The optimization based on a surrogate model and the explicit prediction formulations was carried out to find the optimal lateral thickness distribution of 3 × 3 square multi-cell tube.
Moreover, the prediction formulations have conventionally been based on the practically unrealistic assumption that one has full information about the space of targets and drugs when constructing the models and evaluating their predictive accuracy.
The Results section starts with listing model assumptions, followed by deriving semi-analytical solutions of Nissan and Parker's model and interpretation of the analysis results and prediction formulations.
The constructed ANN model fitted better to the overall desirability than the MLR model (R = 0.838 vs. 0.670, for the additional checkpoint formulations) and therefore, was used for prediction of formulation with optimal in vitro drug release.
The optimized GRNN model was used for prediction of formulation with desired in vitro drug release.
The presence of additive disturbances that are not LP would destroy the prediction error formulation and stability analysis arguments in previous results.
In this paper, a new prediction error formulation is constructed through the use of a recently developed Robust Integral of the Sign of the Error (RISE) technique.
Combination of biorelevant in vitro measurements with in silico physiologically based pharmacokinetic (PBPK) modelling resulted in an accurate prediction of formulation performance and forecasts a reduction in food effects on fenofibrate bioavailability through maximising its fasted state dissolution.
For run-out prediction, empirical formulations (derived from a large sample of landslides statistical data) and analytical approaches (i.e. simple sliding block models) indeed provide valuable information.
