Design porosity osmotic tablet for delivering low and pH-dependent soluble drug using an artificial neural network

In this paper formulation of porosity osmotic tablet containing isradipine (model drug) as a low and pH dependent solubility was optimized based on the simultaneous optimization technique in which an artificial neural network (ANN) was incorporated. Nonlinear relationships between the causal factors and the response variables were represented well with the response surface predicted by ANN. Three causal factors, i.e., drug, osmotic pressure promoting agent rate (Lactose: Fructose), PEG400 content in coating solution and coating weight, were evaluated based on their effects on drug release rate. In vitro dissolution profile time profiles at four different sampling times (1, 12, 20 and 24h) were chosen as output variables. Commercially available STATISTICA 7 (Stat soft, USA) was used throughout the study. The optimize values for the factors X1-X3 were 1.25:0.75, 22% and 2.5% respectively. Calculated difference (f1 = 11.19) and similarity (f2 = 70.07) factors indicate that there is no difference between predicted and experimental observed drug release profile. Artificial neural network technique can be particularly suitable in the pharmaceutical technology of controlled release dosage forms where systems are complex and nonlinear relationships between independent and dependent variables often exist.