Methodological Techniques Used in Machine Learning to Support Individualized Drug Dosing Regimens Based on Pharmacokinetic Data: A Scoping Review.

Abstract

Background and objective: Individualized drug dosing is a highly effective strategy for optimizing therapeutic outcomes, especially for drugs with high inter-individual variability. Population pharmacokinetic modeling is a widely used approach to characterize inter-individual variability in therapeutic drug monitoring. However, the development of population pharmacokinetic models is labor intensive and requires significant technical expertise. Machine learning (ML) represents a promising alternative for personalized drug dosing strategies. Despite numerous studies applying ML in this context, no previous work has comprehensively reviewed and compared their methodologies and predictive performance. This scoping review addresses this gap in the existing literature with the aim to examine the methodological approaches used in ML-based pharmacokinetic modeling for dose optimization.

Methods: Five databases were systematically searched from their inception to May 2025. Studies comparing predictions of drug concentrations or pharmacokinetic parameters between ML and population pharmacokinetic models were included. Studies published in non-English language, reviews, protocols, or studies that did not employ ML models for individualized dose regimens or treatment plans were excluded.

Results: Fifty-eight studies were included. We found that boosting-based models, tree-based models, instance-based, and regression-based models were the most commonly used ML approaches. Approximately 31% of the studies integrated ML with population pharmacokinetic models, while the remainder developed stand-alone ML models. Inconsistencies in reporting were evident, as only 60% of the studies detailed their feature selection methods. Model evaluation approaches also varied: 47% of ML models used internal test sets, while the remainder employed external datasets or mixed approaches. In terms of predictive accuracy, ML models performed comparably to or better than population pharmacokinetic models, especially for drugs with significant pharmacokinetic variability.

Conclusions: This review identifies substantial heterogeneity in ML modeling approaches, feature selection, and model evaluation. To enhance the reproducibility and clinical applicability of ML models in individualized drug dosing, standardization in reporting and methodological practices is essential.