{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T03:59:27Z","timestamp":1791518367600,"version":"4.3.4"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Wuhan Municipal Health Commission","award":["WY22B07"],"award-info":[{"award-number":["WY22B07"]}]},{"name":"Wuhan Municipal Health Commission","award":["WZ24B11"],"award-info":[{"award-number":["WZ24B11"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diabetes mellitus (DM) is one of the most prevalent non-communicable chronic diseases globally, affecting an estimated 530 million adults in 2021, a number projected to rise to 780 million by 2045.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study aimed to develop and validate a risk prediction model for 1-year chronic kidney disease (CKD) progression in patients with type 2 diabetes mellitus (T2DM) and CKD by employing various machine learning (ML) algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design and methods<\/jats:title>\n                    <jats:p>This study included a total of 12\u00a0151 patients with T2DM and CKD with eGFR between 30 and 59.9\u2009ml\/min\/1.73 m2 from a tertiary hospital in Wuhan, enrolled between 2012 and 2024. The cohort was divided into a training set of 5954 patients, an internal validation set of 2552 patients, and an external validation set of 3645 patients. We developed 1-year CKD progression risk prediction models using 10 different ML algorithms. CKD progression was defined as a decline in eGFR by more than 30% from baseline and\/or a reduction in eGFR to below 15\u2009ml\/min\/1.73 m2. The SHAP (SHapley Additive exPlanations) method was utilized to explain the predictions of a model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 10 ML models, the XGBoost model achieved the best predictive performance for 1-year progression of kidney function with an area under the ROC curve of 0.906 in the internal validation set and 0.768 in the external validation set. The final predictive model incorporating only nine variables has been implemented into a web application to enhance its usability in clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our findings suggest that the XGBoost model may serve as a valuable decision-support tool for predicting kidney function decline in patients with T2DM and CKD.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/qjmed\/hcaf101","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T07:41:52Z","timestamp":1745394112000},"page":"647-656","source":"Crossref","is-referenced-by-count":7,"title":["Explainable machine learning prediction of 1-year kidney function progression among patients with type 2 diabetes mellitus and chronic kidney disease: a retrospective study"],"prefix":"10.1093","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1601-1084","authenticated-orcid":false,"given":"Jinyi","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Public Health, Wuhan Fourth Hospital , Wuhan,","place":["China"]},{"name":"School of Public Health, Fudan University , Shanghai,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Wuhan Fourth Hospital , Wuhan,","place":["China"]},{"name":"Wuhan Clinical Research Center for Metabolic Chronic Kidney Disease, Wuhan Fourth Hospital , Wuhan,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Wuhan Fourth Hospital , Wuhan,","place":["China"]},{"name":"Wuhan Clinical Research Center for Metabolic Chronic Kidney Disease, Wuhan Fourth Hospital , Wuhan,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangping","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Health Information, Wuhan Fourth Hospital , Wuhan,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwu","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Wuhan Fourth Hospital , Wuhan,","place":["China"]},{"name":"Wuhan Clinical Research Center for Metabolic Chronic Kidney Disease, Wuhan Fourth Hospital , Wuhan,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglan","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Wuhan Fourth Hospital , Wuhan,","place":["China"]},{"name":"Wuhan Clinical Research Center for Metabolic Chronic Kidney Disease, Wuhan Fourth Hospital , Wuhan,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"2025120114372520900_hcaf101-B1","doi-asserted-by":"crossref","first-page":"e55","DOI":"10.1016\/S2214-109X(23)00508-9","article-title":"Prevalence of hypertension, diabetes, obesity, multimorbidity, and related risk factors among adult Gambians: a cross-sectional nationwide study","volume":"12","author":"Jobe","year":"2024","journal-title":"Lancet Glob Health"},{"key":"2025120114372520900_hcaf101-B2","doi-asserted-by":"crossref","first-page":"110945","DOI":"10.1016\/j.diabres.2023.110945","article-title":"Erratum to \"IDF diabetes atlas: global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045\". [Diabetes Res. Clin. Pract. 183 (2022) 109119]","volume":"204","author":"Sun","year":"2023","journal-title":"Diabetes Res Clin Pract"},{"key":"2025120114372520900_hcaf101-B3","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1007\/s00125-018-4557-7","article-title":"Epidemiology of diabetes and diabetic complications in China","volume":"61","author":"Ma","year":"2018","journal-title":"Diabetologia"},{"key":"2025120114372520900_hcaf101-B4","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1056\/NEJMcp011773","article-title":"Clinical practice. Nephropathy in patients with type 2 diabetes","volume":"346","author":"Remuzzi","year":"2002","journal-title":"N Engl J Med"},{"key":"2025120114372520900_hcaf101-B5","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1056\/NEJMoa1608664","article-title":"Mortality and cardiovascular disease in type 1 and type 2 diabetes","volume":"376","author":"Rawshani","year":"2017","journal-title":"N Engl J Med"},{"key":"2025120114372520900_hcaf101-B6","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/S0140-6736(12)60572-8","article-title":"Risk of coronary events in people with chronic kidney disease compared with those with diabetes: a population-level cohort study","volume":"380","author":"Tonelli","year":"2012","journal-title":"Lancet"},{"key":"2025120114372520900_hcaf101-B7","doi-asserted-by":"crossref","first-page":"319","DOI":"10.4093\/dmj.2018.0060","article-title":"Diabetes mellitus and cause-specific mortality: a population-based study","volume":"43","author":"Li","year":"2019","journal-title":"Diabetes Metab J"},{"key":"2025120114372520900_hcaf101-B8","first-page":"2075","article-title":"Risk and treatment effect heterogeneity: re-analysis of individual participant data from 32 large clinical trials","volume":"45","author":"Kent","year":"2016","journal-title":"Int J Epidemiol"},{"key":"2025120114372520900_hcaf101-B9","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1001\/jama.2011.451","article-title":"A predictive model for progression of chronic kidney disease to kidney failure","volume":"305","author":"Tangri","year":"2011","journal-title":"Jama"},{"key":"2025120114372520900_hcaf101-B10","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1001\/jama.2015.18202","article-title":"Multinational assessment of accuracy of equations for predicting risk of kidney failure: a meta-analysis","volume":"315","author":"Tangri","year":"2016","journal-title":"Jama"},{"key":"2025120114372520900_hcaf101-B11","doi-asserted-by":"crossref","first-page":"1237804","DOI":"10.3389\/fneph.2023.1237804","article-title":"Development and deployment of a nationwide predictive model for chronic kidney disease progression in diabetic patients","volume":"3","author":"Fu","year":"2023","journal-title":"Front Nephrol"},{"key":"2025120114372520900_hcaf101-B12","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1093\/ckj\/sfac252","article-title":"Comparison of a chronic kidney disease predictive model for type 2 diabetes mellitus in Malaysia using cox regression versus machine learning approach","volume":"16","author":"Sim","year":"2023","journal-title":"Clin Kidney J"},{"key":"2025120114372520900_hcaf101-B13","doi-asserted-by":"crossref","first-page":"3371","DOI":"10.1111\/dom.15678","article-title":"Machine learning for prediction of chronic kidney disease progression: validation of the klinrisk model in the CANVAS program and CREDENCE trial","volume":"26","author":"Tangri","year":"2024","journal-title":"Diabetes Obes Metab"},{"key":"2025120114372520900_hcaf101-B14","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1016\/j.ekir.2022.05.004","article-title":"Development and external validation of a machine learning model for progression of CKD","volume":"7","author":"Ferguson","year":"2022","journal-title":"Kidney Int Rep"},{"key":"2025120114372520900_hcaf101-B15","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1007\/s00125-021-05444-0","article-title":"Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease","volume":"64","author":"Chan","year":"2021","journal-title":"Diabetologia"},{"key":"2025120114372520900_hcaf101-B16","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1186\/s12967-022-03339-1","article-title":"Prediction of 3-year risk of diabetic kidney disease using machine learning based on electronic medical records","volume":"20","author":"Dong","year":"2022","journal-title":"J Transl Med"},{"key":"2025120114372520900_hcaf101-B17","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2025120114372520900_hcaf101-B18","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1056\/NEJMp1606181","article-title":"Predicting the future\u2014big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer","year":"2016","journal-title":"N Engl J Med"},{"key":"2025120114372520900_hcaf101-B19","doi-asserted-by":"crossref","first-page":"120126","DOI":"10.1016\/j.techfore.2020.120126","article-title":"A novel hybrid approach to forecast crude oil futures using intraday data","volume":"158","author":"Manickavasagam","year":"2020","journal-title":"Technol Forecast Soc Change"},{"key":"2025120114372520900_hcaf101-B20","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.2337\/dc19-0587","article-title":"Machine learning to predict the risk of incident heart failure hospitalization among patients with diabetes: the WATCH-DM risk score","volume":"42","author":"Segar","year":"2019","journal-title":"Diabetes Care"},{"key":"2025120114372520900_hcaf101-B21","doi-asserted-by":"crossref","first-page":"102409","DOI":"10.1016\/j.eclinm.2023.102409","article-title":"Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study","volume":"68","author":"Hu","year":"2024","journal-title":"EClinicalMedicine"},{"key":"2025120114372520900_hcaf101-B22","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s13099-022-00479-z","article-title":"Obesity is not associated with adverse outcomes among hospitalized patients with Clostridioides difficile infection","volume":"14","author":"Malick","year":"2022","journal-title":"Gut Pathog"},{"key":"2025120114372520900_hcaf101-B23","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1007\/s00109-019-01823-8","article-title":"Novel plasma peptide markers involved in the pathology of CKD identified using mass spectrometric approach","volume":"97","author":"Gajjala","year":"2019","journal-title":"J Mol Med (Berl)"},{"key":"2025120114372520900_hcaf101-B24","doi-asserted-by":"crossref","first-page":"604","DOI":"10.7326\/0003-4819-150-9-200905050-00006","article-title":"A new equation to estimate glomerular filtration rate","volume":"150","author":"Levey","year":"2009","journal-title":"Ann Intern Med"},{"key":"2025120114372520900_hcaf101-B25","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1681\/ASN.2014070696","article-title":"Urine collagen fragments and CKD Progression-the cardiovascular health study","volume":"26","author":"Ix","year":"2015","journal-title":"J Am Soc Nephrol"},{"key":"2025120114372520900_hcaf101-B26","doi-asserted-by":"crossref","first-page":"5600","DOI":"10.1093\/bioinformatics\/btaa1074","article-title":"Identification of sub-golgi protein localization by use of deep representation learning features","volume":"36","author":"Lv","year":"2021","journal-title":"Bioinformatics"},{"key":"2025120114372520900_hcaf101-B27","doi-asserted-by":"crossref","first-page":"3625","DOI":"10.7150\/jca.96052","article-title":"Possible non-linear relation between prostate specific antigen and vitamin D: a machine learning study based on cross-section data","volume":"15","author":"Shi","year":"2024","journal-title":"J Cancer"},{"key":"2025120114372520900_hcaf101-B28","doi-asserted-by":"crossref","first-page":"963138","DOI":"10.3389\/fpubh.2022.963138","article-title":"Association between urinary metals and leukocyte telomere length involving an artificial neural network prediction: findings based on NHANES 1999-2002","volume":"10","author":"Xia","year":"2022","journal-title":"Front Public Health"},{"key":"2025120114372520900_hcaf101-B29","doi-asserted-by":"crossref","first-page":"e2212930","DOI":"10.1001\/jamanetworkopen.2022.12930","article-title":"Development and validation of an explainable machine learning model for major complications after cytoreductive surgery","volume":"5","author":"Deng","year":"2022","journal-title":"JAMA Netw Open"},{"key":"2025120114372520900_hcaf101-B30","doi-asserted-by":"crossref","first-page":"e717","DOI":"10.1016\/S2589-7500(22)00149-2","article-title":"A machine-learning algorithm for diagnosis of multisystem inflammatory syndrome in children and Kawasaki disease in the USA: a retrospective model development and validation study","volume":"4","author":"Lam","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2025120114372520900_hcaf101-B31","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1093\/bioinformatics\/btz646","article-title":"StrainHub: a phylogenetic tool to construct pathogen transmission networks","volume":"36","author":"de Bernardi Schneider","year":"2020","journal-title":"Bioinformatics"},{"key":"2025120114372520900_hcaf101-B32","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.ebiom.2018.09.039","article-title":"Exhaustive non-synonymous variants functionality prediction enables high resolution characterization of the neurofibromin architecture","volume":"36","author":"Isakov","year":"2018","journal-title":"EBioMedicine"},{"key":"2025120114372520900_hcaf101-B33","doi-asserted-by":"crossref","first-page":"103911","DOI":"10.1016\/j.ebiom.2022.103911","article-title":"A comparison of machine learning methods for predicting recurrence and death after curative-intent radiotherapy for non-small cell lung cancer: development and validation of multivariable clinical prediction models","volume":"77","author":"Hindocha","year":"2022","journal-title":"EBioMedicine"},{"key":"2025120114372520900_hcaf101-B34","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1007\/s13300-020-00888-w","article-title":"Insights into the role of renal biopsy in patients with T2DM: a literature review of global renal biopsy results","volume":"11","author":"Tong","year":"2020","journal-title":"Diabetes Ther"}],"container-title":["QJM: An International Journal of Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/qjmed\/advance-article-pdf\/doi\/10.1093\/qjmed\/hcaf101\/63000732\/hcaf101.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/qjmed\/article-pdf\/118\/9\/647\/63000732\/hcaf101.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/qjmed\/article-pdf\/118\/9\/647\/63000732\/hcaf101.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T19:37:39Z","timestamp":1764617859000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/qjmed\/article\/118\/9\/647\/8119255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":34,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,4,24]]},"published-print":{"date-parts":[[2025,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/qjmed\/hcaf101","relation":{},"ISSN":["1460-2725","1460-2393"],"issn-type":[{"value":"1460-2725","type":"print"},{"value":"1460-2393","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,4,24]]}}}