Determining steady-state trough range in vancomycin drug dosing using machine learning.

ABSTRACT:

Background

Vancomycin is a renally eliminated, nephrotoxic, glycopeptide antibiotic with a narrow therapeutic window, widely used in intensive care units (ICU). We aimed to predict the risk of inappropriate vancomycin trough levels and appropriate dosing for each ICU patient.

Methods

Observed vancomycin trough levels were categorized into sub-therapeutic, therapeutic, and supra-therapeutic levels to train and compare different classification models. We included adult ICU patients (≥ 18 years) with at least one vancomycin concentration measurement during hospitalization at Mayo Clinic, Rochester, MN, from January 2007 to December 2017.

Result

The final cohort consisted of 5337 vancomycin courses. The XGBoost models outperformed other machine learning models with the AU

SUBMITTER: Tootooni MS 

PROVIDER: S-EPMC11139571 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature