Stochastic Gates for Covariate Selection in Population Pharmacokinetics Modeling
Authors:
Open Access
- 4 February 2026
- journal article
- Published by Wiley in CPT: Pharmacometrics & Systems Pharmacology
- Vol. 15 (2) , e70147
Abstract
Covariate selection in population pharmacokinetics modeling is essential for understanding interindividual variability in drug response and optimizing dosing. Traditional stepwise covariate modeling is often time‐consuming, compared to the new machine learning alternatives. This study investigates the use of neural networks with stochastic gates for automated covariate selection, aiming to efficiently identify relevant covariates while penalizing excessive covariate inclusion. On various synthetic datasets, the approach demonstrated robustness in detecting important covariates, overcoming challenges such as high correlations, low covariate frequencies, high interindividual variability, and complex covariate dependencies. In real clinical data from a monalizumab study, the method successfully identified covariates that matched those found by experts. However, for tixagevimab/cilgavimab, it identified a superset of covariates, indicating a potential need for further pruning. This machine learning‐based method enhances the covariate preselection process in population pharmacokinetics model development, offering significant time savings and improving efficiency even under challenging scenarios.Keywords
This publication has 22 references indexed in Scilit:
- SAMBA: A novel method for fast automatic model building in nonlinear mixed‐effects modelsCPT: Pharmacometrics & Systems Pharmacology, 2022
- Fast screening of covariates in population models empowered by machine learningJournal of Pharmacokinetics and Pharmacodynamics, 2021
- An artificial neural network−pharmacokinetic model and its interpretation using Shapley additive explanationsCPT: Pharmacometrics & Systems Pharmacology, 2021
- A novel method based on unbiased correlations tests for covariate selection in nonlinear mixed effects models: The COSSAC approachCPT: Pharmacometrics & Systems Pharmacology, 2021
- Evaluation of Approaches to Deal with Low-Frequency Nuisance Covariates in Population Pharmacokinetic AnalysesThe AAPS Journal, 2015
- Importance of Shrinkage in Empirical Bayes Estimates for Diagnostics: Problems and SolutionsThe AAPS Journal, 2009
- The lasso—a novel method for predictive covariate model building in nonlinear mixed effects modelsJournal of Pharmacokinetics and Pharmacodynamics, 2007
- Efficient Screening of Covariates in Population Models Using Wald's Approximation to the Likelihood Ratio TestJournal of Pharmacokinetics and Pharmacodynamics, 2001
- Automated Covariate Model Building Within NONMEMPharmaceutical Research, 1998
- Building population pharmacokineticpharmacodynamic models. I. Models for covariate effectsJournal of Pharmacokinetics and Biopharmaceutics, 1992