Prediction of Vancomycin-Associated Nephrotoxicity Based on the Area under the Concentration–Time Curve of Vancomycin: A Machine Learning Analysis

Abstract

Several machine learning models have been proposed to predict vancomycin (VCM)-associated nephrotoxicity; however, they have notable limitations. Specifically, they do not use the area under the concentration–time curve (AUC) as recommended in the latest guidelines and do not address imbalanced data. Thus, we aimed to develop a novel model for predicting VCM-associated nephrotoxicity while overcoming these limitations. We retrospectively analyzed the medical records of patients who received VCM intravenously at our hospital from August 2017 to July 2021. We developed machine learning models for predicting VCM-associated nephrotoxicity based on the AUC of VCM and other patient background factors by using the following machine learning algorithms: lasso regression, support vector machine, complement naïve Bayes classifier, decision tree, random forest, and AdaBoost. We utilized the synthetic minority oversampling technique (SMOTE) and class weighting technique for dealing with imbalanced data and compared the performance of our developed machine learning models with that of a conventional model (AUC-guided therapeutic drug monitoring (TDM); AUC at steady state ≤600 µg·h/mL). Data from 270 patients were analyzed. The random forest with SMOTE was the best-performing model, achieving an F1 score of 0.353 and a sensitivity of 0.632 on the test data, compared with the conventional model, with an F1 score of 0.286 and a sensitivity of 0.316. We developed the first machine learning model for predicting VCM-associated nephrotoxicity based on the AUC of VCM, reducing the number of overlooked cases of nephrotoxicity compared with AUC-guided TDM, which may benefit patients overlooked by AUC-guided TDM.