{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T15:05:09Z","timestamp":1779807909577,"version":"3.53.1"},"reference-count":42,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"40","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,3]]},"abstract":"<jats:p>\n                    The global prevalence of type 2 diabetes mellitus (T2D) has been increasing dramatically as well as diabetic kidney disease (DKD). We aimed to compare the accuracies of 4 machine learning (Mach-L) methods with multiple linear regression (MLR) in predicting future estimated glomerular filtration rate (eGFR) in T2D patients and to rank the importance of DKD risk factors. The study was conducted from 2013 to 2019. Nine hundred and seven T2D patients were followed up for 4 years. Data of potential DKD risk factors were collected and calculated. We used 4 different Mach-L methods to predict the eGFR, including classification and regression tree, random forest, artificial neural network, and eXtreme Gradient Boosting. Simple correlation was applied to overview the relationships between baseline risk factors and eGFR at the end of follow-up (eGFR\n                    <jats:sub>end<\/jats:sub>\n                    ). Besides, traditional MLR was used as a benchmark to evaluate if Mach-L methods could outperform MLR. For model interpretability, Shapley additive explanation was applied to explain the contribution of each feature and directions of impacts in the prediction model. In 4 different Mach-L methods, random forest, classification and regression tree, and eXtreme Gradient Boosting were more superior than MLR in the prediction of the eGFR\n                    <jats:sub>end<\/jats:sub>\n                    . The first 6 important risk factors in predicting diabetic eGFR\n                    <jats:sub>end<\/jats:sub>\n                    were body mass index (BMI), baseline high-density lipoprotein cholesterol (HDL-C), baseline urine microalbumin creatinine ratio (MCR), baseline low-density lipoprotein cholesterol (LDL-C), duration of diabetes, and age. By applying Shapley additive explanation, it appeared that age, duration of diabetes, HDL, and LDL were positively related to eGFR\n                    <jats:sub>end<\/jats:sub>\n                    and BMI and MCR were negatively related to eGFR\n                    <jats:sub>end<\/jats:sub>\n                    . Mach-L methods were proved to be more accurate in predicting eGFR\n                    <jats:sub>end<\/jats:sub>\n                    than traditional MLR. BMI presented the most influential factor for eGFR\n                    <jats:sub>end<\/jats:sub>\n                    , followed by HDL-C, baseline urine MCR, LDL-C, duration of diabetes, and age. These findings highlight the potential of Mach-L to enhance early risk stratification for DKD, enabling timely interventions to preserve renal function in T2D patients.\n                  <\/jats:p>","DOI":"10.1097\/md.0000000000044732","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T20:05:36Z","timestamp":1759781136000},"page":"e44732","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Using machine learning to predict estimated glomerular filtration rate in type 2 diabetes patients: A 4 year-follow-up study"],"prefix":"10.1097","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5590-2744","authenticated-orcid":false,"given":"Fang-Yu","family":"Chen","sequence":"first","affiliation":[{"name":"Division of Endocrinology and Metabolism, Department of Internal Medicine, Fu Jen Catholic University Hospital, School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei, Taiwan, ROC"},{"name":"Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei City, Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dee","family":"Pei","sequence":"additional","affiliation":[{"name":"Division of Endocrinology and Metabolism, Department of Internal Medicine, Fu Jen Catholic University Hospital, School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei, Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Heng","family":"Kuo","sequence":"additional","affiliation":[{"name":"Division of Endocrinology and Metabolism, Department of Internal Medicine, Fu Jen Catholic University Hospital, School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei, Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Ying","family":"Huang","sequence":"additional","affiliation":[{"name":"Division of Endocrinology and Metabolism, Department of Internal Medicine, Fu Jen Catholic University Hospital, School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei, Taiwan, ROC"},{"name":"Department of Medical Education, Fu Jen Catholic University Hospital, School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei, Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mao-Jhen","family":"Jhou","sequence":"additional","affiliation":[{"name":"Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, Taiwan, ROC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5036-9592","authenticated-orcid":false,"given":"Yao-Jen","family":"Liang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University, New Taipei City, Taiwan, ROC"},{"name":"Department and Institute of Life-Science, Fu Jen Catholic University, New Taipei, Taiwan, ROC."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"issue":"Suppl 2","key":"R2-20260526","doi-asserted-by":"crossref","first-page":"S66","DOI":"10.1016\/j.jfma.2019.06.016","article-title":"Trends in prevalence and incidence of diabetes mellitus from 2005 to 2014 in Taiwan.","volume":"118","author":"Sheen","year":"2019","journal-title":"J Formos Med Assoc"},{"key":"R4-20260526","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.2215\/CJN.11491116","article-title":"Diabetic kidney disease: challenges, progress, and possibilities.","volume":"12","author":"Alicic","year":"2017","journal-title":"Clin J Am Soc Nephrol"},{"key":"R6-20260526","doi-asserted-by":"crossref","first-page":"S47","DOI":"10.1016\/S0168-8227(01)00309-6","article-title":"The impact of diabetes on economic costs in dialysis patients: experiences in Taiwan.","volume":"54","author":"Yang","year":"2001","journal-title":"Diabetes Res Clin Pract"},{"key":"R7-20260526","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1053\/j.ackd.2014.03.009","article-title":"Epidemiology and risk factors for diabetic kidney disease.","volume":"21","author":"Harjutsalo","year":"2014","journal-title":"Adv Chronic Kidney Dis"},{"key":"R8-20260526","doi-asserted-by":"crossref","first-page":"15018","DOI":"10.1038\/nrdp.2015.18","article-title":"Diabetic kidney disease.","volume":"1","author":"Thomas","year":"2015","journal-title":"Nat Rev Dis Primers"},{"key":"R9-20260526","first-page":"49","article-title":"Diabetic kidney disease: world wide difference of prevalence and risk factors.","volume":"5","author":"Gheith","year":"2015","journal-title":"J Nephropharmacol"},{"key":"R11-20260526","doi-asserted-by":"crossref","first-page":"4168340","DOI":"10.1155\/2020\/4168340","article-title":"Comparison of machine learning methods and conventional logistic regressions for predicting gestational diabetes using routine clinical data: a retrospective cohort study.","volume":"2020","author":"Ye","year":"2020","journal-title":"J Diabetes Res"},{"key":"R12-20260526","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.compbiomed.2013.11.006","article-title":"A hybrid intelligent system for diagnosing microalbuminuria in type 2 diabetes patients without having to measure urinary albumin.","volume":"45","author":"Marateb","year":"2014","journal-title":"Comput Biol Med"},{"key":"R13-20260526","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.jclinepi.2020.03.002","article-title":"Logistic regression was as good as machine learning for predicting major chronic diseases.","volume":"122","author":"Nusinovici","year":"2020","journal-title":"J Clin Epidemiol"},{"key":"R14-20260526","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.3390\/diagnostics13111834","article-title":"Using machine learning to predict abnormal carotid intima-media thickness in type 2 diabetes.","volume":"13","author":"Wu","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"R16-20260526","doi-asserted-by":"crossref","first-page":"e007450","DOI":"10.1136\/bmjopen-2014-007450","article-title":"Using decision trees to understand structure in missing data.","volume":"5","author":"Tierney","year":"2015","journal-title":"BMJ Open"},{"key":"R17-20260526","first-page":"20","article-title":"Study of various decision tree pruning methods with their empirical comparison in WEKA.","volume":"60","author":"Patel","year":"2012","journal-title":"Int J Comput Appl"},{"key":"R18-20260526","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests.","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"R19-20260526","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1093\/bib\/bbq011","article-title":"Letter to the editor: Stability of Random Forest importance measures.","volume":"12","author":"Calle","year":"2011","journal-title":"Brief Bioinform"},{"key":"R22-20260526","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s40708-017-0065-7","article-title":"Machine learning-XGBoost analysis of language networks to classify patients with epilepsy.","volume":"4","author":"Torlay","year":"2017","journal-title":"Brain Inform"},{"key":"R28-20260526","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1001\/jama.291.7.844","article-title":"Predictors of new-onset kidney disease in a community-based population.","volume":"291","author":"Fox","year":"2004","journal-title":"JAMA"},{"key":"R29-20260526","doi-asserted-by":"crossref","first-page":"2019","DOI":"10.2337\/dc06-2554","article-title":"Prevalence and risk factors of diabetic nephropathy in an urban South Indian population: the Chennai Urban Rural Epidemiology Study (CURES 45).","volume":"30","author":"Unnikrishnan","year":"2007","journal-title":"Diabetes Care"},{"key":"R30-20260526","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1080\/0886022X.2021.1969247","article-title":"Obesity-related indices are associated with albuminuria and advanced kidney disease in type 2 diabetes mellitus.","volume":"43","author":"Ou","year":"2021","journal-title":"Ren Fail"},{"key":"R31-20260526","doi-asserted-by":"crossref","first-page":"2054358117698669","DOI":"10.1177\/2054358117698669","article-title":"Obesity and kidney disease: hidden consequences of the epidemic.","volume":"4","author":"Kovesdy","year":"2017","journal-title":"Can J Kidney Health Dis"},{"key":"R32-20260526","first-page":"150","article-title":"Dyslipidemia in type 2 diabetes mellitus.","volume":"5","author":"Mooradian","year":"2009","journal-title":"Nat Clin Pract Endocrinol Metab"},{"key":"R33-20260526","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.2337\/dc12-0306","article-title":"Low HDL cholesterol and the risk of diabetic nephropathy and retinopathy: results of the ADVANCE study.","volume":"35","author":"Jamie Morton","year":"2012","journal-title":"Diabetes Care"},{"key":"R34-20260526","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.2337\/dc16-1246","article-title":"Plasma triglycerides and HDL-C levels predict the development of diabetic kidney disease in subjects with type 2 diabetes: the AMD annals initiative.","volume":"39","author":"Russo","year":"2016","journal-title":"Diabetes Care"},{"issue":"Suppl 1","key":"R35-20260526","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/dom.14007","article-title":"An updated overview of diabetic nephropathy: diagnosis, prognosis, treatment goals and latest guidelines.","volume":"22","author":"Selby","year":"2020","journal-title":"Diabetes Obes Metab"},{"key":"R36-20260526","doi-asserted-by":"crossref","first-page":"e0122030","DOI":"10.1371\/journal.pone.0122030","article-title":"Five-year incidence of chronic kidney disease (stage 3\u20135) and associated risk factors in a Spanish cohort: the MADIABETES Study.","volume":"10","author":"Salinero-Fort","year":"2015","journal-title":"PLoS One"},{"key":"R37-20260526","doi-asserted-by":"crossref","first-page":"7079","DOI":"10.1038\/s41598-023-32305-0","article-title":"Prognostic significance of albuminuria in elderly of various ages with diabetes.","volume":"13","author":"Hwang","year":"2023","journal-title":"Sci Rep"},{"issue":"Suppl 1","key":"R38-20260526","doi-asserted-by":"crossref","first-page":"S191","DOI":"10.2337\/dc23-S011","article-title":"11. Chronic kidney disease and risk management: standards of care in diabetes-2023.","volume":"46","author":"ElSayed","year":"2023","journal-title":"Diabetes Care"},{"key":"R39-20260526","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1007\/s00125-008-0961-8","article-title":"What is the mechanism of microalbuminuria in diabetes: a role for the glomerular endothelium?","volume":"51","author":"Satchell","year":"2008","journal-title":"Diabetologia"},{"key":"R40-20260526","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1900\/RDS.2013.10.88","article-title":"Dyslipidemia, kidney disease, and cardiovascular disease in diabetic patients.","volume":"10","author":"Chen","year":"2013","journal-title":"Rev Diabet Stud"},{"key":"R41-20260526","doi-asserted-by":"crossref","first-page":"1124367","DOI":"10.3389\/fendo.2023.1124367","article-title":"Dyslipidemia and serum cystatin C levels as biomarker of diabetic nephropathy in patients with type 2 diabetes mellitus.","volume":"14","author":"Dejenie","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"R42-20260526","doi-asserted-by":"crossref","first-page":"E729","DOI":"10.1503\/cmaj.230093","article-title":"Statin initiation and risk of incident kidney disease in patients with diabetes.","volume":"195","author":"Zhou","year":"2023","journal-title":"CMAJ"},{"key":"R43-20260526","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s41100-016-0028-0","article-title":"Dyslipidemia in diabetic nephropathy.","volume":"2","author":"Kawanami","year":"2016","journal-title":"Renal Replacement Ther"},{"key":"R44-20260526","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1111\/1744-9987.13480","article-title":"Rate of kidney function decline and factors predicting progression of kidney disease in type 2 diabetes mellitus patients with reduced kidney function: a nationwide retrospective cohort study.","volume":"24","author":"Kaewput","year":"2020","journal-title":"Ther Apher Dial"},{"key":"R45-20260526","doi-asserted-by":"crossref","first-page":"14705","DOI":"10.1038\/s41598-021-94099-3","article-title":"Rate of decline in kidney function and known age-of-onset or duration of type 2 diabetes.","volume":"11","author":"Buyadaa","year":"2021","journal-title":"Sci Rep"},{"key":"R46-20260526","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.1007\/s00125-021-05494-4","article-title":"Young age at diabetes diagnosis amplifies the effect of diabetes duration on risk of chronic kidney disease: a prospective cohort study.","volume":"64","author":"Wu","year":"2021","journal-title":"Diabetologia"},{"key":"R47-20260526","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1007\/s10157-021-02107-7","article-title":"The distribution of eGFR by age in a community-based healthy population: the Japan Specific Health Checkups Study (J-SHC Study).","volume":"25","author":"Araumi","year":"2021","journal-title":"Clin Exp Nephrol"},{"key":"R48-20260526","doi-asserted-by":"crossref","first-page":"401","DOI":"10.2215\/CJN.07650711","article-title":"Predictors of estimated GFR decline in patients with type 2 diabetes and preserved kidney function.","volume":"7","author":"Zoppini","year":"2012","journal-title":"Clin J Am Soc Nephrol"},{"key":"R49-20260526","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1111\/j.1523-1755.2004.00925.x","article-title":"Progression of nephropathy in type 2 diabetic patients.","volume":"66","author":"Rossing","year":"2004","journal-title":"Kidney Int"},{"key":"R50-20260526","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1002\/dmrr.2574","article-title":"The risk for diabetic nephropathy is low in young adults in a 17-year follow-up from the Diabetes Incidence Study in Sweden (DISS). Older age and higher BMI at diabetes onset can be important risk factors.","volume":"31","author":"Svensson","year":"2015","journal-title":"Diabetes Metab Res Rev"},{"key":"R51-20260526","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.2337\/dc20-0352","article-title":"The association between age of onset of type 2 diabetes and the long-term risk of end-stage kidney disease: a national registry study.","volume":"43","author":"Morton","year":"2020","journal-title":"Diabetes Care"},{"key":"R52-20260526","first-page":"BC05","article-title":"Association of diabetic nephropathy and liver disorders.","volume":"10","author":"Adiga","year":"2016","journal-title":"J Clin Diagn Res"},{"key":"R53-20260526","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1007\/s13340-020-00483-1","article-title":"Retrospective study of factors associated with progression and remission\/regression of diabetic kidney disease-hypomagnesemia was associated with progression and elevated serum alanine aminotransferase levels were associated with remission or regression.","volume":"12","author":"Yanagawa","year":"2021","journal-title":"Diabetol Int"},{"key":"R54-20260526","doi-asserted-by":"crossref","first-page":"31","DOI":"10.4103\/2229-516X.149232","article-title":"A comparative study of serum aminotransferases in chronic kidney disease with and without end-stage renal disease: need for new reference ranges.","volume":"5","author":"Ray","year":"2015","journal-title":"Int J Appl Basic Med Res"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T14:29:30Z","timestamp":1779805770000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000044732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":42,"journal-issue":{"issue":"40","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000044732","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"2025-07-01","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-02","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}