Development and Validation of Time-Dependent Risk Prediction Models for the Incidence and Progression of Chronic Kidney Disease in Individuals with Type 2 Diabetes Mellitus

Development and Validation of Time-Dependent Risk Prediction Models for the Incidence and Progression of Chronic Kidney Disease in Individuals with Type 2 Diabetes Mellitus | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Development and Validation of Time-Dependent Risk Prediction Models for the Incidence and Progression of Chronic Kidney Disease in Individuals with Type 2 Diabetes Mellitus Yubo Zhao, Shuya Lu, Jiqiao Lu, Lin Yang, Cheuk Wai Lo, Man Kin Wong, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6591201/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Feb, 2026 Read the published version in npj Digital Medicine → Version 1 posted 10 You are reading this latest preprint version Abstract Background Chronic kidney disease (CKD) is a common and severe complication of type 2 diabetes mellitus (T2DM), contributing substantially to global disease burden. However, current prognostic models for CKD progression in Asian populations remain underdeveloped. Methods We developed and validated time-dependent CKD progression models using 17-year electronic health records (EHR) from Hong Kong. Multiple machine learning (ML) and deep learning (DL) models were compared to identify the best-performing model based on area under the receiver operating characteristic curve (AUC). Survival analyses based on the Weibull Accelerated Failure Time (AFT) model were applied to estimate progression risk across different predicted risk strata. Findings The final model included 158,205 individuals from 2003 to 2019. Deep neural network (DNN) models consistently outperformed other ML models, achieving AUCs of 87.1%, 85.3%, and 84.7% for 2-, 5-, and 10-year predictions, respectively. Key predictors included serum creatinine, sex, eye complications, systolic blood pressure, age, and two-year prescription history of angiotensin. The probability of survival during the follow-up period declined more rapidly in high-risk individuals predicted by the best model. External validation in the UK Biobank (n = 17,351) the China Health and Retirement Longitudinal Study (n = 4,174) cohorts yielded AUCs of 79.7% and 74.6%, respectively. Conclusion Deep learning-based prognostic models for CKD progression in individuals with T2DM show satisfactory performance in both internal and external cohorts of Asian populations as well as in the western populations. This model could serve as a powerful tool for CKD prevention and patient management, thereby enhancing risk management, supporting early intervention and clinical decision-making. Health sciences/Endocrinology/Endocrine system and metabolic diseases Health sciences/Biomarkers/Prognostic markers Health sciences/Health care/Prognosis Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryInformation.pdf Cite Share Download PDF Status: Published Journal Publication published 16 Feb, 2026 Read the published version in npj Digital Medicine → Version 1 posted Editorial decision: Revision requested 06 Jul, 2025 Reviews received at journal 07 Jun, 2025 Reviewers agreed at journal 29 May, 2025 Reviewers agreed at journal 28 May, 2025 Reviews received at journal 28 May, 2025 Reviewers agreed at journal 16 May, 2025 Reviewers invited by journal 15 May, 2025 Editor assigned by journal 14 May, 2025 Submission checks completed at journal 14 May, 2025 First submitted to journal 05 May, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6591201","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":457653502,"identity":"dfa4619c-bcd6-44cb-94bb-00b90bfbfb88","order_by":0,"name":"Yubo Zhao","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Yubo","middleName":"","lastName":"Zhao","suffix":""},{"id":457653503,"identity":"aace4cde-f3cc-41ea-ad7c-2a1b126a25af","order_by":1,"name":"Shuya Lu","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Shuya","middleName":"","lastName":"Lu","suffix":""},{"id":457653504,"identity":"2f764697-c36b-4018-96b4-2cbbbc9e85ef","order_by":2,"name":"Jiqiao Lu","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Jiqiao","middleName":"","lastName":"Lu","suffix":""},{"id":457653505,"identity":"344f1911-f238-4598-8d1e-65254576d71d","order_by":3,"name":"Lin Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYBACPghlw8DADmYwMzBIsOHXApVOAysmScthkrTwGH4u+HU+j5+Zx0yCocI6sUG6LYGQFmPpmX23iyWbQVrOpCc2yBw7QEiLgTRvz+3EDYeBWhjbDic2SKQ3ELTlN2/POaiWf8RpMZPm+XEAqqUBpCWNgMOY2cqseRuSgX5hK7ZIOJZu3CaRloBXCz978+bbPH/s8oCMjTc+1FjL9kukGeDVwsDMYcDA2MYANBjISGCAxxQ+wP6AgeEPSDGIMQpGwSgYBaMACwAApxg8I13paucAAAAASUVORK5CYII=","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Lin","middleName":"","lastName":"Yang","suffix":""},{"id":457653506,"identity":"b71e4b45-cfca-4858-b6cb-bf69d7c75bf7","order_by":4,"name":"Cheuk Wai Lo","email":"","orcid":"","institution":"Hospital Authority","correspondingAuthor":false,"prefix":"","firstName":"Cheuk","middleName":"Wai","lastName":"Lo","suffix":""},{"id":457653507,"identity":"37da0b6f-9515-4d1c-8860-b96b456094e2","order_by":5,"name":"Man Kin Wong","email":"","orcid":"","institution":"Hospital Authority","correspondingAuthor":false,"prefix":"","firstName":"Man","middleName":"Kin","lastName":"Wong","suffix":""},{"id":457653508,"identity":"36d10d4c-7ef0-40fb-bc9b-d9b6f5d79cf4","order_by":6,"name":"Ting Li","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Ting","middleName":"","lastName":"Li","suffix":""},{"id":457653509,"identity":"1cffeb6c-aa85-4612-9914-7c56dde3ddb5","order_by":7,"name":"Ren Hui","email":"","orcid":"","institution":"Massachusetts General Hospital, Harvard Medical School","correspondingAuthor":false,"prefix":"","firstName":"Ren","middleName":"","lastName":"Hui","suffix":""},{"id":457653510,"identity":"7c21bee9-1ae6-4b35-bb8d-24e12982b91f","order_by":8,"name":"Xiang Li","email":"","orcid":"","institution":"Massachusetts General Hospital, Harvard Medical School","correspondingAuthor":false,"prefix":"","firstName":"Xiang","middleName":"","lastName":"Li","suffix":""},{"id":457653511,"identity":"1b2c6387-1ce8-4ec7-9cb2-28f9fcc8c50a","order_by":9,"name":"Lin Xu","email":"","orcid":"","institution":"Sun Yat-Sen University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Xu","suffix":""},{"id":457653512,"identity":"c7435746-5114-4bea-b12e-75a3a5eee0de","order_by":10,"name":"Jun Liang","email":"","orcid":"","institution":"Hospital Authority","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Liang","suffix":""},{"id":457653513,"identity":"9aa432c4-3809-4a76-8405-f3cacec52d6e","order_by":11,"name":"Daihai He","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Daihai","middleName":"","lastName":"He","suffix":""},{"id":457653514,"identity":"b3a68db1-a6a5-4847-8614-ee12ae12f3cc","order_by":12,"name":"David H.K. Shum","email":"","orcid":"","institution":"Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"H.K.","lastName":"Shum","suffix":""}],"badges":[],"createdAt":"2025-05-05 04:53:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6591201/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6591201/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41746-026-02439-2","type":"published","date":"2026-02-16T15:59:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":103251374,"identity":"8db8c492-0fe8-4fc0-bcc3-4f513ce87399","added_by":"auto","created_at":"2026-02-23 16:08:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1258711,"visible":true,"origin":"","legend":"","description":"","filename":"CKDmanuscript429.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6591201/v1_covered_6a41e42f-e930-47d8-9fd2-ad9d7105c51d.pdf"},{"id":83058606,"identity":"3b76c202-a959-4f92-8eee-e736df129e24","added_by":"auto","created_at":"2025-05-19 14:12:02","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":693819,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6591201/v1/02560ecfb561c218bddf60a5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and Validation of Time-Dependent Risk Prediction Models for the Incidence and Progression of Chronic Kidney Disease in Individuals with Type 2 Diabetes Mellitus","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6591201/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6591201/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eChronic kidney disease (CKD) is a common and severe complication of type 2 diabetes mellitus (T2DM), contributing substantially to global disease burden. However, current prognostic models for CKD progression in Asian populations remain underdeveloped.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe developed and validated time-dependent CKD progression models using 17-year electronic health records (EHR) from Hong Kong. Multiple machine learning (ML) and deep learning (DL) models were compared to identify the best-performing model based on area under the receiver operating characteristic curve (AUC). Survival analyses based on the Weibull Accelerated Failure Time (AFT) model were applied to estimate progression risk across different predicted risk strata.\u003c/p\u003e\u003ch2\u003eFindings\u003c/h2\u003e \u003cp\u003eThe final model included 158,205 individuals from 2003 to 2019. Deep neural network (DNN) models consistently outperformed other ML models, achieving AUCs of 87.1%, 85.3%, and 84.7% for 2-, 5-, and 10-year predictions, respectively. Key predictors included serum creatinine, sex, eye complications, systolic blood pressure, age, and two-year prescription history of angiotensin. The probability of survival during the follow-up period declined more rapidly in high-risk individuals predicted by the best model. External validation in the UK Biobank (n\u0026thinsp;=\u0026thinsp;17,351) the China Health and Retirement Longitudinal Study (n\u0026thinsp;=\u0026thinsp;4,174) cohorts yielded AUCs of 79.7% and 74.6%, respectively.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eDeep learning-based prognostic models for CKD progression in individuals with T2DM show satisfactory performance in both internal and external cohorts of Asian populations as well as in the western populations. This model could serve as a powerful tool for CKD prevention and patient management, thereby enhancing risk management, supporting early intervention and clinical decision-making.\u003c/p\u003e","manuscriptTitle":"Development and Validation of Time-Dependent Risk Prediction Models for the Incidence and Progression of Chronic Kidney Disease in Individuals with Type 2 Diabetes Mellitus","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-19 14:11:58","doi":"10.21203/rs.3.rs-6591201/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-06T23:57:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-07T23:00:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162221467558936635535211276623995513394","date":"2025-05-29T07:54:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"266559564963517329747063844257526850756","date":"2025-05-28T16:10:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-28T13:47:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"128927783039756729951254075423996618554","date":"2025-05-16T13:25:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-15T13:14:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-14T20:08:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-14T04:30:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2025-05-05T04:43:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0500d588-6162-4333-8ed9-dfd835380bf2","owner":[],"postedDate":"May 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48638766,"name":"Health sciences/Endocrinology/Endocrine system and metabolic diseases"},{"id":48638767,"name":"Health sciences/Biomarkers/Prognostic markers"},{"id":48638768,"name":"Health sciences/Health care/Prognosis"}],"tags":[],"updatedAt":"2026-02-23T16:04:10+00:00","versionOfRecord":{"articleIdentity":"rs-6591201","link":"https://doi.org/10.1038/s41746-026-02439-2","journal":{"identity":"npj-digital-medicine","isVorOnly":false,"title":"npj Digital Medicine"},"publishedOn":"2026-02-16 15:59:23","publishedOnDateReadable":"February 16th, 2026"},"versionCreatedAt":"2025-05-19 14:11:58","video":"","vorDoi":"10.1038/s41746-026-02439-2","vorDoiUrl":"https://doi.org/10.1038/s41746-026-02439-2","workflowStages":[]},"version":"v1","identity":"rs-6591201","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6591201","identity":"rs-6591201","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}