Pharmaceutical Research

, Volume 16, Issue 1, pp 1–6 | Cite as

Artificial Neural Network as a Novel Method to Optimize Pharmaceutical Formulations

  • Kozo TakayamaEmail author
  • Mikito Fujikawa
  • Tsuneji Nagai


One of the difficulties in the quantitative approach to designing pharmaceutical formulations is the difficulty in understanding the relationship between causal factors and individual pharmaceutical responses. Another difficulty is desirable formulation for one property is not always desirable for the other characteristics. This is called a multi-objective simultaneous optimization problem. A response surface method (RSM) has proven to be a useful approach for selecting pharmaceutical formulations. However, prediction of pharmaceutical responses based on the second-order polynomial equation commonly used in RSM, is often limited to low levels, resulting in poor estimations of optimal formulations. The aim of this review is to describe the basic concept of the multi-objective simultaneous optimization technique in which an artificial neural network (ANN) is incorporated. ANNs are being increasingly used in pharmaceutical research to predict the non-linear relationship between causal factors and response variables. The usefulness and reliability of this ANN approach is demonstrated by the optimization for ketoprofen hydrogel ointment as a typical numerical example, in comparison with the results obtained with a classical RSM approach.

artificial neural networks response surface method multi-objective optimization polynomial equation pharmaceutical formulation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A. I. Khuri and J. A. Cornel. Response Surface, Design and Analysis. Dekker, New York, 1987.Google Scholar
  2. 2.
    D. E. Fonner, Jr., J. B. Buck, and G. S. Banker. Mathematical optimization techniques in drug product design and process analysis. J. Pharm. Sci. 59:1587–1596 (1970).Google Scholar
  3. 3.
    J. B. Schwartz, J. R. Flamholz, and R. H. Press. Computer optimization of pharmaceutical formulations I: General procedure. J. Pharm. Sci. 62:1165–1170 (1973).Google Scholar
  4. 4.
    K. Takayama, H. Imaizumi, N. Nambu, and T. Nagai. Mathematical optimization of formulation of indomethacin/polyvinylpolypyrrolidone/methyl cellulose solid dispersions by the sequential unconstrained minimization technique. Chem. Pharm. Bull. 33:292–300 (1985).Google Scholar
  5. 5.
    K. Takayama and T. Nagai. Novel computer optimization methodology for pharmaceutical formulations investigated by using sustained-release granules of indomethacin. Chem. Pharm. Bull. 37:160–167 (1989).Google Scholar
  6. 6.
    K. Takayama, H. Okabe, Y. Obata, and T. Nagai, Formulation design of indomethacin gel ointment containing d-limonene using computer optimization methodology. Int. J. Pharm. 61:225–234 (1990).Google Scholar
  7. 7.
    K. Takayama and T. Nagai. Simultaneous optimization for several characteristics concerning percutaneous absorption and skin damage of ketoprofen hydrogels containing d-limonene. Int. J. Pharm. 74:115–126 (1991).Google Scholar
  8. 8.
    M. Hirata, K. Takayama, and T. Nagai. Formulation optimization of sustained-release tablet of chlorpheniramine maleate by means of extreme vertices design and simultaneous optimization technique. Chem. Pharm. Bull. 40:741–746 (1992).Google Scholar
  9. 9.
    S. Ogawa, T. Kamijima, Y. Miyamoto, M. Miyajima, H. Sato, K. Takayama, and T. Nagai. A new attempt to solve the scale-up problem for granulation using response surface methodology. J. Pharm. Sci. 83:439–443 (1994).Google Scholar
  10. 10.
    K. K. Levison, K. Takayama, K. Isowa, K. Okabe, and T. Nagai. Formulation optimization of indomethacin gels containing a combination of three kinds of cyclic monoterpenes as percutaneous penetration enhancers. J. Pharm. Sci. 83:1367–1372 (1994).Google Scholar
  11. 11.
    J. Takahara, K. Takayama, and T. Nagai, Multi-objective simultaneous optimization based on artificial neural network in sustained release formulations. J. Contr. Rel. 49:11–20 (1997).Google Scholar
  12. 12.
    J. Takahara, K. Takayama, K. Isowa, and T. Nagai. Multi-objective simultaneous optimization based on artificial neural network in a ketoprofen hydrogel formula containing O-ethylmenthol as a percutaneous absorption enhancer. Int. J. Pharm. 158:203–210 (1997).Google Scholar
  13. 13.
    A. S. Achanta, J. G. Kowalski, and C. T. Rhodes. Artificial neural networks: Implications for pharmaceutical sciences. Drug Dev. Ind. Pharm. 21:119–155 (1995).Google Scholar
  14. 14.
    A. S. Hussain, X. Yu, and R. D. Johnson. Application of neural computing in pharmaceutical product development. Pharm. Res. 8:1248–1252 (1991).Google Scholar
  15. 15.
    B. K. Jha, S. S. Tambe, and B. D. Kulkarni. Estimating diffusion coefficients of a micellar system using an artificial neural network. J. Coll. I. Sci. 170:392–398 (1995).Google Scholar
  16. 16.
    J. N. Weinstein, K. W. Kohn, M. R. Grever, V. N. Viswanadhan, L. V. Rubinstein, A. P. Monks, D. A. Scudiero, L. Welch, A. D. Koutsoukos, A. J. Chiausa, and K. D. Paull. Neural computing in cancer drug development: Predicting mechanism of action. Science 258:447–451 (1992).Google Scholar
  17. 17.
    A. S. Hussain, R. D. Johnson, N. Vachhrajani, and W. A. Ritschel. Feasibility of developing a neural network for prediction of human pharmacokinetic parameters from animal data. Pharm. Res. 10:466–469 (1993).Google Scholar
  18. 18.
    E. Brier, J. M. Zurada, and G. R. Aronoff. Neural network predicted peak and trough gentamicin concentrations. Pharm. Res. 12:406–412 (1995).Google Scholar
  19. 19.
    J. V. S. Gobburu and W. H. Shelver. Quantitative structure-pharmacokinetic relationship (QSPR) of beta blockers derived using neural networks. J. Pharm. Sci. 84:862–865 (1995).Google Scholar
  20. 20.
    B. P. Smith and M. E. Brier. Statistical approach to neural network model building for gentamicin peak predictions, J. Pharm. Sci. 85:65–69 (1996).Google Scholar
  21. 21.
    K. Takayama, J. Takahara, M. Fujikawa, and T. Nagai. Formula optimization based on artificial neural networks in transdermal drug delivery. J. Contr. Rel. submitted.Google Scholar
  22. 22.
    J. L. McClelland and D. E. Rumelhart. Explorations in parallel distributed processing, MIT Press, Cambridge, MA, 1988.Google Scholar
  23. 23.
    R. J. Erb. Introduction to backpropagation neural network computation. Pharm. Res. 10:165–170 (1993).Google Scholar
  24. 24.
    H. Murase, S. Koyama, N. Honami, and T. Kuwabara. Kalman filter neuron training. Bull. Univ. Osaka Pref., Ser. B. 43:91–101 (1991).Google Scholar
  25. 25.
    T. B. Blank and S. D. Brown. Adaptive, global, extended Kalman filters for training feedforward neural networks. J. Chemom., 8:391–407 (1994).Google Scholar
  26. 26.
    R. Simutis, I. Havlik, M. Dors, and A. Luebbert. Training of artificial networks extended by linear dynamic subsystems. Process Control Qual., 4:211–220 (1993).Google Scholar
  27. 27.
    R. P. Lippman. An introduction to computing with neural nets. IEEE ASSP Mag. April: 4–22 (1987).Google Scholar
  28. 28.
    D. G. Bounds and P. J. Lloyd. A multilayer perceptron network for the diagnosis of low back pain. In Proceedings of Second IEEE International Conference on Neural Networks, San Diego, CA, July 24–27, 1988, pp. II-481–II-489.Google Scholar
  29. 29.
    G. Cybenko. Approximations by superpositions of a sigmoidal function. Math. Control Signals Syst. 2:303–314 (1989).Google Scholar
  30. 30.
    W. C. Carpenter and M. E. Hoffman. Understanding neural network approximations and polynomial approximations helps neural network performance. AI Expert March: 31–33 (1995).Google Scholar
  31. 31.
    M. Fujikawa, K. Takayama, and T. Nagai. Application of partitioned artificial neural networks to optimize pharmaceutical formulations. In Abstract of Conference on Challenges for Drug Delivery and Pharmaceutical Technology [DDPT], Tokyo, Japan, June 9–11, 1998, p. 133.Google Scholar
  32. 32.
    G. Derringer and R. Suich. Simultaneous optimization of several response variables. J. Quality Tech. 12:214–219 (1980).Google Scholar
  33. 33.
    A. D. McLeod, F. C. Lam, P. K. Gupta, and C. T. Hung. Optimized synthesis of polyglutaraldehyde nanoparticles using central composite design. J. Pharm. Sci. 77:704–710 (1988).Google Scholar
  34. 34.
    B. G. Müller, H. Leuenberger, and T. Kissel. Albumin nanospheres as carriers for passive drug targeting: An optimized manufacturing technique. Pharm. Res. 13:32–37 (1996).Google Scholar
  35. 35.
    Y. M. Wang, H. Sato, I. Adachi, and I. Horikoshi. Optimization of the formulation design of chitosan microspheres containing cisplatin. J. Pharm. Sci. 85:1204–1210 (1996).Google Scholar
  36. 36.
    A. I. Khuri and M. Conlon. Simultaneous optimization of multiple responses predicted by polynomial regression functions. Technometrics 23:363–375 (1981).Google Scholar
  37. 37.
    J. Negishi, K. Takayama, K. Higashiyama, Y. Chida, K. Isowa, and T. Nagai. Promoting effect of O-alkylmenthol and O-acylmenthol derivatives on the percutaneous absorption of ketoprofen in rats. S. T. P. Pharma Sci. 5:156–161 (1995).Google Scholar
  38. 38.
    Y. Nakamura, K. Takayama, K. Higashiyama, T. Suzuki, and T. Nagai. Promoting effect of O-ethylmenthol on the percutaneous absorption of ketoprofen. Int. J. Pharm. 145:29–36 (1996).Google Scholar

Copyright information

© Plenum Publishing Corporation 1999

Authors and Affiliations

  1. 1.Department of PharmaceuticsHoshi UniversityShina-gawa-ku, TokyoJapan

Personalised recommendations