Neural Expert System for Pharmaceutical Formulation Development — Focus on Solid Dispersions
Neural network-based expert system was created for improvement of pharmaceutical formulation development process. The knowledge database for this system was created from original, experimental data as well as from literature data. Different models for soluble and poorly soluble drugs were trained and tested. Best results were found when specific, pharmaceutical criterions were used to split base dataset in order to create more specialized neural models predicting behavior of some, well defined class of excipients. ANN function as a PharmCAD system (Pharmaceutical Computer Aided Design) was confirmed.
KeywordsTraining Dataset Solid Dispersion Physical Mixture Ethyl Cellulose Soluble Drug
Unable to display preview. Download preview PDF.
- 1.Bilski J (2000) The backropagation learning with logarithmic transfer function. In: Rutkowski L, Tadeusiewicz R, (eds) Proceedings of the 51s Conference Neural Networks and Soft Computing pp. 71–76Google Scholar
- 2.Duch W, Korbicz J, Rutkowski T, Tadeusiewicz R (eds) Neural Networks (2000). In: Nalgcz M (ed). Biocybernetics and Biomedical Engineering. Vol. 6. Academic Publishing Flouse EXIT, WarsawGoogle Scholar
- 3.Kier LB, Hall LH, Murray WJ (1976) Molecular Connectivity [I: Relationship to Water Sol ubiblity and Boiling Point, J. Pharm. Sci. 65Google Scholar
- 4.Mendyk A, Jachowicz R (2000) A simple approach to neural optimisation of pharmaceutical dosage form. In: Rutkowski L, Tadeusiewicz R, (eds) Proceedings of the 5th Conference Neural Networks and Soft Computing pp. 562–567Google Scholar
- 5.Osowski S (1996) Neural Networks in the Algorithmic Approach, WNT, WarsawGoogle Scholar