 1·73 m²), in a person with hypertension (systolic blood pressure 150 mm Hg), diabetes (HbA 1c 7·4%), and moderate diabetic retinopathy. eGFR=estimated glomerular filtration rate. HbA 1c =glycated haemoglobin.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 31 references

Cited by

See all 279

Metadata

Authors
Sabanayagam, C., Xu, D., Ting, D. S. W., Nusinovici, S., Banu, R., Hamzah, H., Lim, C., Tham, Y.-C., Cheung, C. Y., Tai, E. S., Wang, Y. X., Jonas, J. B., Cheng, C.-Y., Lee, M. L., Hsu, W., & Wong, T. Y.
Affiliations
  • National University of Singapore (SG)
  • Singapore National Eye Center (SG)
  • Singapore General Hospital (SG)
  • Chinese University of Hong Kong (HK)
  • Beijing Tongren Hospital (CN)
Corresponding author
Wong, Tien Y
Venue
The Lancet Digital Health
Publisher
Elsevier BV
Published
2020-06
Volume
2
Issue
6
Pages
e295-e302
ISSN
2589-7500 (ISSN-L)
OpenAlex
W3025767749
Cited by
279
References
32
Citations by year
2026: 40 · 2025: 58 · 2024: 54 · 2023: 55 · 2022: 40 · 2021: 25 · 2020: 6
FWCI
15.34
Type
journal article
Language
en
Open access
Licence
Locations
  • The Lancet Digital Health (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • National University of Singapore (submittedVersion)
Funders
National Medical Research Council (OFLCG/001/2017, NMRC/STaR/003/2008, NMRC/0796/2003, NMRC/1249/2010, NMRC/STaR/0016/2013, NMRC/CIRG/1417/2015)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
  • Health Sciences › Medicine › Nephrology › Chronic Kidney Disease and Diabetes
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
chronic kidney disease, fundus photography, deep learning algorithms, automated disease detection, kidney disease screening, estimated glomerular filtration rate, retinal microvascular abnormalities, diabetes mellitus, hypertension, risk factors, community-based population, primary care, Singapore, China, multi-ethnic population, external validation, Beijing Eye Study
MeSH terms
Deep Learning, Algorithms, China, Cross-Sectional Studies, Eye Diseases, Female, Fundus Oculi, Humans, Image Interpretation, Computer-Assisted, Male, Middle Aged, Photography, Sensitivity and Specificity, Singapore, Reproducibility of Results, Renal Insufficiency, Chronic

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations. https://app.cochat.ai/papers/10.1016/s2589-7500(20)30063-7
The paper
Sabanayagam, C., Xu, D., Ting, D. S. W., Nusinovici, S., Banu, R., Hamzah, H., Lim, C., Tham, Y.-C., Cheung, C. Y., Tai, E. S., Wang, Y. X., Jonas, J. B., Cheng, C.-Y., Lee, M. L., Hsu, W., & Wong, T. Y. (2020). A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations. The Lancet Digital Health. https://doi.org/10.1016/s2589-7500(20)30063-7

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.