Generalized in vitro-in vivo relationship (IVIVR) model based on artificial neural networks

This study compared the blood concentrations of remifentanil obtained in a previous clinical investigation with the predicted remifentanil concentrations produced by different pharmacokinetic models: a non-linear mixed effects model created by the software NONMEM; an artificial neural network (ANN) model; a support vector machine (SVM) model; and multi-method ensembles. The ensemble created from the mean of the ANN and the non-linear mixed effects model predictions achieved the smallest error and the highest correlation coefficient. The SVM model produced the highest error and the lowest correlation coefficient. Paired t-tests indicated that there was insufficient evidence that the predicted values of the ANN, SVM and two multi-method ensembles differed from the actual measured values at alpha = 0.05. The ensemble method combining the ANN and non-linear mixed effects model predictions outperformed either method alone. These results indicated a potential advantage of ensembles in improving the accuracy and reducing the variance of pharmacokinetic models.

Delivery of drugs to the large bowel has been extensively investigated during the last decade. The aim of this study was to investigate whether enteric-coated tablets could be made from enteric-coated matrix granules and drug release targeted to the colon. Whether in vitro drug release rate and in vivo absorption could be delayed by adding citric acid to the granules and/or to the tablet matrix was also studied. Ibuprofen was used as model drug because it is absorbed throughout the gastrointestinal tract. Eudragit S and Aqoat AS-HF were used as enteric polymers. Drug release rates were studied at different pH levels and drug absorption was studied in bioavailability tests. The conclusion was that citric acid retarded in vitro drug release when used in multiple-unit tablets. In vivo absorption of ibuprofen was markedly delayed when citric acid was included in both granules and tablet matrix. Further studies are needed to determine the optimal amount of citric acid in formulations.