An interpretable XGBoost model for predicting measured teicoplanin plasma concentrations in ICU patients with bloodstream infection: a two-center real-world validation study
Abstract
BackgroundProfound pharmacokinetic variability complicates individualized teicoplanin therapy in critically ill patients with bloodstream infection. We aimed to develop and externally validate an interpretable machine learning (ML) model for predicting teicoplanin plasma concentrations in this population.MethodsThis retrospective two-center real-world study included 260 intensive care unit patients from one center as the modeling cohort (randomly split 8:2 into training and internal test sets) and 91 patients from an independent center as the external validation cohort. Ten ML and deep learning algorithms were constructed using demographic, clinical, and laboratory variables. The optimal model was interpreted via Shapley additive explanations (SHAP).ResultsThe extreme gradient boosting (XGBoost) model achieved the most favorable point estimates. On the internal test set (n = 52): the model yielded an R2 of 0.73 (95% CI 0.56–0.81), RMSE of 3.22 (95% CI 2.62–3.77), MAE of 2.52 (95% CI 1.98–3.10), and ±30% prediction accuracy (P30%) of 78.8% (95% CI 67.3–88.5). On the external validation cohort (n = 91), it achieved an R2 of 0.76 (95% CI 0.69–0.80), RMSE of 3.61 (95% CI 3.08–4.14), MAE of 2.89 (95% CI 2.48–3.35), and P30% of 69.2% (95% CI 59.3–78.0). After Holm–Bonferroni correction, paired bootstrap comparisons showed XGBoost significantly outperformed 5 of 9 comparator algorithms in the internal test set and 7 of 9 in the external cohort, with performance comparable to several other tree-based ensemble methods. SHAP analysis identified daily dose, hemodialysis, and mechanical ventilation as features positively associated with predicted teicoplanin concentrations.ConclusionThis internally and externally validated interpretable XGBoost model delivers consistent cross-cohort performance, and serves as a dose-anchored adjunct to conventional therapeutic drug monitoring, providing a preliminary methodological foundation for exploring individualized teicoplanin dosing strategies.
Related
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
- Development and Validation of an Interpretable Machine‐Learning Model for Predicting Suboptimal Clinical Response After Sleeve Gastrectomy: A Multicenter Study
- An interpretable machine learning model for predicting intensive care unit mortality risk in elderly patients with concomitant cardiogenic shock and sepsis: Development and external validation using two large critical care databases
- Development and validation of interpretable machine learning models for predicting cumulative live birth rates in assisted reproductive technology: a SHAP-based analysis.
- Development and internal validation of an interpretable machine learning model for predicting vancomycin-induced nephrotoxicity in hospitalized children
BibTeX
@article{zhou2026interpretable,
title = {{An interpretable XGBoost model for predicting measured teicoplanin plasma concentrations in ICU patients with bloodstream infection: a two-center real-world validation study}},
author = {Wenbin Zhou and Yingying Liu and Yuanan Ma and Lhamo Sonam and Ming Zhang and Yuancan Xiao and Chunming Lyu and Lixin Wei},
journal = {Frontiers in Pharmacology},
year = {2026},
month = nov,
doi = {10.3389/fphar.2026.1963274},
url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1963274},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - An interpretable XGBoost model for predicting measured teicoplanin plasma concentrations in ICU patients with bloodstream infection: a two-center real-world validation study
AU - Wenbin Zhou
AU - Yingying Liu
AU - Yuanan Ma
AU - Lhamo Sonam
AU - Ming Zhang
AU - Yuancan Xiao
AU - Chunming Lyu
AU - Lixin Wei
PY - 2026
DA - 2026/11/09
JO - Frontiers in Pharmacology
DO - 10.3389/fphar.2026.1963274
UR - https://www.frontiersin.org/articles/10.3389/fphar.2026.1963274
AB - BackgroundProfound pharmacokinetic variability complicates individualized teicoplanin therapy in critically ill patients with bloodstream infection. We aimed to develop and externally validate an interpretable machine learning (ML) model for predicting teicoplanin plasma concentrations in this population.MethodsThis retrospective two-center real-world study included 260 intensive care unit patients from one center as the modeling cohort (randomly split 8:2 into training and internal test sets) and 91 patients from an independent center as the external validation cohort. Ten ML and deep learning algorithms were constructed using demographic, clinical, and laboratory variables. The optimal model was interpreted via Shapley additive explanations (SHAP).ResultsThe extreme gradient boosting (XGBoost) model achieved the most favorable point estimates. On the internal test set (n = 52): the model yielded an R2 of 0.73 (95% CI 0.56–0.81), RMSE of 3.22 (95% CI 2.62–3.77), MAE of 2.52 (95% CI 1.98–3.10), and ±30% prediction accuracy (P30%) of 78.8% (95% CI 67.3–88.5). On the external validation cohort (n = 91), it achieved an R2 of 0.76 (95% CI 0.69–0.80), RMSE of 3.61 (95% CI 3.08–4.14), MAE of 2.89 (95% CI 2.48–3.35), and P30% of 69.2% (95% CI 59.3–78.0). After Holm–Bonferroni correction, paired bootstrap comparisons showed XGBoost significantly outperformed 5 of 9 comparator algorithms in the internal test set and 7 of 9 in the external cohort, with performance comparable to several other tree-based ensemble methods. SHAP analysis identified daily dose, hemodialysis, and mechanical ventilation as features positively associated with predicted teicoplanin concentrations.ConclusionThis internally and externally validated interpretable XGBoost model delivers consistent cross-cohort performance, and serves as a dose-anchored adjunct to conventional therapeutic drug monitoring, providing a preliminary methodological foundation for exploring individualized teicoplanin dosing strategies.
SN - 1663-9812
ER -