Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

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

Robert R Bies1, Matthew F Muldoon, Bruce G Pollock

  • 1Department of Pharmaceutical Sciences and Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA. rrb47@pitt.edu

Journal of Pharmacokinetics and Pharmacodynamics
|March 28, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Amygdala and hippocampal volumes as neural correlates of resilience and loneliness in older adults.

Neurobiology of aging·2026
Same author

Impact of Transcranial Direct Current Stimulation-Induced Electric Fields on Slowing Cognitive Decline in Older Adults With Mild Cognitive Impairment or Remitted Major Depressive Disorder: An Analysis of the PACt-MD Randomized Clinical Trial.

Biological psychiatry·2026
Same author

Angiogenesis markers and cognitive response in a randomized trial of cognitive remediation plus transcranial direct current stimulation in older adults at risk of dementia.

Journal of Alzheimer's disease : JAD·2026
Same author

Brain Structures and Cognitive Decline: Moderation Analysis of the PACt-MD Randomized Clinical Trial of Brain Stimulation Plus Cognitive Remediation in Older Adults With Remitted Depression or Mild Cognitive Impairment.

The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry·2026
Same author

Eight-session manualized cognitive behavioral therapy for anxiety and depression symptoms in perimenopause and postmenopause: a pilot study.

Menopause (New York, N.Y.)·2026
Same author

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same journal

Optimizing Subcutaneous Antibody Dosing Regimens Through Operating Space Maps: rHuPH20 Case Study.

Journal of pharmacokinetics and pharmacodynamics·2026
Same journal

Mechanistic modeling of FcRn-dependent IgG drug interactions: Clinical applications and dosing implications.

Journal of pharmacokinetics and pharmacodynamics·2026
Same journal

Comparing heavy-tailed residual error models for outlier handling in population PK modeling.

Journal of pharmacokinetics and pharmacodynamics·2026
Same journal

Personalized prophylactic therapy optimization in hemophilia A using a hybrid PK-PD-TTE model and deep RL.

Journal of pharmacokinetics and pharmacodynamics·2026
Same journal

Pediatric oral cavity physiologically based pharmacokinetic model to predict pharmacokinetics of mucoadhesive atropine gel to treat sialorrhea.

Journal of pharmacokinetics and pharmacodynamics·2026
Same journal

Exposure-safety analyses of talazoparib in combination with enzalutamide in patients with metastatic castration-resistant prostate cancer (mCRPC) in the TALAPRO-2 trial.

Journal of pharmacokinetics and pharmacodynamics·2026
See all related articles

This study introduces a machine learning approach to find the best non-linear mixed effects model, optimizing its structure and parameters. The method uses a genetic algorithm for robust and efficient model identification.

Area of Science:

  • Pharmacometrics and Systems Pharmacology
  • Computational Biology
  • Statistical Modeling

Background:

  • Non-linear mixed effects (NLME) models are crucial for analyzing complex biological data, such as drug concentration-time profiles.
  • Identifying the optimal NLME model structure, including random effects and covariate relationships, is challenging and often relies on manual or heuristic approaches.
  • Existing methods may lack robustness or efficiency in exploring the vast model space.

Purpose of the Study:

  • To present a general and robust computational method for the automated identification of optimal non-linear mixed effects models.
  • To leverage machine learning, specifically genetic algorithms, for efficient exploration and selection of complex model structures.
  • To optimize all key components of an NLME model: structural, random effects, covariate, and residual error models.

Related Experiment Videos

Main Methods:

  • A machine learning-based approach employing combinatorial optimization through a genetic algorithm.
  • Systematic evaluation and selection of model structures based on predefined criteria.
  • Integration of structural model identification, random effects, covariate, and residual error model selection within a single framework.

Main Results:

  • Demonstration of a general and robust method applicable to various NLME modeling scenarios.
  • Successful identification of optimal model components, leading to improved model performance.
  • The genetic algorithm efficiently navigates the complex model space to find optimal configurations.

Conclusions:

  • The proposed genetic algorithm-based method provides a powerful and automated tool for optimal non-linear mixed effects model identification.
  • This approach enhances the efficiency and robustness of model building in pharmacometrics and related fields.
  • Automated model selection can accelerate research by reducing the time and effort required for complex statistical modeling.