Abstract
Selecting an appropriate population pharmacokinetic (PK) model for individual patients in model-informed precision dosing (MIPD) can be challenging, particularly in the absence of therapeutic drug monitoring (TDM) samples. We developed a machine learning (ML) model to guide individualized PK model selection for a priori MIPD of vancomycin based on routinely recorded patient characteristics. This retrospective analysis included 343,636 vancomycin TDM records, each from a distinct adult patient across 156 healthcare centers, along with a priori predictions from six PK models. A multi-label classification approach was applied, labeling PK model predictions based on whether they fell within 80%–125% of observed TDM values. Various modeling strategies were evaluated using XGBoost as the base algorithm, with binary relevance selected for the final model. At the prediction stage, PK models were ranked and averaged for each patient based on ML-predicted probabilities that predictions would fall within 80%–125% of the observed concentration. Selecting the highest ranked PK model for each patient and ML-based model averaging outperformed all single PK models, body mass index-based selection, and naive averaging. On a population level, these ML approaches resulted in more accurate predictions, a higher proportion of predictions within 80%–125% of observed vancomycin concentrations, and no systematic bias. Predictive performance declined with lower ML-assigned rankings, and selecting the lowest-ranked PK model for each patient resulted in worse performance than the worst-performing single PK model. By guiding the selection of appropriate models and avoiding less suitable ones, ML approaches for a priori MIPD may improve early dosing decisions.
Summary
What is the current knowledge on the topic?
Pharmacokinetic (PK) model selection is a key challenge in model-informed precision dosing (MIPD), especially in the absence of therapeutic drug monitoring (TDM) data. Current practice often relies on patient similarity to model development populations or external validation studies.
What question did this study address?
Can machine learning (ML) guide individualized PK model selection and help avoid inappropriate models for a priori vancomycin MIPD, using only routinely recorded patient characteristics?
What does this study add to our knowledge?
ML-based ranking and averaging of PK models improved a priori prediction accuracy compared to conventional model selection strategies for vancomycin MIPD and helped avoid inaccurate models. This study highlights the potential of ML models trained with real-world data to guide model selection in MIPD.
How might this change drug discovery, development, and/or therapeutics
Integrating ML-guided model selection into MIPD tools could improve early dosing decisions before TDM data become available.
W. van Os, A. O'Jeanson, C. Troisi, et al., “ Machine Learning-Based Model Selection and Averaging Outperform Single-Model Approaches for a Priori Vancomycin Precision Dosing,” CPT: Pharmacometrics & Systems Pharmacology (2025): 1–11, https://doi.org/10.1002/psp4.70084.