Predicting drug contents of hydroxypropylmethylcellulose films using Artificial Neural Network

Abstract

The aim of this study is to investigate Artificial Neural Network (ANN) for prediction of drug contents. Hydroxypropylmethylcellulose and loratadine specifically were selected as model matrix polymer and drug. All 0, 5, 10, 20 and 40 mg drug loaded in hydroxypropylmethylcellulose films were conditioned at the relative humidity of 25, 50 and 75% each prior to psysicochemical characterization using microwave non-destructive testing (NDT) technique. Forward reflection coefficient magnitude S <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</inf> produced by microwave NDT technique along with the relative humidity were utilized as inputs to the ANN model with the value of drug contents as output. Initial results showed that an accuracy of 86% is achieved using ANN for prediction of drug contents.