Beyond Traditional Covariates: An Interpretable Machine Learning Workflow for Improved Hybrid Pharmacometric Modeling
5 affiliations
- 1Department of Biomedical Engineering Eindhoven University of Technology Eindhoven the Netherlands
- 2Department of Hospital Pharmacy Erasmus University Medical Center Rotterdam the Netherlands
- 3Rotterdam Clinical Pharmacometrics Group Rotterdam the Netherlands
- 4Division of Neonatology, Department of Neonatal & Pediatric ICU Erasmus MC Rotterdam the Netherlands
- 5Department of Intensive Care Medicine Radboud University Medical Center Nijmegen the Netherlands
Abstract
Model‐informed precision dosing is often constrained by the limited generalizability of traditional population pharmacokinetic models, especially in critically ill patients. A hybrid machine learning‐population pharmacokinetic framework is proposed to improve a priori pharmacokinetic predictions by integrating real‐world clinical data. This approach was applied to vancomycin trough concentration prediction. Two widely used two‐compartment population pharmacokinetic models provided individual pharmacokinetic parameter estimates. Maximum a posteriori Bayesian estimation was used to adjust population parameters for individual patients based on drug administration records, therapeutic drug monitoring values, and patient‐specific covariates from the MIMIC‐IV database. The resulting clearance and central volume of distribution estimates served as training targets for XGBoost and symbolic regression models. Machine learning‐predicted parameters were reinserted into the original pharmacokinetic equations to generate a priori vancomycin trough concentrations without reliance on therapeutic drug monitoring input. The hybrid models demonstrated improved prediction accuracy over traditional population pharmacokinetic covariate models and reduced vancomycin trough concentration prediction error by up to ~20%. XGBoost generally provided the highest predictive performance, while symbolic regression produced interpretable mathematical expressions revealing associations between non‐traditional clinical predictors and pharmacokinetic parameters, highlighting a trade‐off between accuracy and interpretability. This framework illustrates the potential of combining machine learning with population pharmacokinetic modeling to refine pharmacokinetic parameter estimation and support more precise, individualized dosing. The workflow is adaptable to other drugs and patient populations, offering a generalizable methodological strategy to identify non‐traditional predictors and enhance existing pharmacometric model performance in real‐world clinical settings.
Related
- Interpretable machine learning for identifying cost drivers of inpatient traditional Chinese medicine services in a tertiary hospital in China
- COMBINING CHEST X-RAY AND CLINICAL COVARIATES FOR OSTEOPOROSIS SCREENING: A MULTIMODAL DEEP LEARNING APPROACH
- A dynamic pharmacometric framework defining the relationship between ivermectin exposure and mosquito lethality
- Enhancing prenatal diagnostic workflow: a deep learning-based system for multi-class fetal ultrasound classification across all gestational stages
- Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
BibTeX
@article{relouw2026beyond,
title = {{Beyond Traditional Covariates: An Interpretable Machine Learning Workflow for Improved Hybrid Pharmacometric Modeling}},
author = {Freek J. A. Relouw and Jort J. M. T. Lokers and Tim Preijers and Sebastiaan D. T. Sassen and Natal A. W. van Riel and Birgit C. P. Koch},
journal = {CPT: Pharmacometrics \& Systems Pharmacology},
year = {2026},
month = aug,
doi = {10.1002/psp4.70313},
url = {https://doi.org/10.1002/psp4.70313},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Beyond Traditional Covariates: An Interpretable Machine Learning Workflow for Improved Hybrid Pharmacometric Modeling
AU - Freek J. A. Relouw
AU - Jort J. M. T. Lokers
AU - Tim Preijers
AU - Sebastiaan D. T. Sassen
AU - Natal A. W. van Riel
AU - Birgit C. P. Koch
PY - 2026
DA - 2026/08/04
JO - CPT: Pharmacometrics & Systems Pharmacology
DO - 10.1002/psp4.70313
UR - https://doi.org/10.1002/psp4.70313
AB - Model‐informed precision dosing is often constrained by the limited generalizability of traditional population pharmacokinetic models, especially in critically ill patients. A hybrid machine learning‐population pharmacokinetic framework is proposed to improve a priori pharmacokinetic predictions by integrating real‐world clinical data. This approach was applied to vancomycin trough concentration prediction. Two widely used two‐compartment population pharmacokinetic models provided individual pharmacokinetic parameter estimates. Maximum a posteriori Bayesian estimation was used to adjust population parameters for individual patients based on drug administration records, therapeutic drug monitoring values, and patient‐specific covariates from the MIMIC‐IV database. The resulting clearance and central volume of distribution estimates served as training targets for XGBoost and symbolic regression models. Machine learning‐predicted parameters were reinserted into the original pharmacokinetic equations to generate a priori vancomycin trough concentrations without reliance on therapeutic drug monitoring input. The hybrid models demonstrated improved prediction accuracy over traditional population pharmacokinetic covariate models and reduced vancomycin trough concentration prediction error by up to ~20%. XGBoost generally provided the highest predictive performance, while symbolic regression produced interpretable mathematical expressions revealing associations between non‐traditional clinical predictors and pharmacokinetic parameters, highlighting a trade‐off between accuracy and interpretability. This framework illustrates the potential of combining machine learning with population pharmacokinetic modeling to refine pharmacokinetic parameter estimation and support more precise, individualized dosing. The workflow is adaptable to other drugs and patient populations, offering a generalizable methodological strategy to identify non‐traditional predictors and enhance existing pharmacometric model performance in real‐world clinical settings.
SN - 2163-8306
ER -