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

Neural network based optimization of drug formulations.

Kozo Takayama1, Mikito Fujikawa, Yasuko Obata

  • 1Department of Pharmaceutics, Hoshi University, Ebara 2-4-41, Shinagawa, Tokyo 142-8501, Japan. takayama@hoshi.ac.jp

Advanced Drug Delivery Reviews
|September 5, 2003
PubMed
Summary

Optimizing pharmaceutical formulations requires balancing multiple factors. Artificial neural networks (ANNs) offer superior prediction for complex relationships, improving the design of effective and stable drug products.

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

Developing and validating patient safety sessions in Japanese medical education: a modified Delphi study.

International journal of medical education·2026
Same author

The history of Nagasaki, the Japanese birthplace of Western medicine and its education.

Advances in health sciences education : theory and practice·2026
Same author

Effect of Surfactants on Oral Delivery of Nanoemulsions Containing Fexofenadine, a Substrate for P-glycoprotein.

AAPS PharmSciTech·2025
Same author

Exploring Japanese Medical Students' mental distress and wellbeing challenges.

Social science & medicine (1982)·2025
Same author

Foreword.

Chemical & pharmaceutical bulletin·2025
Same author

Effect of Alcohols on the Skin Permeation of Various Drugs.

Chemical & pharmaceutical bulletin·2025

Area of Science:

  • Pharmaceutical Sciences
  • Computational Chemistry
  • Biotechnology

Background:

  • Pharmaceutical formulation involves optimizing multiple factors (effectiveness, stability, safety).
  • Traditional Response Surface Methods (RSM) often provide limited prediction accuracy for optimal formulations.
  • Expertise is crucial but insufficient for complex multi-objective optimization challenges.

Purpose of the Study:

  • To introduce a multi-objective simultaneous optimization technique incorporating artificial neural networks (ANNs).
  • To address the limitations of conventional RSM in predicting optimal pharmaceutical formulations.
  • To highlight the advantages of ANNs in handling complex, nonlinear relationships in drug development.

Main Methods:

  • Review of multi-objective optimization principles.

Related Experiment Videos

  • Integration of artificial neural networks (ANNs) for predictive modeling.
  • Application of ANNs to model nonlinear relationships between formulation factors and responses.

    • Main Results:

    • ANNs demonstrate superior predictive capabilities compared to traditional polynomial models in RSM.
    • The ANN approach effectively handles complex, nonlinear relationships in pharmaceutical response variables.
    • Demonstrated improved optimization outcomes for typical numerical examples.

    Conclusions:

    • Artificial neural networks (ANNs) provide a powerful tool for multi-objective optimization in pharmaceutical formulation.
    • ANNs enhance the accuracy and efficiency of predicting optimal drug formulations.
    • This approach can lead to the development of more effective, stable, and safer pharmaceutical products.