Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Symbolic neural networks for automated covariate modeling in a mixed-effects framework

Sundell, Jesper LU ; Wahlquist, Ylva LU and Soltesz, Kristian LU orcid (2024) 12th IFAC Symposium on Biological and Medical Systems (BMS) In IFAC-PapersOnLine
Abstract
Mixed-effects models are used to describe the inter-patient variability in drugs. Modeling of these variabilities include both fixed and random effects. Fixed effects relate covariates such as age and weight to compartment volumes and clearances, whereas random effects account for unexplained variability. Traditionally, the development of fixed effects models is an inefficient process where covariate relationships are evaluated in a step-wise manner. In this study, we implemented a symbolic neural network (SNN) to automate the development of a fixed effects model and used it to develop a population pharmacokinetic model for propofol. With the SNN, we can find covariate relationships that are traditionally not evaluated. Then, we apply... (More)
Mixed-effects models are used to describe the inter-patient variability in drugs. Modeling of these variabilities include both fixed and random effects. Fixed effects relate covariates such as age and weight to compartment volumes and clearances, whereas random effects account for unexplained variability. Traditionally, the development of fixed effects models is an inefficient process where covariate relationships are evaluated in a step-wise manner. In this study, we implemented a symbolic neural network (SNN) to automate the development of a fixed effects model and used it to develop a population pharmacokinetic model for propofol. With the SNN, we can find covariate relationships that are traditionally not evaluated. Then, we apply random effects and estimate parameters in the standard mixed-effects modeling framework. Our final model shows comparable predictive performance to a published model for propofol, despite having fewer covariates and model parameters. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
in press
subject
in
IFAC-PapersOnLine
publisher
IFAC Secretariat
conference name
12th IFAC Symposium on Biological and Medical Systems (BMS)
conference location
Villingen-Schwenningen, Germany
conference dates
2024-09-11 - 2024-09-13
ISSN
2405-8963
project
Learning pharmacometric model structures from data
language
English
LU publication?
yes
additional info
© 2024.. This work has been accepted to IFAC for publication under a Creative Commons Licence CC-BY-NC-ND
id
28d9cd55-798f-4f21-a111-7bddacb03bad
date added to LUP
2024-04-12 11:50:57
date last changed
2024-04-16 11:16:21
@article{28d9cd55-798f-4f21-a111-7bddacb03bad,
  abstract     = {{Mixed-effects models are used to describe the inter-patient variability in drugs. Modeling of these variabilities include both fixed and random effects. Fixed effects relate covariates such as age and weight to compartment volumes and clearances, whereas random effects account for unexplained variability. Traditionally, the development of fixed effects models is an inefficient process where covariate relationships are evaluated in a step-wise manner. In this study, we implemented a symbolic neural network (SNN) to automate the development of a fixed effects model and used it to develop a population pharmacokinetic model for propofol. With the SNN, we can find covariate relationships that are traditionally not evaluated. Then, we apply random effects and estimate parameters in the standard mixed-effects modeling framework. Our final model shows comparable predictive performance to a published model for propofol, despite having fewer covariates and model parameters.}},
  author       = {{Sundell, Jesper and Wahlquist, Ylva and Soltesz, Kristian}},
  issn         = {{2405-8963}},
  language     = {{eng}},
  publisher    = {{IFAC Secretariat}},
  series       = {{IFAC-PapersOnLine}},
  title        = {{Symbolic neural networks for automated covariate modeling in a mixed-effects framework}},
  url          = {{https://lup.lub.lu.se/search/files/180133628/covariate_model_random_effects.pdf}},
  year         = {{2024}},
}