Inflammation Markers Help Predict AKI After Bladder Cancer Surgery, reports study
Researchers have identified in a new study that perioperative dynamic alterations in systemic inflammatory markers are highly correlated with acute kidney injury (AKI) following radical cystectomy. The research also illustrated that machine learning–based prediction models, particularly those incorporating perioperative inflammatory measures, can efficiently classify patients at increased risk. The study was published in the Journal of Inflammation Research by Liu Z. and colleagues.
The research sought to establish if dynamic perioperative variations in systemic inflammatory markers were linked to AKI after radical cystectomy and if such changes would enhance prediction performance when integrated into machine learning models.
It was a multi-center retrospective cohort study between 2013 and 2022 in three university-affiliated tertiary care hospitals. A total of 727 patients undergoing radical cystectomy with urinary diversion for bladder cancer were included in the study. Inflammatory markers were based on pre- and post-operative blood counts, and trends were classified with restricted cubic splines (RCS).
A perioperative inflammation index was estimated from the number of positive trends in these markers. Multivariable logistic regression was employed to find independent risk factors for AKI. Machine learning models, such as XGBoost, were used to derive predictive models. Predictive performance was assessed with the area under the receiver operating characteristic curve (AUROC).
Results
Of 727 enrolled patients, 151 (20.8%) developed AKI after surgery.
Postoperative hemoglobin (p = 0.003; OR, 0.977; 95% CI, 0.962–0.992)
Albumin level (p = 0.007; OR, 0.906; 95% CI, 0.843–0.974)
Intraoperative fluid infusion rate (p < 0.001; OR, 0.769; 95% CI, 0.665–0.890)
Perioperative inflammation index (p < 0.001; OR, 1.507; 95% CI, 1.209–1.877)
Among all predictive models, XGBoost reported the highest accuracy with an AUROC of 0.801 (95% CI, 0.735–0.867), which reflected better performance in comparison to other algorithms.
This study shows that dynamic perioperative changes in systemic inflammation markers are strongly associated with AKI risk after radical cystectomy. Integrating perioperative inflammatory assessment into routine practice can potentially optimize care and avert AKI among patients undergoing bladder cancer surgery.
Reference:
Liu Z, Fan P, Lu Y, Cao M, Yao W, Chen D, Ji F. Integrating Pre- and Postoperative Systemic Inflammatory Markers for Acute Kidney Injury Prediction Following Radical Cystectomy: A Multi-Center Retrospective Study. J Inflamm Res. 2025;18:13335-13345
https://doi.org/10.2147/JIR.S529335
