The development of stable solid dispersion formulations that maintain desired improvement of drug dissolution rate during the entire shelf life requires the analysis of drug-polymer solubility and miscibility. Only if the drug concentration is below the solubility limit in the polymer, the physical stability of solid dispersions is guaranteed without risk for drug (re)crystallization. If the drug concentration is above the solubility, but below the miscibility limit, the system is stabilized through intimate drug-polymer mixing, with additional kinetic stabilization if stored sufficiently below the mixture glass transition temperature. Therefore, it is of particular importance to assess the drug-polymer solubility and miscibility, to select suitable formulation (a type of polymer and drug loading), manufacturing process, and storage conditions, with the aim to ensure physical stability during the product shelf life. Drug-polymer solubility and miscibility can be assessed using analytical methods, which can detect whether the system is single-phase or not. Thermodynamic modeling enables a mechanistic understanding of drug-polymer solubility and miscibility and identification of formulation compositions with the expected formation of the stable single-phase system. Advance molecular modeling and simulation techniques enable getting insight into interactions between the drug and polymer at the molecular level, which determine whether the single-phase system formation will occur or not.

The aim of this work was to investigate effects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the effects of excipients and printing parameters on drug dissolution rate in DLP printlets two different neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R² experimental vs. predicted value was 0.9811 (neural network 1) and 0.9960 (neural network 2). According to difference f₁ and similarity factor f₂ (f₁ = 14.30 and f₂ = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input–output relationship in DLP printing of pharmaceutics.

Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.

Various three-dimensional printing (3DP) technologies have been investigated so far in relation to their potential to produce customizable medicines and medical devices. The aim of this study was to examine the possibility of tailoring drug release rates from immediate to prolonged release by varying the tablet thickness and the drug loading, as well as to develop artificial neural network (ANN) predictive models for atomoxetine (ATH) release rate from DLP 3D-printed tablets. Photoreactive mixtures were comprised of poly(ethylene glycol) diacrylate (PEGDA) and poly(ethylene glycol) 400 in a constant ratio of 3:1, water, photoinitiator and ATH as a model drug whose content was varied from 5% to 20% (w/w). Designed 3D models of cylindrical shape tablets were of constant diameter, but different thickness. A series of tablets with doses ranging from 2.06 mg to 37.48 mg, exhibiting immediate- and modified-release profiles were successfully fabricated, confirming the potential of this technology in manufacturing dosage forms on demand, with the possibility to adjust the dose and release behavior by varying drug loading and dimensions of tablets. DSC (differential scanning calorimetry), XRPD (X-ray powder diffraction) and microscopic analysis showed that ATH remained in a crystalline form in tablets, while FTIR spectroscopy confirmed that no interactions occurred between ATH and polymers.

Gelatin-polyvinylpyrrolidone (PVP) and gelatin-poly(vinyl alcohol) (PVA) mucoadhesive buccal films loaded with propranolol hydrochloride (PRH) were prepared by semi-solid extrusion 3D printing. The aim of this study was to evaluate the effects of the synthetic polymers PVP and PVA on thermal and mechanical properties and drug release profiles of gelatin-based films. The Fourier-transform infrared spectroscopy showed that hydrogen bonding between gelatin and PVP formed during printing. In the other blend, neither the esterification of PVA nor gelatin occurred. Differential scanning calorimetry revealed the presence of partial helical structures. In line with these results, the mechanical properties and drug release profiles were different for each blend. Formulation with gelatin-PVP and PRH showed higher tensile strength, hardness, and adhesive strength but slower drug release than formulation with gelatin-PVA and PRH. The in silico population simulations indicated increased drug bioavailability and decreased inter-individual variations in the resulting pharmacokinetic profiles compared to immediate-release tablets. Moreover, the simulation results suggested that reduced PRH daily dosing can be achieved with prolonged-release buccal films, which improves patient compliance.