Development and internal validation of an interpretable machine learning model for predicting vancomycin-induced nephrotoxicity in hospitalized children.

introductionVancomycin is widely used for severe Gram‑positive infections in children, but vancomycin‑induced nephrotoxicity (VIN) limits its safe application. Existing prediction models rely primarily on traditional logistic regression with limited discriminative performance in pediatric populations, and machine learning (ML) approaches have not been systematically evaluated.

aimThis study aimed to develop and internally validate an interpretable ML model for predicting VIN in pediatric patients using electronic health record (EHR) data.

methodWe conducted a retrospective EHR-based study at a tertiary children's hospital. Children aged 1 month to 18 years who received vancomycin for ≥ 3 consecutive days between December 2017 and November 2024 were included. Patients with moderate-to-severe pre-existing renal dysfunction [estimated glomerular filtration rate (eGFR) ≤ 59 mL/min/1.73 m

resultsA total of 1,452 children were included, of whom 206 (14.2%) developed VIN. EXtreme gradient boosting (XGboost) achieved the best predictive performance (AUROC = 0.90, AUPR = 0.74, Brier score = 0.07). A simplified 6‑feature XGBoost model (eGFR, amphotericin B, early vancomycin trough concentration, albumin, immunosuppressant use, and acyclovir/ganciclovir co-administration) achieved comparable discrimination to the full model (AUROC = 0.87; P > 0.05 by DeLong's test) with acceptable calibration (ECE 3.8%). DCA suggested favorable net benefit across clinically relevant risk thresholds.

conclusionOur interpretable 6-feature XGBoost model demonstrated promising internal discrimination for pediatric VIN prediction. Pending external validation and temporal evaluation, this model may serve as a hypothesis-generating decision-support framework for risk stratification.