# A nomogram for predicting individual risk of acute kidney injury after endovascular therapy in large vessel occlusion stroke

## TL;DR

This study created a tool to predict the risk of kidney injury in stroke patients after a specific treatment.

## Contribution

A novel nomogram model was developed and validated for predicting acute kidney injury after endovascular therapy in large vessel occlusion stroke.

## Key findings

- Hypertension, smoking, blood glucose, proteinuria, creatinine, and ventilation duration were identified as risk factors for AKI.
- The nomogram achieved an AUC of 0.890, indicating strong predictive performance.
- The model showed favorable net clinical benefit and good calibration and clinical utility.

## Abstract

This study was conducted to develop and validate a nomogram model for the early prediction of acute kidney injury (AKI) in patients with acute ischemic stroke with large vessel occlusion (AIS-LVO) following endovascular therapy (EVT).

This retrospective study enrolled 450 patients with AIS-LVO admitted to the Dongguan Hospital of Guangzhou University of Chinese Medicine for EVT between July 2018 and September 2024. After applying exclusion criteria, 346 patients meeting the research criteria were included. These patients were randomly divided into a training cohort (N = 243) and a validation cohort (N = 103) at a 7:3 ratio for model development and validation. Least absolute shrinkage and selection operator (LASSO) regression and multinomial logistic regression analysis were employed for feature selection and identification of key predictors for the nomogram. The performance and clinical utility of the nomogram were assessed using the receiver operating characteristic (ROC) curve, calibration curve, clinical impact curve (CIC), and decision curve analysis (DCA) curve.

Hypertension, smoking, admission blood glucose, proteinuria, serum creatinine, and duration of mechanical ventilation were identified as independent risk factors for AKI in patients with AIS-LVO after EVT. The nomogram demonstrated excellent predictive performance, with an area under curve (AUC) of 0.890 [95% CI (0.846–0.935)]. These results indicate that the model offers a favorable net clinical benefit.

The nomogram developed in this study demonstrates significant clinical utility in identifying patients with AIS-LVO at high risk of developing AKI after EVT.