Prediction of kinetics of doxorubicin release from sulfopropyl dextran ion-exchange microspheres using artificial neural networks

The purpose of this work was to develop artificial neural networks (ANN) models to predict in vitro release kinetics of doxorubicin (Dox) delivered by sulfopropyl dextran ion-exchange microspheres. Four ANN models for responses at different time points were developed to describe the release profiles of Dox. Model selection was performed using the Akaike information criterion (AIC). Sixteen data sets were used to train the ANN models and two data sets for the validation. Good correlations were obtained between the observed and predicted release profiles for the two randomly selected validation data sets. The difference factor (f1) and similarity factor (f2) between the ANN predicted and the observed release profiles indicated good performance of the ANN models. The established models were then applied to predict release kinetics of Dox from the microspheres of various initial loadings in media of different ionic strengths and NaCl/CaCl2 ratios. The results suggested that ANN offered a flexible and effective approach to predicting the kinetics of Dox release from the ion-exchange microspheres.