Artificial Neural Network Based in Vitro-in Vivo Correlations

  • Ajaz S. Hussain
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 423)


In vitro drug dissolution test facilitates design, development, and quality assurance of solid (oral) products. During product development dissolution tests are used to characterize impact of formulation variables on drug release and to optimize formulations to achieve a target drug release profile (assuming the in vitro test is predictive of in vivo drug release). Every manufactured batch must meet pre-set specifications prior to being released for distribution. Certain “minor” post-approval changes in the manufacturing process and/or formulation may be justified by demonstrating equivalent in vitro dissolution profiles1. For certain “major” post-approval changes the FDA may grant requests for waiver of in vivo bioequivalence studies when a sponsor demonstrates acceptable predictive ability of the selected in vitro test (i.e., availability of an validated in vitro to in vivo correlation -IVIVC)2.


Artificial Neural Network Drug Release Root Mean Square Processing Element Slow Release Formulation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    “Draft Guidance for Industry: Modified Release Solid Oral Dosage Forms; Scale-Up and Post Approval Changes: Chemistry, Manufacturing and Controls, In Vitro Dissolution Testing and In Vivo Bioequivalence Documentation”, U. S. Department of Health and Human Services, Food and Drug Administration, Center for Drug Evaluation and Research, July 1996.Google Scholar
  2. 2.
    “Draft Guidance for Industry: Extended Release Solid Oral Dosage Forms; Development, Evaluation and Application of In Vitro/In Vivo Correlations”. U. S. Department of Health and Human Services, Food and Drug Administration, Center for Drug Evaluation and Research, July 1996.Google Scholar
  3. 3.
    Hussain, A. S., et. al. Artificial neural network (ANN) approach for establishing a predictive relationship between in vitro drug release and in vitro serum drug levels. Pharm. Res. 10: S-489 (1996)Google Scholar
  4. 4.
    Piscitelli, D. A., et. al. Investigation of an Level A correlation for diltiazem. Pharm. Res. 10: S-475 (1996).Google Scholar
  5. 5.
    Dowell, J. A.., et. al. Neural network model development for in vitro — in vivo relationships. Pharm. Res. 10:S-450(1996).Google Scholar
  6. 6.
    Robert Hecht-Nielsen. Neurocomputing, Addison-Wesley Publishing Company, Reading, Massachusetts, 1989.Google Scholar
  7. 7.
    Neural Computing: A Technology Handbook for Professional II/Plus and NeuralWorks Explorer. Neural-Ware, Inc., Pittsburgh, PA. (1993).Google Scholar
  8. 8.
    Shadmehr, R. and D’Argenio, D. Z. A neural network for nonlinear Bayesian estimation in drug therapy. Neural Comput. 2: 216–225 (1990).CrossRefGoogle Scholar
  9. 9.
    Hussain, A. S., Yu, X., Johnson, R. D. Application of neural computing to pharmaceutical product development, Pharm. Res. 8, 1248–1252 (1991).Google Scholar
  10. 10.
    Veng-Pedersen, P., Modi, N. B. Neural networks in pharmacodynamic modeling. Is current modeling practice of complex kinetic system at a dead end? J. Pharmacokin. Biopharm., 20, 397–412 (1992).CrossRefGoogle Scholar
  11. 11.
    Hussain, A. S., et. al., Feasibility of developing a neural network for prediction of human pharmacokinetic parameters from animal data. Pharm. Res. 10, 466–469 (1993).PubMedCrossRefGoogle Scholar
  12. 12.
    Erb, R. J. Introduction to backpropagation neural network computations. Pharm. Res. 10, 165–170 (1993).PubMedCrossRefGoogle Scholar
  13. 13.
    Hussain, A. S., Shivanand, P., Johnson, R. D. Application of neural computing in pharmaceutical product development: Computer-Aided formulation design. Drug. Dev. Ind. Pharm.20, 1739–1752 (1994).CrossRefGoogle Scholar
  14. 14.
    Murtoniemi, E. et. al., The advantages by the use of neural networks in modeling the fluidized bed granulation process. Int. J. Pharm. 108, 155–164 (1994).CrossRefGoogle Scholar
  15. 15.
    Brier, M. E., Zurada, J. M., Aronoff, G. R. Neural network predicted gentamicin peak and trough concentrations. Pharm. Res. 12, 406–412, (1995)PubMedCrossRefGoogle Scholar
  16. 16.
    Gobburu, J. V. S., Chen, E. P. Artificial neural networks as a novel approach to integrated pharmacokineticpharmacodynamic analysis. J. Pharm. Sci. 85, 505–510 (1996).PubMedCrossRefGoogle Scholar
  17. 17.
    Kesavan, J. G. And Peck, G. E. Pharmaceutical granulation and tablet formulation using neural networks. Pharm. Develop. And Tech. 1, 391–404 (1996).CrossRefGoogle Scholar
  18. 18.
    Hussain A. S.: Application of artificial neural network to population pharmacokinetic and pharmacodynamic data analysis. In: Pharmacokinetic/Pharmacodynamic Analysis: Accelerating Drug Discovery and Development. IBC Biomedical Library Series, Southborough, MA., J. Schlegel (Ed.), July 1996Google Scholar

Copyright information

© Plenum Press, New York 1997

Authors and Affiliations

  • Ajaz S. Hussain
    • 1
  1. 1.Division of Product Quality Research Office of Testing and Research Center for Drug Evaluation and ResearchFood and Drug AdministrationRockvilleUSA

Personalised recommendations