An online dynamic nomogram for predicting acute kidney injury after endovascular therapy in acute ischemic stroke.

OBJECTIVE: There is still a lack of effective means for comprehensively and accurately evaluating the risk of acute kidney injury (AKI) after endovascular therapy (EVT) in patients with acute ischemic stroke (AIS). Therefore, this study aimed to develop and validate a nomogram for accurately predicting the risk of AKI after EVT in patients with AIS. METHODS: 673 patients were included in our study, comprising 324 in the training cohort, 140 in the internal validation cohort, and 209 in the external validation cohort. The nomogram was developed based on the variables screened using the least absolute shrinkage and selection operator regression and multivariate logistic regression. The predictive efficiency of the nomogram was validated using both internal and external validation cohorts. Furthermore, the association between AKI and 90-day functional outcomes and mortality was analyzed based on propensity-score matching. RESULTS: Five risk factors for AKI were identified and used to construct a nomogram: baseline National Institutes of Health Stroke Scale score, preoperative creatinine level, pneumonia, acute heart failure, and hypotension. The nomogram exhibited good predictive performance as assessed by the area under the curve, calibration plots, and decision-curve analysis. In the propensity-score matched cohorts, AKI remained significantly associated with 90-day worse neurological outcomes. CONCLUSIONS: We developed and validated an online dynamic nomogram with high predictive accuracy for predicting the risk of AKI in patients with AIS undergoing EVT, which is beneficial for clinical decision-making. Furthermore, our analysis showed that AKI was associated with poorer functional outcomes after EVT.