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

Robert Bies, Matthew F. Muldoon, Bruce G. Pollock, Steven Manuck, Gwenn Smith, Mark E. Sale

Research output: Contribution to journalArticle

53 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)195-221
Number of pages27
JournalJournal of Pharmacokinetics and Pharmacodynamics
Volume33
Issue number2
DOIs
StatePublished - Apr 2006
Externally publishedYes

Fingerprint

Learning systems
Genetic algorithms
Combinatorial optimization
Identification (control systems)
Machine Learning

Keywords

  • Automated machine learning
  • Covariate selection
  • Genetic algorithm
  • Model building
  • Nonlinear mixed effects modeling
  • Population paramacokinetics

ASJC Scopus subject areas

  • Pharmacology
  • Catalysis

Cite this

A genetic algorithm-based, hybrid machine learning approach to model selection. / Bies, Robert; Muldoon, Matthew F.; Pollock, Bruce G.; Manuck, Steven; Smith, Gwenn; Sale, Mark E.

In: Journal of Pharmacokinetics and Pharmacodynamics, Vol. 33, No. 2, 04.2006, p. 195-221.

Research output: Contribution to journalArticle

Bies, Robert ; Muldoon, Matthew F. ; Pollock, Bruce G. ; Manuck, Steven ; Smith, Gwenn ; Sale, Mark E. / A genetic algorithm-based, hybrid machine learning approach to model selection. In: Journal of Pharmacokinetics and Pharmacodynamics. 2006 ; Vol. 33, No. 2. pp. 195-221.
@article{2aad9180d197434dacb6b70ed9dceec9,
title = "A genetic algorithm-based, hybrid machine learning approach to model selection",
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.",
keywords = "Automated machine learning, Covariate selection, Genetic algorithm, Model building, Nonlinear mixed effects modeling, Population paramacokinetics",
author = "Robert Bies and Muldoon, {Matthew F.} and Pollock, {Bruce G.} and Steven Manuck and Gwenn Smith and Sale, {Mark E.}",
year = "2006",
month = "4",
doi = "10.1007/s10928-006-9004-6",
language = "English (US)",
volume = "33",
pages = "195--221",
journal = "Journal of Pharmacokinetics and Pharmacodynamics",
issn = "1567-567X",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - A genetic algorithm-based, hybrid machine learning approach to model selection

AU - Bies, Robert

AU - Muldoon, Matthew F.

AU - Pollock, Bruce G.

AU - Manuck, Steven

AU - Smith, Gwenn

AU - Sale, Mark E.

PY - 2006/4

Y1 - 2006/4

N2 - 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.

AB - 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.

KW - Automated machine learning

KW - Covariate selection

KW - Genetic algorithm

KW - Model building

KW - Nonlinear mixed effects modeling

KW - Population paramacokinetics

UR - http://www.scopus.com/inward/record.url?scp=33645806542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645806542&partnerID=8YFLogxK

U2 - 10.1007/s10928-006-9004-6

DO - 10.1007/s10928-006-9004-6

M3 - Article

C2 - 16565924

AN - SCOPUS:33645806542

VL - 33

SP - 195

EP - 221

JO - Journal of Pharmacokinetics and Pharmacodynamics

JF - Journal of Pharmacokinetics and Pharmacodynamics

SN - 1567-567X

IS - 2

ER -