Risk Scoring System for Vancomycin-Associated Acute Kidney Injury

Area of Science:

• Nephrology
• Pharmacology
• Clinical Medicine

Background:

• Vancomycin-associated acute kidney injury (AKI) is a significant clinical concern.
• Effective risk stratification for vancomycin-AKI is crucial for patient management.

Purpose of the Study:

• To develop and validate a predictive risk scoring system for vancomycin-associated AKI.
• To identify key risk factors contributing to vancomycin-induced nephrotoxicity.

Main Methods:

• Retrospective analysis of 104 patients undergoing vancomycin therapeutic drug monitoring.
• Univariate and multivariable logistic regression to identify risk factors.
• Development of a scoring system and validation using machine learning models (elastic net, random forest, SVM).

Main Results:

• The incidence of vancomycin-associated AKI was 31.7%.
• Key predictors included bodyweight ≤60 kg, Charlson comorbidity index ≥3, vancomycin trough level >15 μg/ml, and ≥6 concomitant nephrotoxic agents.
• The scoring system demonstrated good predictive performance with an average AUROC of 0.735.
• Risk of AKI increased progressively with higher scores (5% for 0-1 to 65% for 6-7).

Conclusions:

• A validated risk scoring system can effectively predict vancomycin-associated AKI.
• The system is applicable in clinical settings, particularly when vancomycin is co-administered with nephrotoxic agents.
• Early identification of high-risk patients can guide preventative strategies and treatment adjustments.