Integrating 72-h BUN/Cr trajectories with interpretable machine learning for 28-day mortality after acute stroke: a dual-center landmark study.
- 1College of Clinical Medicine Qinghai University, Qinghai University, Xining, China.
- 2Department of Neurosurgery, Qinghai Provincial People's Hospital, Xining, China.
- 3Qinghai Provincial People's Hospital, Xining, China.
Abstract
Background
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.Methods
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 = 1,964) and an internal test set (n = 841). 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 = 387). Eight algorithms and prespecified nested models were evaluated using Cox regression, discrimination, calibration, paired comparisons, decision curves, and TreeSHAP.Results
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 1.25-2.79) for Class 2 and 1.73 (1.31-2.29) for Class 3. The training-selected Light Gradient Boosting Machine (LightGBM) achieved an AUROC of 0.734 (95% CI 0.695-0.773), 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 0.559-0.689), 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 (p = 0.515) and -0.014 in the Qinghai external validation cohort (p = 0.130), without a clear gain in discrimination.Conclusion
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.
Related
- XGBoost-Cox model effectively predicts mortality risk in elderly male patients with acute kidney injury: a retrospective cohort study integrating nonlinear feature engineering and interpretable machine learning
- Development and validation of an interpretable machine learning model for early prediction of mortality in ICU patients with chronic obstructive pulmonary disease and heart failure
- Joint Dynamic Trajectories of CEA and CA19-9 After Gastric Cancer Surgery: Prognostic Associations and a 12-Month Landmark Analysis
- An interpretable machine learning model integrating mucosal and cellular immunity to predict SARS-CoV-2 reinfection: a multicenter cohort study.
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
BibTeX
@article{cheng2026integrating,
title = {{Integrating 72-h BUN/Cr trajectories with interpretable machine learning for 28-day mortality after acute stroke: a dual-center landmark study.}},
author = {Zihai Cheng and Zhongsheng Lu and Shuren Wang and Menghui He and Yiwei Lv and Zhuoma Duoji and Xiaoqing Jin and Wanpeng Fan and Pei Han and Qiang Zhang},
journal = {Frontiers in neurology},
year = {2026},
month = oct,
doi = {10.3389/fneur.2026.1865384},
url = {https://europepmc.org/article/MED/42903085},
note = {CC BY},
}
RIS
TY - JOUR
TI - Integrating 72-h BUN/Cr trajectories with interpretable machine learning for 28-day mortality after acute stroke: a dual-center landmark study.
AU - Zihai Cheng
AU - Zhongsheng Lu
AU - Shuren Wang
AU - Menghui He
AU - Yiwei Lv
AU - Zhuoma Duoji
AU - Xiaoqing Jin
AU - Wanpeng Fan
AU - Pei Han
AU - Qiang Zhang
PY - 2026
DA - 2026/10/06
JO - Frontiers in neurology
DO - 10.3389/fneur.2026.1865384
UR - https://europepmc.org/article/MED/42903085
AB - Background 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.Methods 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 = 1,964) and an internal test set (n = 841). 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 = 387). Eight algorithms and prespecified nested models were evaluated using Cox regression, discrimination, calibration, paired comparisons, decision curves, and TreeSHAP.Results 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 1.25-2.79) for Class 2 and 1.73 (1.31-2.29) for Class 3. The training-selected Light Gradient Boosting Machine (LightGBM) achieved an AUROC of 0.734 (95% CI 0.695-0.773), 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 0.559-0.689), 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 (p = 0.515) and -0.014 in the Qinghai external validation cohort (p = 0.130), without a clear gain in discrimination.Conclusion 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.
SN - 1664-2295
ER -