Preparation and Optimization of N-Acetylcysteine Nanosuspension through Nanoprecipitation: An Artificial Neural Networks Study

Purpose

Nanosuspensions, as a promising strategy to improve the solubility and bioavailability of poorly water soluble drugs, have been widely investigated in recent years. However, no comprehensive work so far has detailed the effect of independent processing/formulation parameters on the quality of the prepared nanosuspension.

Methods

In the present study, the relations between solvent flow rate, stirring rate of antisolvent and surfactant concentration (i.e., inputs) on size, and polydispersity index (PDI) (i.e., outputs) of an N-acetylcysteine nanosuspension were investigated using artificial neural networks (ANNs).

Results and conclusion

The response surfaces, generated as 3D graphs after ANNs modeling, demonstrated that all the three factors have a reverse effect on size and PDI. The dominant factor appeared to be the concentration of surfactant. Overall, it was found that the optimum formulation (i.e., minimum size and PDI value) is obtained at high values of surfactant concentration, solvent flow rate, and stirring rate (i.e., >0.9 mg/ml and 120 ml/h and 500 rpm, respectively).