20-27
ARTIFICIAL NEURAL NETWORK AS TOOL FOR QUALITY BY DESIGN IN FORMULATION DEVELOPMENT OF SOLID DISPERSION OF FENOFIBRATE
Authors: Patel TB*, Patel LD, Patel TR, Suhagia BN

Number of views: 556
Optimization techniques are abundant in pharmaceutical industry. In general, all the required information should be obtained from as few experiments as possible. Conventional techniques such as response surface models or simplex optimization are often used. With the advent of the computer in the laboratory, a new class of optimization problems arose which could not be tackled with the standard methodologies. For these search type problems, new strategies such as simulated annealing (SA), genetic algorithms (GA) and artificial neural network are applied. Artificial neural network (ANN) is now become more efficient technique for the optimization of pharmaceutical formulation compared with the Multiple Linear Regression Analysis (MLRA). In the present
investigation Self Organizing Featured Maps (SOFM) tool of ANN was implicated for the optimization of formulation of solid dispersion for fenofibrate. Solid dispersion was prepared using 32 full factorial design and the results obtained were evaluated using ANN for the optimization purpose. Solid dispersion was prepared using Poloxamer 407 as carrier and Lyophilization methods as method of preparation. Amount of Poloxamer 407 (X1) and lyophilization temperature (X2) was selected as independent variable, angle of repose and T90% was selected as dependent variables.Results of angle of repose and T90% obtained by factorial analysis was choose as set of ANN training data and results of check point analysis for angle of repose and T90% was choose as a
set of test data for ANN. Both sets of data were trained using SOFM tool for ANN training using Software NEUROSOLUTION 6.31. Data was trained for satisfactory results.