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

被引：76

作者：

Bies, RR ^{[1
]}

Muldoon, MF

Pollock, BG

Manuck, S

Smith, G

Sale, ME

机构：

[1] Univ Pittsburgh, Dept Pharmaceut Sci & Psychiat, Pittsburgh, PA 15260 USA

[2] Univ Pittsburgh, Ctr Clin Pharmacol, Pittsburgh, PA USA

[3] Univ Toronto, Rotman Res Inst, Ctr Addict & Mental Hlth, Toronto, ON, Canada

[4] Univ Pittsburgh, Dept Psychol, Pittsburgh, PA 15260 USA

[5] Zucker Hillside Hosp, Albert Einstein Coll Med, Glen Oaks, NY USA

[6] Next Level Solut, Raleigh, NC USA

来源：

JOURNAL OF PHARMACOKINETICS AND PHARMACODYNAMICS | 2006年 / 33卷 / 02期

关键词：

nonlinear mixed effects modeling; covariate selection; automated machine learning; genetic algorithm; population paramacokinetics; model building;

D O I：

10.1007/s10928-006-9004-6

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

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.

引用

页码：195 / 221

页数：27