{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T04:54:27Z","timestamp":1791262467242,"version":"4.1.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The blood urea nitrogen-to-creatinine ratio (BUN\/Cr) may reflect renal perfusion and systemic stress, but its early course after acute stroke is unclear. We identified 72-h BUN\/Cr trajectories and assessed their role in interpretable machine-learning evaluation of 28-day mortality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This dual-center landmark study included 2,805 ICU patients with acute ischemic stroke, nontraumatic intracerebral hemorrhage, or nontraumatic subarachnoid hemorrhage from the Medical Information Mart for Intensive Care IV (MIMIC-IV) version 3.1. Before modeling, patients were split into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f1,964) and an internal test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f841). The trajectory and prediction models developed in the training set were applied without modification to the internal test set and the Qinghai external validation cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f387). Eight algorithms and prespecified nested models were evaluated using Cox regression, discrimination, calibration, paired comparisons, decision curves, and TreeSHAP.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A quadratic three-class model identified low\/stable, high U-shaped, and rising-to-plateau patterns, with mortality rates of 21.6, 35.9, and 39.7%. Adjusted hazard ratios versus Class 1 were 1.87 (95% CI 1.25\u20132.79) for Class 2 and 1.73 (1.31\u20132.29) for Class 3. The training-selected Light Gradient Boosting Machine (LightGBM) achieved an AUROC of 0.734 (95% CI 0.695\u20130.773), a calibration slope of 0.894, and an O\/E ratio of 1.015 in the internal test set. In the Qinghai external validation cohort, the AUROC was 0.624 (95% CI 0.559\u20130.689), the calibration slope was 0.459, and the O\/E ratio was 1.920. Adding trajectory class to a model already containing routine clinical and static renal variables changed the AUROC by 0.003 in the internal test set (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.515) and \u22120.014 in the Qinghai external validation cohort (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f=\u202f0.130), without a clear gain in discrimination.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>BUN\/Cr trajectories were associated with post-landmark mortality and summarized the three-day renal course. Training-selected LightGBM showed moderate internal discrimination and underwent frozen external evaluation. Trajectory class added modest information beyond routine clinical and static renal variables, while the combined approach provides an interpretable framework for 72-h reassessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1865384","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T04:26:10Z","timestamp":1791260770000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating 72-h BUN\/Cr trajectories with interpretable machine learning for 28-day mortality after acute stroke: a dual-center landmark study"],"prefix":"10.3389","volume":"17","author":[{"given":"Zihai","family":"Cheng","sequence":"first","affiliation":[{"name":"College of Clinical Medicine Qinghai University, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongsheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]},{"name":"Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuren","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Clinical Medicine Qinghai University, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghui","family":"He","sequence":"additional","affiliation":[{"name":"College of Clinical Medicine Qinghai University, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Clinical Medicine Qinghai University, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoma","family":"Duoji","sequence":"additional","affiliation":[{"name":"College of Clinical Medicine Qinghai University, Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqing","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]},{"name":"Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanpeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]},{"name":"Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Han","sequence":"additional","affiliation":[{"name":"Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]},{"name":"Qinghai Provincial People\u2019s Hospital","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/S1474-4422(21)00252-0","article-title":"Global, regional, and national burden of stroke and its risk factors, 1990\u20132019: a systematic analysis for the global burden of disease study 2019","volume":"20","year":"2019","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e347","DOI":"10.1161\/CIR.0000000000001209","article-title":"2024 heart disease and stroke statistics: a report of US and global data from the American Heart Association","volume":"149","author":"Martin","year":"2024","journal-title":"Circulation"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s40635-020-00305-3","article-title":"Ischaemic stroke-induced distal organ damage: pathophysiology and new therapeutic strategies","volume":"8","author":"Robba","year":"2020","journal-title":"Intensive Care Med Exp"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1007\/s11064-024-04126-8","article-title":"Stroke and distal organ damage: exploring brain-kidney crosstalk","volume":"49","author":"Dulam","year":"2024","journal-title":"Neurochem Res"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1038\/nrneurol.2012.98","article-title":"The immunology of acute stroke","volume":"8","author":"Chamorro","year":"2012","journal-title":"Nat Rev Neurol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1177\/0271678X19890931","article-title":"Brain-kidney interaction: renal dysfunction following ischemic stroke","volume":"40","author":"Zhao","year":"2020","journal-title":"J Cereb Blood Flow Metab"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1186\/s12882-018-1085-0","article-title":"Incidence and impact on outcomes of acute kidney injury after a stroke: a systematic review and meta-analysis","volume":"19","author":"Arnold","year":"2018","journal-title":"BMC Nephrol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1159\/000469669","article-title":"Serum creatinine: Not so simple!","volume":"136","author":"Delanaye","year":"2017","journal-title":"Nephron"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"R82","DOI":"10.1186\/cc9004","article-title":"Fluid accumulation, recognition and staging of acute kidney injury in critically ill patients","volume":"14","author":"Macedo","year":"2010","journal-title":"Crit Care"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/nrneph.2013.22","article-title":"Vasopressin: A novel target for the prevention and retardation of kidney disease?","volume":"9","author":"Bankir","year":"2013","journal-title":"Nat Rev Nephrol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e0337807","DOI":"10.1371\/journal.pone.0337807","article-title":"Elevated blood urea nitrogen-to-creatinine ratio predicts short-term mortality in intensive care unit patients with ischemic stroke: evidence from a multicenter cohort","volume":"20","author":"Huang","year":"2025","journal-title":"PLoS One"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"e085912","DOI":"10.1136\/bmjopen-2024-085912","article-title":"Association between blood urea nitrogen to creatinine ratio and 3-month outcome in patients with acute ischaemic stroke: a retrospective cohort study from a large healthcare system","volume":"14","author":"Wang","year":"2024","journal-title":"BMJ Open"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e179","DOI":"10.1016\/S2589-7500(20)30018-2","article-title":"Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records","volume":"2","author":"Thorsen-Meyer","year":"2020","journal-title":"Lancet Digit Health"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1582","DOI":"10.1007\/s00134-022-06890-z","article-title":"Development and validation of novel sepsis subphenotypes using trajectories of vital signs","volume":"48","author":"Bhavani","year":"2022","journal-title":"Intensive Care Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1186\/s13054-016-1546-4","article-title":"Acute kidney injury subphenotypes based on creatinine trajectory identifies patients at increased risk of death","volume":"20","author":"Bhatraju","year":"2016","journal-title":"Crit Care"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1038\/s41392-025-02261-4","article-title":"Development and validation of dynamic clinical subphenotypes in acute pancreatitis patients using vital sign trajectories in intensive care units: a multinational cohort study","volume":"10","author":"Wang","year":"2025","journal-title":"Signal Transduct Target Ther"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1016\/S2213-2600(20)30124-7","article-title":"Subphenotypes in critical care: translation into clinical practice","volume":"8","author":"Reddy","year":"2020","journal-title":"Lancet Respir Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1161\/CIRCOUTCOMES.110.957951","article-title":"Landmark analysis at the 25-year landmark point","volume":"4","author":"Dafni","year":"2011","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e020683","DOI":"10.1136\/bmjopen-2017-020683","article-title":"Framework to construct and interpret latent class trajectory modelling","volume":"8","author":"Lennon","year":"2018","journal-title":"BMJ Open"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v078.i02","article-title":"Estimation of extended mixed models using latent classes and latent processes: the R package lcmm","volume":"78","author":"Proust-Lima","year":"2017","journal-title":"J Stat Softw"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1093\/biomet\/81.3.515","article-title":"Proportional hazards tests and diagnostics based on weighted residuals","volume":"81","author":"Grambsch","year":"1994","journal-title":"Biometrika"},{"key":"ref26","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/BF01709751","article-title":"The SOFA (Sepsis-related organ failure assessment) score to describe organ dysfunction\/failure","volume":"22","author":"Vincent","year":"1996","journal-title":"Intensive Care Med"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1001\/jama.270.24.2957","article-title":"A new simplified acute physiology score (SAPS II) based on a European\/North American Multicenter Study","volume":"270","author":"Le Gall","year":"1993","journal-title":"JAMA"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1186\/s13054-019-2663-7","article-title":"The SOFA score-development, utility and challenges of accurate assessment in clinical trials","volume":"23","author":"Lambden","year":"2019","journal-title":"Crit Care"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Mak"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/s00134-021-06454-7","article-title":"Acute kidney injury in the critically ill: an updated review on pathophysiology and management","volume":"47","author":"Pickkers","year":"2021","journal-title":"Intensive Care Med"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1161\/STROKEAHA.122.042075","article-title":"Perspective review of myeloid immune cell responses and poststroke immunosuppression","volume":"54","author":"Xie","year":"2023","journal-title":"Stroke"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1149671","DOI":"10.3389\/fneur.2023.1149671","article-title":"A review of stress-induced hyperglycaemia in the context of acute ischaemic stroke: definition, underlying mechanisms, and the status of insulin therapy","volume":"14","author":"Yao","year":"2023","journal-title":"Front Neurol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1186\/s12916-024-03689-1","article-title":"The associations of post-stroke delirium with outcomes: a systematic review and meta-analysis","volume":"22","author":"Zhang","year":"2024","journal-title":"BMC Med"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1054098","DOI":"10.3389\/fneur.2022.1054098","article-title":"Association of hypocalcemia with in-hospital mortality in critically ill patients with intracerebral hemorrhage: a retrospective cohort study","volume":"13","author":"Gu","year":"2023","journal-title":"Front Neurol"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1056\/NEJMc2104626","article-title":"The clinician and dataset shift in artificial intelligence","volume":"385","author":"Finlayson","year":"2021","journal-title":"N Engl J Med"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"kxz041","DOI":"10.1093\/biostatistics\/kxz041","article-title":"From development to deployment: dataset shift, causality, and shift-stable models in health AI","volume":"21","author":"Subbaswamy","year":"2020","journal-title":"Biostatistics"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1038\/s41591-019-0548-6","article-title":"Do no harm: a roadmap for responsible machine learning for health care","volume":"25","author":"Wiens","year":"2019","journal-title":"Nat Med"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1865384\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T04:26:12Z","timestamp":1791260772000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1865384\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,6]]},"references-count":43,"alternative-id":["10.3389\/fneur.2026.1865384"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1865384","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,6]]},"article-number":"1865384"}}