{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:35:51Z","timestamp":1792427751945,"version":"4.5.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Clinicians need practical tools to identify chronic kidney disease (CKD) patients at highest short-term risk of dialysis using only routine clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 400 adults with CKD stages 3\u20134 treated at The Central Hospital of Wuhan (2022\u20132024). Incident hemodialysis during follow-up was the outcome. From 64 candidate variables, LASSO logistic regression embedded within 10-fold cross-validation selected predictors spanning renal, hematologic, and metabolic domains. Ten machine learning models were trained and evaluated using nested cross-validation; temporal validation was performed on a 2024 hold-out set. Performance was summarized as mean \u00b1 SD with 95% confidence intervals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>After correcting for data leakage, the Random Forest model demonstrated excellent discrimination with an AUC of 0.988 (95% CI: 0.974\u20131.003), accuracy of 0.965 (95% CI: 0.941\u20130.989), and recall of 0.970 (95% CI: 0.926\u20131.015). XGBoost and ANN showed comparable AUCs (0.987 and 0.985, respectively). Temporal validation yielded perfect discrimination (AUC\u202f=\u202f1.000, recall\u202f=\u202f1.000). Subgroup analysis showed consistent performance across sex, age, and diabetes strata. SHAP analysis identified creatinine, urine microalbumin, and eGFR as key predictors, with evidence of interaction between proteinuria and erythropoietic dysfunction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A model based on widely available clinical tests accurately predicts 12-month dialysis risk in stage 3\u20134 CKD patients. Its high performance and interpretability support potential use for early risk stratification in real-world nephrology practice, without requiring novel biomarkers or longitudinal monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1782951","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:26:16Z","timestamp":1775107576000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Development and internal validation of an interpretable machine learning model for predicting dialysis risk in patients with stage 3\u20134 chronic kidney disease"],"prefix":"10.3389","volume":"14","author":[{"given":"Peng","family":"Shu","sequence":"first","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Qin","sequence":"additional","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Xu","sequence":"additional","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Guo","sequence":"additional","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuping","family":"Wen","sequence":"additional","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Wang","sequence":"additional","affiliation":[{"name":"The Central Hospital of Wuhan, Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"S0140","DOI":"10.1016\/S0140-6736(25)01942-7","article-title":"Chronic kidney disease","volume":"7","author":"Herrington","year":"2025","journal-title":"Lancet"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"S117","DOI":"10.1016\/j.kint.2023.10.018","article-title":"KDIGO 2024 clinical practice guideline for the evaluation and management of chronic kidney disease","volume":"105","author":"Stevens","year":"2024","journal-title":"Kidney Int"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1016\/S0140-6736(20)30045-3","article-title":"Global, regional, and national burden of chronic kidney disease, 1990\u20132017: a systematic analysis for the global burden of disease study 2017","volume":"395","author":"Bikbov","year":"2020","journal-title":"Lancet"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/S2213-8587(18)30313-9","article-title":"Change in albuminuria and subsequent risk of end-stage kidney disease: an individual participant-level consortium meta-analysis of observational studies","volume":"7","author":"Coresh","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1056\/NEJMoa011303","article-title":"Renoprotective effect of the angiotensin-receptor antagonist irbesartan in patients with nephropathy due to type 2 diabetes","volume":"345","author":"Lewis","year":"2001","journal-title":"N Engl J Med"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"475","DOI":"10.2147\/CEOR.S313857","article-title":"A predictive model for progression of chronic kidney disease to kidney failure using a large administrative claims database","volume":"13","author":"Dai","year":"2021","journal-title":"Clinicoecon Outcomes Res"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"21613","DOI":"10.1038\/s41598-023-48815-w","article-title":"A machine learning driven nomogram for predicting chronic kidney disease stages 3\u20135","volume":"13","author":"Ghosh","year":"2023","journal-title":"Sci Rep"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e2291","DOI":"10.7717\/peerj-cs.2291","article-title":"Enhancing machine learning-based forecasting of chronic renal disease with explainable AI","volume":"10","author":"Singamsetty","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"103286","DOI":"10.1016\/j.eclinm.2025.103286","article-title":"Identification and validation of an explainable early-stage chronic kidney disease prediction model: a multicenter retrospective study","volume":"84","author":"He","year":"2025","journal-title":"EClinicalMedicine"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit Care"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e33043","DOI":"10.2196\/33043","article-title":"Automatically explaining machine learning predictions on severe chronic obstructive pulmonary disease exacerbations: retrospective cohort study","volume":"10","author":"Zeng","year":"2022","journal-title":"JMIR Med Inform"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1007\/s40620-023-01573-4","article-title":"Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review","volume":"36","author":"Sanmarchi","year":"2023","journal-title":"J Nephrol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e60145","DOI":"10.7759\/cureus.60145","article-title":"Predicting the progression of chronic kidney disease: a systematic review of artificial intelligence and machine learning approaches","volume":"16","author":"Khalid","year":"2024","journal-title":"Cureus"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1177\/0962280218784726","article-title":"Sample size for binary logistic prediction models: beyond events per variable criteria","volume":"28","author":"Van Smeden","year":"2019","journal-title":"Stat Methods Med Res"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1002\/sim.7992","article-title":"Minimum sample size for developing a multivariable prediction model: PART II - binary and time-to-event outcomes","volume":"38","author":"Riley","year":"2019","journal-title":"Stat Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.6009\/jjrt.2023-2266","article-title":"[Fundamentals] 5. Python+scikit-learn for machine learning in medical imaging","volume":"79","author":"Tanaka","year":"2023","journal-title":"Jpn J Radiol Technol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/s12325-020-01568-8","article-title":"Burden of chronic kidney disease by KDIGO categories of glomerular filtration rate and albuminuria: a systematic review","volume":"38","author":"Murton","year":"2021","journal-title":"Adv Ther"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1093\/jamia\/ocad051","article-title":"Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection","volume":"30","author":"Jang","year":"2023","journal-title":"J Am Med Inform Assoc"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3389\/fpubh.2024.1495054","article-title":"Development of a machine learning tool to predict the risk of incident chronic kidney disease using health examination data","volume":"12","author":"Yoshizaki","year":"2024","journal-title":"Front Public Health"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1159\/000540682","article-title":"Development and validation of a machine learning-based prognostic model for IgA nephropathy with chronic kidney disease stage 3 or 4","volume":"10","author":"Yu","year":"2024","journal-title":"Kidney Dis (Basel)"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/1472-6947-8-53","article-title":"Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers","volume":"8","author":"Vickers","year":"2008","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1093\/ndt\/gfad195","article-title":"Proteinuria, measured or estimated albuminuria for risk prediction in patients with chronic kidney disease?","volume":"39","author":"Kim","year":"2024","journal-title":"Nephrol Dial Transplant"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1007\/s00467-016-3555-6","article-title":"Anemia in nephrotic syndrome: approach to evaluation and treatment","volume":"32","author":"Iorember","year":"2017","journal-title":"Pediatr Nephrol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1053\/ajkd.2001.25174","article-title":"Erythropoietin and transferrin metabolism in nephrotic syndrome","volume":"38","author":"Vaziri","year":"2001","journal-title":"Am J Kidney Dis"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"105020","DOI":"10.1016\/j.phrs.2020.105020","article-title":"Efficacy and safety of HIF prolyl-hydroxylase inhibitor vs epoetin and darbepoetin for anemia in chronic kidney disease patients not undergoing dialysis: a network meta-analysis","volume":"159","author":"Zheng","year":"2020","journal-title":"Pharmacol Res"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1080\/15384101.2023.2296184","article-title":"High-density lipoprotein protects vascular endothelial cells from indoxyl sulfate insults through its antioxidant ability","volume":"22","author":"Chen","year":"2023","journal-title":"Cell Cycle"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2830","DOI":"10.3390\/ijms22062830","article-title":"Effect of high-density lipoprotein from healthy subjects and chronic kidney disease patients on the CD14 expression on polymorphonuclear leukocytes","volume":"22","author":"Cohen","year":"2021","journal-title":"Int J Mol Sci"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1782951\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:26:17Z","timestamp":1775107577000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1782951\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":29,"alternative-id":["10.3389\/fpubh.2026.1782951"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1782951","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]},"article-number":"1782951"}}