Pharmacometric covariate modeling using symbolic regression networks
(2022) The 6th IEEE Conference on Control Technology and Applications p.1099-1104- Abstract
- A central challenge within pharmacometrics is to establish a relation between pharmacological model parameters, such as compartment volumes and diffusion rate constants, and known population covariates, such as age and body mass. There is rich literature dedicated to the learning of functional mappings from the covariates to the model parameters, once a search class of functions has been determined. However, the state-of-the-art selection of the search class itself is ad hoc. We demonstrate how neural network-based symbolic regression can be used to simultaneously find the function form and its parameters. The method is put in relation to the literature on symbolic regression and equation learning. A conceptual demonstration is provided... (More)
- A central challenge within pharmacometrics is to establish a relation between pharmacological model parameters, such as compartment volumes and diffusion rate constants, and known population covariates, such as age and body mass. There is rich literature dedicated to the learning of functional mappings from the covariates to the model parameters, once a search class of functions has been determined. However, the state-of-the-art selection of the search class itself is ad hoc. We demonstrate how neural network-based symbolic regression can be used to simultaneously find the function form and its parameters. The method is put in relation to the literature on symbolic regression and equation learning. A conceptual demonstration is provided through examples, as is a road map to full-scale employment to pharmacological data sets, relevant to closed-loop anesthesia. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/af8160ef-631e-4538-b92b-e7be7e0b9414
- author
- Wahlquist, Ylva LU ; Soltesz, Kristian LU and Morin, Martin LU
- organization
- publishing date
- 2022
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 6th IEEE Conference on Control Technology and Applications
- pages
- 1099 - 1104
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- The 6th IEEE Conference on Control Technology and Applications
- conference location
- Trieste, Italy
- conference dates
- 2022-08-23 - 2022-08-25
- external identifiers
-
- scopus:85144597352
- ISBN
- 978-166547338-5
- DOI
- 10.1109/CCTA49430.2022.9966112
- project
- Learning pharmacometric model structures from data
- language
- English
- LU publication?
- yes
- id
- af8160ef-631e-4538-b92b-e7be7e0b9414
- date added to LUP
- 2022-06-15 11:59:14
- date last changed
- 2023-12-04 10:29:36
@inproceedings{af8160ef-631e-4538-b92b-e7be7e0b9414, abstract = {{A central challenge within pharmacometrics is to establish a relation between pharmacological model parameters, such as compartment volumes and diffusion rate constants, and known population covariates, such as age and body mass. There is rich literature dedicated to the learning of functional mappings from the covariates to the model parameters, once a search class of functions has been determined. However, the state-of-the-art selection of the search class itself is ad hoc. We demonstrate how neural network-based symbolic regression can be used to simultaneously find the function form and its parameters. The method is put in relation to the literature on symbolic regression and equation learning. A conceptual demonstration is provided through examples, as is a road map to full-scale employment to pharmacological data sets, relevant to closed-loop anesthesia.}}, author = {{Wahlquist, Ylva and Soltesz, Kristian and Morin, Martin}}, booktitle = {{6th IEEE Conference on Control Technology and Applications}}, isbn = {{978-166547338-5}}, language = {{eng}}, pages = {{1099--1104}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Pharmacometric covariate modeling using symbolic regression networks}}, url = {{https://lup.lub.lu.se/search/files/119944791/pharmacometric_covariate_modeling.pdf}}, doi = {{10.1109/CCTA49430.2022.9966112}}, year = {{2022}}, }