Uncovering Population PK Covariates from VAE-Generated Latent Spaces

TL;DR

This paper introduces a novel data-driven framework combining Variational Autoencoders and LASSO regression to identify key covariates influencing drug pharmacokinetics from high-dimensional data, enhancing personalized medicine.

Contribution

It presents a scalable, interpretable, and model-free approach that effectively uncovers clinically relevant covariates from simulated PK profiles, outperforming traditional methods.

Findings

VAE achieves 2.26% MAPE in PK signal reconstruction.

LASSO identifies key covariates like SNP, age, albumin, hemoglobin.

Method discards non-informative features effectively.

Abstract

Population pharmacokinetic (PopPK) modelling is a fundamental tool for understanding drug behaviour across diverse patient populations and enabling personalized dosing strategies to improve therapeutic outcomes. A key challenge in PopPK analysis lies in identifying and modelling covariates that influence drug absorption, as these relationships are often complex and nonlinear. Traditional methods may fail to capture hidden patterns within the data. In this study, we propose a data-driven, model-free framework that integrates Variational Autoencoders (VAEs) deep learning model and LASSO regression to uncover key covariates from simulated tacrolimus pharmacokinetic (PK) profiles. The VAE compresses high-dimensional PK signals into a structured latent space, achieving accurate reconstruction with a mean absolute percentage error (MAPE) of 2.26%. LASSO regression is then applied to map patient-specific covariates to the latent space, enabling sparse feature selection through L1 regularization. This approach consistently identifies clinically relevant covariates for tacrolimus including SNP, age, albumin, and hemoglobin which are retained across the tested regularization strength levels, while effectively discarding non-informative features. The proposed VAE-LASSO methodology offers a scalable, interpretable, and fully data-driven solution for covariate selection, with promising applications in drug development and precision pharmacotherapy.