Search tips
Search criteria 


Logo of aapspharmspringer.comThis journalToc AlertsSubmit OnlineOpen Choice
AAPS PharmSciTech. 2004 March; 5(1): 11.
Published online 2009 November 27. doi:  10.1208/pt050104
PMCID: PMC2784849

Artificial neural network as an alternative to multiple regression analysis in optimizing formulation parmaeters of cytarabine liposomes


The objective of the study was to optimize the formulation parameters of cytarabine liposomes by using artificial neural networks (ANN) and multiple regression analysis using 33 factorial design (FD). As model formulations, 27 formulations were prepared. The formulation variables, drug (cytarabine)/lipid (phosphatidyl choline [PC] and cholesterol [Chol]) molar ratio (X1, PC/Chol in percentage ratio of total lipids (X2), and the volume of hydration medium, (X3) were selected as the independent variables; and the percentage drug entrapment (PDE) was selected as the dependent variable. A set of causal factors was used as tutorial data for ANN and fed into a computer. The optimization was performed by minimizing the generalized distance between the predicted values of each response and the optimized one that was obtained individually. In case of 33 factorial design, a second-order full-model polynomial equation and a reduced model were established by subjecting the transformed values of independent variables to multiple regression analysis, and contour plots were drawn using the equation. The optimization methods developed by both ANN and FD were validated by preparing another 5 liposomal formulations. The predetermined PDE and the experimental data were compared with predicted data by pairedt test, no statistically significant difference was observed. ANN showed less error compared with multiple regression analysis. These findings demonstrate that ANN provides more accurate prediction and is quite useful in the optimization of pharmaceutical formulations when compared with the multiple regression analysis method.

KeyWords: artificial neural network, contour plots, cytarabine liposomes, multiple regression, factorial design

Full Text

The Full Text of this article is available as a PDF (788K).

Selected References

These references are in PubMed. This may not be the complete list of references from this article.
1. Levison KK, Takayama K, Isowa K, Okaba K, Nagai T. Formulation optimization of indomethacin gels containing a combination of three kinds of cyclic monoterpenes as percutaneous penetration enhancers. J Pharm Sci. 1994;83:1367–1372. doi: 10.1002/jps.2600830932. [PubMed] [Cross Ref]
2. Shirakura O, Yamada M, Hashimoto M, Ishimaru S, Takayama K, Nagai T. Particle size design using computer optimization technique. Drug Dev Ind Pharm. 1991;17:471–483. doi: 10.3109/03639049109044257. [Cross Ref]
3. Takayama K, Morva A, Fujikawa M, Hattori Y, Obata Y, Nagai T. Fomula optimization of theophylline controlled-release tablet based on artificial neural networks. J Control Release. 2000;68:175–186. doi: 10.1016/S0168-3659(00)00248-0. [PubMed] [Cross Ref]
4. Takahara J, Takayama K, Nagai T. Multi-objective simultaneous optimization technique based on an artificial neural network in sustained release formulations. J Control Release. 1997;49:11–20. doi: 10.1016/S0168-3659(97)00030-8. [Cross Ref]
5. Takayama K, Fujikawa M, Nagai T. Artificial neural network as a novel method to optimize pharmaceutical formulations. Pharm Res. 1991;16:1–6. doi: 10.1023/A:1011986823850. [PubMed] [Cross Ref]
6. Takahara J, Takayama K, Isowa K, Nagai T. 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. 1997;158:203–210. doi: 10.1016/S0378-5173(97)00260-3. [Cross Ref]
7. Haykin Simon. Neural Networks: A Comprehensive Foundation. 2nd ed. Englewood Cliffs, NJ: Prentice-Hall; 1999. pp. 156–254.
8. Achanta AS, Kowalski IG, Rhodes CT. Artificial neural networks: implications for pharmaceutical sciences. Drug Dev Ind Pharm. 1995;21:119–155. doi: 10.3109/03639049509048099. [Cross Ref]
9. Baughman DR, Liu YA. Neural Networks in Bioprocessing and Chemical Engineering. New York, NY: Academic Press; 1995.
10. Tricot G, De Bock R, Dekker AW. Low dose cytosine arabinoside (Ara C) in myelodysplastic syndromes. Br J Haematol. 1984;58:231–240. doi: 10.1111/j.1365-2141.1984.tb06081.x. [PubMed] [Cross Ref]
11. Roberts JD, Ershlew WB, Tindle BH. Low-dose cytosine arabinoside in the treatment of myelodysplastic syndromes and acute myelogenous leukemia. Cancer. 1985;56:1001–1005. doi: 10.1002/1097-0142(19850901)56:5<1001::AID-CNCR2820560504>3.0.CO;2-P. [PubMed] [Cross Ref]
12. Winter JN, Variakojis D, Gaynor ER. Low-dose cytosine arabinoside (Ara-C) therapy in myelodysplastic syndromes and acute leukemia. J Cancer. 1985;56:443–449. doi: 10.1002/1097-0142(19850801)56:3<443::AID-CNCR2820560305>3.0.CO;2-Q. [PubMed] [Cross Ref]
13. Allen TM, Mehra T, Hansen C, Chin YC. Stealth liposomes: an improved sustained release system for 1-ß-D-arabinofuranosylcytosine. Cancer Res. 1992;52(9):2431–2439. [PubMed]
14. Zou Y, Ling YH, Van NT, Priebe W, Perz Solar R. Antitumor or activity of free and liposome-entrapped annamycin, a lipophilic antracycline antibiotic with non-cross-resistance properties. Cancer Res. 1994;54(6):1479–1484. [PubMed]
15. Cochran WG, Cox GM. Experimental Designs. 2nd ed. New York, NY: John Wiley & Sons; 1992.
16. Murtonemi E, Ylinuusi J, Kinnunen P, Merkku P, Leiviska K. The advantages by the use of the neural networks in modeling the fluidized bed granulation process. Int J Pharm. 1994;108:155–164. doi: 10.1016/0378-5173(94)90327-1. [Cross Ref]
17. Hussian AS. Application of neural computing in pharmaceutical product development. Pharm Res. 1991;8(10):1248–1252. doi: 10.1023/A:1015843527138. [PubMed] [Cross Ref]
18. Ebube NK, McCall T, Chen Y, Meyer MC. Relating formulation variables to in vitro dissolution using an artificial neural network. Pharm Dev Technol. 1997;2(3):225–232. doi: 10.3109/10837459709031442. [PubMed] [Cross Ref]
19. New RRC. Liposomes: A Practical Approach. Oxford, UK: Oxford University Press; 1990. Preparation of liposomes; pp. 33–104.
20. Armstrong NA, James KC. Pharmaceutical Experimental Design and Interpretation. Bristol, PA: Taylor and Francis Publishers; 2004. pp. 131–192.
21. Erb RJ. Introduction to backpropagation neural network computation. Pharm Res. 1993;10:165–170. doi: 10.1023/A:1018966222807. [PubMed] [Cross Ref]
22. Nielsen RH. Kolmogrov's mapping neural network existence theorem. In: Proceedings of the Second IEEE International Conference on Neural Networks; June 21–24, San Diego, CA. 1987: 11–14.
23. Akhnazarova S, Kafarov V. Experiment Optimization in Chemistry and Chemical Engineering. Moscow, Russian: Mir Publications; 1982.
24. Adinarayana K, Ellaiah P. Response surface optimization of the critical medium components for the production of alkaline protease by a newly isolatedBacillus sp. J Pharm Pharm Sci. 2002;5(3):281–287. [PubMed]
25. Box GEP, Wilson KB. On the experimental attainment of optimum conditions. J Roy Stat Soc. “Ser C Appl Stat” 1951;13:1–45.
26. Box GEP, Hunter WG, Hunter JS. Statistics for Expeirmenters: An Introduction to Design, Data Analysis, and Model Building. New York, NY: John Wiley & Sons; 1978.
27. Yee L, Blanch HW. Defined media optimization for the growth of recombinant.Escherichia colix90. Biotechnol Bioeng. 1993;41:221–227. doi: 10.1002/bit.260410208. [PubMed] [Cross Ref]
28. Jha BK, Thambe SS, Kulkarni BD. Estimating diffusion coenficients of a micellar system using an artificial neural network. J Colloid Interface Sci. 1995;170:392–398. doi: 10.1006/jcis.1995.1117. [Cross Ref]

Articles from AAPS PharmSciTech are provided here courtesy of American Association of Pharmaceutical Scientists