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

Artificial neural network as a novel method to optimize pharmaceutical formulations

K Takayama1, M Fujikawa, T Nagai

  • 1Department of Pharmaceutics, Hoshi University, Tokyo, Japan. takayama@hoshi.ac.jp

Pharmaceutical Research
|February 9, 1999
PubMed
Summary

This study introduces artificial neural networks (ANNs) for multi-objective pharmaceutical formulation optimization. ANNs improve predictions over traditional response surface methods (RSM), leading to better formulation design.

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

A novel method of drug delivery for fibrinolysis with Ho:YAG laser-induced liquid jet.

Lasers in medical science·2002
Same author

Fiber shaft extension in combination with HI loop ligands augments infectivity for CAR-negative tumor targets but does not enhance hepatotropism in vivo.

Gene therapy·2002
Same author

Molecular genotyping of isolates of Actinobacillus actinomycetemcomitans by pulsed-field gel electrophoresis after separate digestion with Sse8387I and XhoI.

Journal of basic microbiology·2002
Same author

The enhancing effect of nasal absorption of FITC-dextran 4,400 by beta-sitosterol beta-D-glucoside in rabbits.

Journal of controlled release : official journal of the Controlled Release Society·2002
Same author

Release property of progesterone from a mixed-base suppository consisting of Witepsol W35 and Witepsol E85.

Drug development and industrial pharmacy·2002
Same author

Detection of early venous filling in gliomas on MRI: preliminary study by 2D time-resolved dynamic contrast-enhanced MR angiography with echo-sharing technique.

Magnetic resonance imaging·2002

Area of Science:

  • Pharmaceutical Sciences
  • Formulation Development
  • Computational Chemistry

Background:

  • Quantitative pharmaceutical formulation faces challenges in understanding causal factor-response relationships and optimizing multiple, often conflicting, formulation characteristics simultaneously.
  • Traditional Response Surface Methods (RSM) using second-order polynomials have limitations in accurately predicting optimal formulations due to restricted prediction levels.

Purpose of the Study:

  • To introduce and describe the concept of multi-objective simultaneous optimization incorporating artificial neural networks (ANNs) for pharmaceutical formulation design.
  • To demonstrate the effectiveness of ANNs in predicting non-linear relationships between formulation factors and responses.

Main Methods:

  • Review of artificial neural network (ANN) principles for predictive modeling in pharmaceutical research.

Related Experiment Videos

  • Application and comparison of ANN-based optimization with classical Response Surface Methods (RSM).
  • Case study: Optimization of ketoprofen hydrogel ointment formulation.

    • Main Results:

    • Artificial neural networks (ANNs) offer a powerful approach to model complex, non-linear relationships between formulation variables and desired properties.
    • The ANN approach demonstrated superior reliability and accuracy in predicting optimal formulations compared to traditional RSM.
    • Successful optimization of ketoprofen hydrogel ointment using the proposed ANN methodology.

    Conclusions:

    • Artificial neural networks (ANNs) provide a robust and reliable tool for tackling multi-objective simultaneous optimization problems in pharmaceutical formulation.
    • The integration of ANNs enhances the quantitative approach to formulation design, overcoming limitations of conventional methods like RSM.
    • This approach holds significant potential for improving the efficiency and success rate of pharmaceutical product development.