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

Abstract

BackgroundThe aim of this study was to develop a generalized in vitro-in vivo relationship (IVIVR) model based on in vitro dissolution profiles together with quantitative and qualitative composition of dosage formulations as covariates. Such a model would be of substantial aid in the early stages of development of a pharmaceutical formulation, when no in vivo results are yet available and it is impossible to create a classical in vitro-in vivo correlation (IVIVC)/IVIVR.MethodsChemoinformatics software was used to compute the molecular descriptors of drug substances (ie, active pharmaceutical ingredients) and excipients. The data were collected from the literature. Artificial neural networks were used as the modeling tool. The training process was carried out using the 10-fold cross-validation technique.ResultsThe database contained 93 formulations with 307 inputs initially, and was later limited to 28 in a course of sensitivity analysis. The four best models were introduced into the artificial neural network ensemble. Complete in vivo profiles were predicted accurately for 37.6% of the formulations.ConclusionIt has been shown that artificial neural networks can be an effective predictive tool for constructing IVIVR in an integrated generalized model for various formulations. Because IVIVC/IVIVR is classically conducted for 2–4 formulations and with a single active pharmaceutical ingredient, the approach described here is unique in that it incorporates various active pharmaceutical ingredients and dosage forms into a single model. Thus, preliminary IVIVC/IVIVR can be available without in vivo data, which is impossible using current IVIVC/IVIVR procedures.

In vitro release testing methods for drug-releasing vaginal rings

“…By comparison, in vitro-in vivo relationships (IVIVRs) are semi-quantitative or rankorder relationships between in vitro release data and an in vivo outcome (e.g. blood levels of the drug or the amount of drug absorbed) [142][143][144]. As such, IVIVRs are not considered as robust as IVIVCs.…”

In Vitro-In Vivo Correlation (IVIVC): From Current Achievements Towards the Future

“…Good results on the training and validation data (R 2 > 0.85 and > 0.77, respectively) have demonstrated the feasibility of this method in IVIVC/IVIVR procedures. Apart from that, there were few examples, where artificial neural networks (ANNs) were used to develop a relatively high level of IVIVC/IVIVR for sustained release dosage forms consisting of nifedipine or paracetamol (30)(31). Later, the concept of using ANNs to correlate in vitro and in vivo data was extended by Mendyk et al, who included quantitative and qualitative composition of dosage formulations as covariates for in vitro data (32).…”

Polymers for siRNA Delivery: A Critical Assessment of Current Technology Prospects for Clinical Application

“…would provide a foundation for the quantitative comparison of results from different studies. The development of in silico approaches, leading to predictive models, and the broader adoption of quantitative studies evaluating structure–activity relationships would both aid in the search for more accurate trends with increasing clinical significance.…”