{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T12:47:49Z","timestamp":1776170869807,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Korean Nephrology Research Foundation"},{"DOI":"10.13039\/501100003625","name":"Ministry of Health and Welfare","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003625","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Despite the importance of preventing chronic kidney disease (CKD), predicting high-risk patients who require active intervention is challenging, especially in people with preserved kidney function. In this study, a predictive risk score for CKD (Reti-CKD score) was derived from a deep learning algorithm using retinal photographs. The performance of the Reti-CKD score was verified using two longitudinal cohorts of the UK Biobank and Korean Diabetic Cohort. Validation was done in people with preserved kidney function, excluding individuals with eGFR &lt;90\u2009mL\/min\/1.73\u2009m<jats:sup>2<\/jats:sup> or proteinuria at baseline. In the UK Biobank, 720\/30,477 (2.4%) participants had CKD events during the 10.8-year follow-up period. In the Korean Diabetic Cohort, 206\/5014 (4.1%) had CKD events during the 6.1-year follow-up period. When the validation cohorts were divided into quartiles of Reti-CKD score, the hazard ratios for CKD development were 3.68 (95% Confidence Interval [CI], 2.88\u20134.41) in the UK Biobank and 9.36 (5.26\u201316.67) in the Korean Diabetic Cohort in the highest quartile compared to the lowest. The Reti-CKD score, compared to eGFR based methods, showed a superior concordance index for predicting CKD incidence, with a delta of 0.020 (95% CI, 0.011\u20130.029) in the UK Biobank and 0.024 (95% CI, 0.002\u20130.046) in the Korean Diabetic Cohort. In people with preserved kidney function, the Reti-CKD score effectively stratifies future CKD risk with greater performance than conventional eGFR-based methods.<\/jats:p>","DOI":"10.1038\/s41746-023-00860-5","type":"journal-article","created":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T14:01:53Z","timestamp":1687010513000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Non-invasive chronic kidney disease risk stratification tool derived from retina-based deep learning and clinical factors"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7890-0928","authenticated-orcid":false,"given":"Young Su","family":"Joo","sequence":"first","affiliation":[]},{"given":"Tyler Hyungtaek","family":"Rim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4510-2823","authenticated-orcid":false,"given":"Hee Byung","family":"Koh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2895-8483","authenticated-orcid":false,"given":"Joseph","family":"Yi","sequence":"additional","affiliation":[]},{"given":"Hyeonmin","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Geunyoung","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Young Ah","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Shin-Wook","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Sung Soo","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2325-8982","authenticated-orcid":false,"given":"Jung Tak","family":"Park","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"860_CR1","doi-asserted-by":"publisher","first-page":"382","DOI":"10.23876\/j.krcp.18.0128","volume":"38","author":"KM Kim","year":"2019","unstructured":"Kim, K. M., Oh, H. J., Choi, H. Y., Lee, H. & Ryu, D. R. Impact of chronic kidney disease on mortality: a nationwide cohort study. Kidney Res Clin. Pr. 38, 382\u2013390 (2019).","journal-title":"Kidney Res Clin. Pr."},{"key":"860_CR2","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1161\/CIRCULATIONAHA.120.050686","volume":"143","author":"J Jankowski","year":"2021","unstructured":"Jankowski, J., Floege, J., Fliser, D., B\u00f6hm, M. & Marx, N. Cardiovascular disease in chronic kidney disease: pathophysiological insights and therapeutic options. Circulation 143, 1157\u20131172 (2021).","journal-title":"Circulation"},{"key":"860_CR3","doi-asserted-by":"publisher","first-page":"2504","DOI":"10.1681\/ASN.2014070714","volume":"26","author":"S Thompson","year":"2015","unstructured":"Thompson, S. et al. Cause of death in patients with reduced kidney function. J. Am. Soc. Nephrology JASN 26, 2504\u20132511 (2015).","journal-title":"J. Am. Soc. Nephrology JASN"},{"key":"860_CR4","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1016\/S0140-6736(20)30045-3","volume":"395","author":"GBD Chronic Kidney Disease Collaboration.","year":"2020","unstructured":"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\u2013733 (2020).","journal-title":"Lancet"},{"key":"860_CR5","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1016\/j.kint.2018.04.011","volume":"94","author":"Y Xie","year":"2018","unstructured":"Xie, Y. et al. Analysis of the Global Burden of Disease study highlights the global, regional, and national trends of chronic kidney disease epidemiology from 1990 to 2016. Kidney Int. 94, 567\u2013581 (2018).","journal-title":"Kidney Int."},{"key":"860_CR6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1038\/kisup.2012.65","volume":"3","author":"Kidney Disease: Improving global outcomes (KDIGO) CKD work group.","year":"2013","unstructured":"Kidney Disease: Improving global outcomes (KDIGO) CKD work group. Chapter 2: Definition, identification, and prediction of CKD progression. Kidney Int. Suppl. 3, 63\u201372 (2013).","journal-title":"Kidney Int. Suppl."},{"key":"860_CR7","doi-asserted-by":"publisher","first-page":"3263","DOI":"10.1093\/ndt\/gfp428","volume":"24","author":"SS Waikar","year":"2009","unstructured":"Waikar, S. S., Betensky, R. A. & Bonventre, J. V. Creatinine as the gold standard for kidney injury biomarker studies? Nephrol. Dialysis Transplant. 24, 3263\u20133265 (2009).","journal-title":"Nephrol. Dialysis Transplant."},{"key":"860_CR8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.5527\/wjn.v4.i1.57","volume":"4","author":"S Lopez-Giacoman","year":"2015","unstructured":"Lopez-Giacoman, S. & Madero, M. Biomarkers in chronic kidney disease, from kidney function to kidney damage. World J. Nephrol. 4, 57\u201373 (2015).","journal-title":"World J. Nephrol."},{"key":"860_CR9","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1515\/CCLM.2009.263","volume":"47","author":"AA Soares","year":"2009","unstructured":"Soares, A. A. et al. Glomerular filtration rate measurement and prediction equations. Clin. Chem. Lab Med. 47, 1023\u20131032 (2009).","journal-title":"Clin. Chem. Lab Med."},{"key":"860_CR10","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1053\/j.ajkd.2012.04.010","volume":"60","author":"CN Naresh","year":"2012","unstructured":"Naresh, C. N., Hayen, A., Craig, J. C. & Chadban, S. J. Day-to-day variability in spot urine protein-creatinine ratio measurements. Am. J. Kidney Dis. 60, 561\u2013566 (2012).","journal-title":"Am. J. Kidney Dis."},{"key":"860_CR11","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1071\/PY17156","volume":"24","author":"JE Manski-Nankervis","year":"2018","unstructured":"Manski-Nankervis, J. E. et al. Screening and diagnosis of chronic kidney disease in people with type 2 diabetes attending Australian general practice. Aust. J. Prim. Health 24, 280\u2013286 (2018).","journal-title":"Aust. J. Prim. Health"},{"key":"860_CR12","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1038\/ki.2013.491","volume":"85","author":"CW Wong","year":"2014","unstructured":"Wong, C. W., Wong, T. Y., Cheng, C. Y. & Sabanayagam, C. Kidney and eye diseases: common risk factors, etiological mechanisms, and pathways. Kidney Int. 85, 1290\u20131302 (2014).","journal-title":"Kidney Int."},{"key":"860_CR13","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1093\/aje\/kwn367","volume":"169","author":"C Sabanayagam","year":"2009","unstructured":"Sabanayagam, C. et al. Retinal microvascular caliber and chronic kidney disease in an Asian population. Am. J. Epidemiol. 169, 625\u2013632 (2009).","journal-title":"Am. J. Epidemiol."},{"key":"860_CR14","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1001\/jamaophthalmol.2019.1052","volume":"137","author":"JE Grunwald","year":"2019","unstructured":"Grunwald, J. E. et al. Association between progression of retinopathy and concurrent progression of kidney disease: findings from the chronic renal insufficiency cohort (CRIC) study. JAMA Ophthalmol. 137, 767\u2013774 (2019).","journal-title":"JAMA Ophthalmol."},{"key":"860_CR15","doi-asserted-by":"publisher","first-page":"e526","DOI":"10.1016\/S2589-7500(20)30216-8","volume":"2","author":"TH Rim","year":"2020","unstructured":"Rim, T. H. et al. Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms. Lancet Digit Health 2, e526\u2013e536 (2020).","journal-title":"Lancet Digit Health"},{"key":"860_CR16","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158\u2013164 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"860_CR17","doi-asserted-by":"publisher","first-page":"e295","DOI":"10.1016\/S2589-7500(20)30063-7","volume":"2","author":"C Sabanayagam","year":"2020","unstructured":"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\u2013e302 (2020).","journal-title":"Lancet Digit Health"},{"key":"860_CR18","doi-asserted-by":"publisher","first-page":"1540","DOI":"10.1681\/ASN.2006050445","volume":"18","author":"WB Eijkelkamp","year":"2007","unstructured":"Eijkelkamp, W. B. et al. Albuminuria is a target for renoprotective therapy independent from blood pressure in patients with type 2 diabetic nephropathy: post hoc analysis from the Reduction of Endpoints in NIDDM with the Angiotensin II Antagonist Losartan (RENAAL) trial. J. Am. Soc. Nephrology 18, 1540\u20131546 (2007).","journal-title":"J. Am. Soc. Nephrology"},{"key":"860_CR19","first-page":"Cd010137","volume":"6","author":"M Ruospo","year":"2017","unstructured":"Ruospo, M. et al. Glucose targets for preventing diabetic kidney disease and its progression. Cochrane Database Syst. Rev. 6, Cd010137 (2017).","journal-title":"Cochrane Database Syst. Rev."},{"key":"860_CR20","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.kint.2020.10.012","volume":"99","author":"MG Shlipak","year":"2021","unstructured":"Shlipak, M. G. et al. The case for early identification and intervention of chronic kidney disease: conclusions from a Kidney Disease: Improving Global Outcomes (KDIGO) Controversies Conference. Kidney Int. 99, 34\u201347 (2021).","journal-title":"Kidney Int."},{"key":"860_CR21","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1001\/archinternmed.2011.2230","volume":"172","author":"SG Coca","year":"2012","unstructured":"Coca, S. G., Ismail-Beigi, F., Haq, N., Krumholz, H. M. & Parikh, C. R. Role of intensive glucose control in development of renal end points in type 2 diabetes mellitus: systematic review and meta-analysis. Arch. Intern. Med. 172, 761\u2013769 (2012).","journal-title":"Arch. Intern. Med."},{"key":"860_CR22","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1056\/NEJMoa1611925","volume":"377","author":"B Neal","year":"2017","unstructured":"Neal, B. et al. Canagliflozin and cardiovascular and renal events in type 2 diabetes. N. Engl. J. Med. 377, 644\u2013657 (2017).","journal-title":"N. Engl. J. Med."},{"key":"860_CR23","doi-asserted-by":"crossref","unstructured":"Cheung, K. L. et al. Risk factors for incident CKD in Black and White Americans: the REGARDS study. Am. J. Kidney Dis. S0272-6386, 00005-7 (2023).","DOI":"10.1053\/j.ajkd.2022.11.015"},{"key":"860_CR24","doi-asserted-by":"publisher","first-page":"A7","DOI":"10.1053\/j.ajkd.2019.01.001","volume":"73","author":"R Saran","year":"2019","unstructured":"Saran, R. et al. US renal data system 2018 annual data report: epidemiology of kidney disease in the United States. Am. J. Kidney Dis. 73, A7\u2013a8 (2019).","journal-title":"Am. J. Kidney Dis."},{"key":"860_CR25","doi-asserted-by":"publisher","first-page":"S46","DOI":"10.2337\/dc22-S004","volume":"45","author":"B Draznin","year":"2022","unstructured":"Draznin, B. et al. 4. Comprehensive medical evaluation and assessment of comorbidities: standards of medical care in diabetes-2022. Diabetes Care 45, S46\u2013s59 (2022).","journal-title":"Diabetes Care"},{"key":"860_CR26","doi-asserted-by":"publisher","first-page":"2685","DOI":"10.1038\/s41433-021-01572-4","volume":"35","author":"T Das","year":"2021","unstructured":"Das, T. et al. Recently updated global diabetic retinopathy screening guidelines: commonalities, differences, and future possibilities. Eye 35, 2685\u20132698 (2021).","journal-title":"Eye"},{"key":"860_CR27","doi-asserted-by":"crossref","unstructured":"Unger, T. et al. 2020 International Society of Hypertension Global Hypertension Practice Guidelines. Hypertension 75, 1334\u20131357 (2020).","DOI":"10.1161\/HYPERTENSIONAHA.120.15026"},{"key":"860_CR28","doi-asserted-by":"crossref","unstructured":"Kim, H. W. et al. Systolic blood pressure and chronic kidney disease progression in patients with primary glomerular disease. J. Nephrol. 34, 1057\u20131067 (2021).","DOI":"10.1007\/s40620-020-00930-x"},{"key":"860_CR29","doi-asserted-by":"crossref","unstructured":"Lee, J. Y. et al. Association of blood pressure with the progression of CKD: findings from KNOW-CKD study. Am. J. Kidney Dis. 78, 236\u2013245 (2021).","DOI":"10.1053\/j.ajkd.2020.12.013"},{"key":"860_CR30","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.kint.2021.05.021","volume":"100","author":"Kidney Disease: Improving Global Outcomes (KDIGO) Glomerular Diseases Work Group.","year":"2021","unstructured":"Kidney Disease: Improving Global Outcomes (KDIGO) Glomerular Diseases Work Group. KDIGO 2021 clinical practice guideline for the management of glomerular diseases. Kidney Int. 100, S1\u2013s276 (2021).","journal-title":"Kidney Int."},{"key":"860_CR31","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/nrneph.2010.157","volume":"7","author":"V Kon","year":"2011","unstructured":"Kon, V., Linton, M. F. & Fazio, S. Atherosclerosis in chronic kidney disease: the role of macrophages. Nat. Rev. Nephrol. 7, 45\u201354 (2011).","journal-title":"Nat. Rev. Nephrol."},{"key":"860_CR32","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41551-021-00745-6","volume":"5","author":"K Zhang","year":"2021","unstructured":"Zhang, K. 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\u2013545 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"860_CR33","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1046\/j.1523-1755.2003.00712.x","volume":"63","author":"AI Adler","year":"2003","unstructured":"Adler, A. I. et al. Development and progression of nephropathy in type 2 diabetes: the United Kingdom Prospective Diabetes Study (UKPDS 64). Kidney Int 63, 225\u2013232 (2003).","journal-title":"Kidney Int"},{"key":"860_CR34","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1136\/bmj.314.7083.783","volume":"314","author":"MA Gall","year":"1997","unstructured":"Gall, M. A., Hougaard, P., Borch-Johnsen, K. & Parving, H. H. Risk factors for development of incipient and overt diabetic nephropathy in patients with non-insulin dependent diabetes mellitus: prospective, observational study. BMJ 314, 783\u2013788 (1997).","journal-title":"BMJ"},{"key":"860_CR35","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1093\/ndt\/gfr561","volume":"27","author":"N Altemtam","year":"2012","unstructured":"Altemtam, N., Russell, J. & El Nahas, M. A study of the natural history of diabetic kidney disease (DKD). Nephrol. Dial Transplant. 27, 1847\u20131854 (2012).","journal-title":"Nephrol. Dial Transplant."},{"key":"860_CR36","doi-asserted-by":"publisher","first-page":"604","DOI":"10.7326\/0003-4819-150-9-200905050-00006","volume":"150","author":"AS Levey","year":"2009","unstructured":"Levey, A. S. et al. A new equation to estimate glomerular filtration rate. Ann. Intern. Med. 150, 604\u2013612 (2009).","journal-title":"Ann. Intern. Med."},{"key":"860_CR37","unstructured":"Springenberg, J. T., Dosovitskiy, A., Brox, T. & Riedmiller, M. Striving for simplicity: the all convolutional net. Preprint at https:\/\/arxiv.org\/abs\/1412.6806 (2014)."},{"key":"860_CR38","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F. & Wattenberg, M. Smoothgrad: removing noise by adding noise. Preprint at https:\/\/arxiv.org\/abs\/1706.03825 (2017)."},{"key":"860_CR39","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1002\/sim.4085","volume":"30","author":"MJ Pencina","year":"2011","unstructured":"Pencina, M. J., D\u2019Agostino, R. B. Sr. & Steyerberg, E. W. Extensions of net reclassification improvement calculations to measure usefulness of new biomarkers. Stat. Med. 30, 11\u201321 (2011).","journal-title":"Stat. Med."},{"key":"860_CR40","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1002\/sim.2929","volume":"27","author":"MJ Pencina","year":"2008","unstructured":"Pencina, M. J., D\u2019Agostino, R. B. Sr., D\u2019Agostino, R. B. Jr. & Vasan, R. S. Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond. Stat. Med. 27, 157\u2013172 (2008).","journal-title":"Stat. Med."},{"key":"860_CR41","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1056\/NEJMoa1114248","volume":"367","author":"LA Inker","year":"2012","unstructured":"Inker, L. A. et al. Estimating glomerular filtration rate from serum creatinine and cystatin C. N. Engl. J. Med. 367, 20\u201329 (2012).","journal-title":"N. Engl. J. Med."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00860-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00860-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00860-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T14:04:47Z","timestamp":1687010687000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00860-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["860"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00860-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"24 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"T.H.R. was a former scientific adviser and owned stocks in Mediwhale. H.K. and G.L. are employees of Mediwhale, and G.L. owns stocks in Mediwhale. T.H.R. and G.L. hold the following patents that might have been affected by this study: 10\u20132018\u20130166720(KR), 10\u20132018\u20130166721(KR), 10\u20132018\u20130166722(KR), 62\/694,901(US), 62\/715,729(US), and 62\/776,345 (US). All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"114"}}