A genetic algorithm-based, hybrid machine learning approach to model selection

Robert R Bies; Matthew F Muldoon; Bruce G Pollock; Steven Manuck; Gwenn Smith; Mark E Sale

doi:10.1007/s10928-006-9004-6

A genetic algorithm-based, hybrid machine learning approach to model selection

J Pharmacokinet Pharmacodyn. 2006 Apr;33(2):195-221. doi: 10.1007/s10928-006-9004-6. Epub 2006 Mar 28.

Authors

Robert R Bies¹, Matthew F Muldoon, Bruce G Pollock, Steven Manuck, Gwenn Smith, Mark E Sale

Affiliation

¹ Department of Pharmaceutical Sciences and Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA. [email protected]

PMID: 16565924
DOI: 10.1007/s10928-006-9004-6

Abstract

We describe a general and robust method for identification of an optimal non-linear mixed effects model. This includes structural, inter-individual random effects, covariate effects and residual error models using machine learning. This method is based on combinatorial optimization using genetic algorithm.

MeSH terms

Algorithms*
Antidepressive Agents, Second-Generation / administration & dosage
Antidepressive Agents, Second-Generation / pharmacokinetics
Antidepressive Agents, Second-Generation / pharmacology
Artificial Intelligence*
Citalopram / administration & dosage
Citalopram / pharmacokinetics
Citalopram / pharmacology
Computer Simulation
Humans
Infusions, Intravenous
Models, Biological*
Models, Genetic
Software

Substances

Antidepressive Agents, Second-Generation
Citalopram