Estimation of design space for an extrusion–spheronization process using response surface methodology and artificial neural network modelling

Investigation of the Electrokinetic Potential of Granules and Optimization of the Pelletization Method Using the Quality by Design Approach

The preparation of pellets using a high-shear granulator in a rapid single-step is considered a good economic alternative to the extrusion spheronization process. As process parameters and material attributes greatly affect pellet qualities, successful process optimization plays a vital role in producing pellet dosage forms with the required critical quality attributes. This study was aimed at the development and optimization of the pelletization technique with the Pro-CepT granulator. According to the quality by design (QbD) and screening design results, chopper speed, the volume of the granulating liquid, binder amount, and impeller speed were selected as the highest risk variables for a two-level full factorial design and central composite design, which were applied to the formula of microcrystalline cellulose, mannitol, and with a binding aqueous polyvinylpyrrolidone solution. The design space was estimated based on physical response results, including the total yield of the required size, hardness, and aspect ratio. The optimized point was tested with two different types of active ingredients. Amlodipine and hydrochlorothiazide were selected as model drugs and were loaded into an optimized formulation. The kinetics of the release of the active agent was examined and found that the results show a correlation with the electrokinetic potential because amlodipine besylate can be adsorbed on the surface of the MCC, while hydrochlorothiazide less so; therefore, in this case, the release of the active agent increases. The research results revealed no significant differences between plain and model drug pellets, except for hydrochlorothiazide yield percent, in addition to acceptable content uniformity and dissolution enhancement.

Applications of Machine Learning in Solid Oral Dosage Form Development

This review comprehensively summarizes the application of machine learning in solid oral dosage form development over the past three decades. In both academia and industry, machine learning is increasingly applied for multiple preformulation/formulation and process development studies. Further, this review provides the authors' perspectives on how pharmaceutical scientists can use machine learning for right projects and in right ways; some key ingredients include (1) the determination of inputs, outputs, and objectives; (2) the generation of a database containing high-quality data; (3) the development of machine learning models based on dataset training and model optimization; (4) the application of trained models in making predictions for new samples. It is expected by the authors and others that machine learning will promisingly play a more important role in tomorrow's projects for solid oral dosage form development.

A Precise Prediction Method for the Properties of API-Containing Tablets Based on Data from Placebo Tablets

We previously reported a novel method for the precise prediction of tablet properties (e.g., tensile strength (TS)) using a small number of experimental data. The key technique of this method is to compensate for the lack of experimental data by using data of placebo tablets collected in a database. This study provides further technical knowledge to discuss the usefulness of this prediction method. Placebo tablets consisting of microcrystalline cellulose, lactose, and cornstarch were prepared using the design of an experimental method, and their TS and disintegration time (DT) were measured. The response surfaces representing the relationship between the formulation and the tablet properties were then created. This study investigated tablets containing four different active pharmaceutical ingredients (APIs) with a drug load ranging from 20–60%. Overall, the TS of API-containing tablets could be precisely predicted by this method, while the prediction accuracy of the DT was much lower than that of the TS. These results suggested that the mode of action of APIs on the DT was more complicated than that on the TS. Our prediction method could be valuable for the development of tablet formulations.

The significance of artificial intelligence in drug delivery system design

Over the last decade, increasing interest has been attracted towards the application of artificial intelligence (AI) technology for analyzing and interpreting the biological or genetic information, accelerated drug discovery, and identification of the selective small-molecule modulators or rare molecules and prediction of their behavior. Application of the automated workflows and databases for rapid analysis of the huge amounts of data and artificial neural networks (ANNs) for development of the novel hypotheses and treatment strategies, prediction of disease progression, and evaluation of the pharmacological profiles of drug candidates may significantly improve treatment outcomes. Target fishing (TF) by rapid prediction or identification of the biological targets might be of great help for linking targets to the novel compounds. AI and TF methods in association with human expertise may indeed revolutionize the current theranostic strategies, meanwhile, validation approaches are necessary to overcome the potential challenges and ensure higher accuracy. In this review, the significance of AI and TF in the development of drugs and delivery systems and the potential challenging issues have been highlighted.

Computer-based formulation design and optimization using Hansen solubility parameters to enhance the delivery of ibuprofen through the skin

Trial-and-error approach to formulation development is long and costly. With growing time and cost pressures in the pharmaceutical industry, the need for computer-based formulation design is greater than ever. In this project, emulgels were designed and optimized using Formulating for Efficacy™ (FFE) for the topical delivery of ibuprofen. FFE helped select penetration enhancers, design and optimize emulgels and simulate skin penetration studies. pH, viscosity, spreadability, droplet size and stability of emulgels were evaluated. Franz cell studies were performed to test in vitro drug release on regenerated cellulose membrane, drug permeation in vitro on Strat-M® membrane and ex vivo on porcine ear skin, a marketed ibuprofen gel served as control. Emulgels had skin compatible pH, viscosity and spreadability comparable to a marketed emulgel, were opaque and stable at 25 °C for 6 months. Oleyl alcohol (OA), combined with either dimethyl isosorbide (DMI) or diethylene glycol monoethyl ether (DGME) provided the highest permeation in 24 h in vitro, which was significantly higher than the marketed product (p < 0.01). OA + DGME significantly outperformed OA ex vivo (p < 0.05). The computer predictions, in vitro and ex vivo penetration results correlated well. FFE was a fast, valuable and reliable tool for aiding in topical product design for ibuprofen.

A two-step approach for fluidized bed granulation in pharmaceutical processing: Assessing different models for design and control

Various modeling techniques were used to understand fluidized bed granulation using a two-step approach. First, Plackett-Burman design (PBD) was used to identify the high-risk factors. Then, Box-Behnken design (BBD) was used to analyze and optimize those high-risk factors. The relationship between the high-risk input variables (inlet air temperature X1, binder solution rate X3, and binder-to-powder ratio X5) and quality attributes (flowability Y1, temperature Y2, moisture content Y3, aggregation index Y4, and compactability Y5) of the process was investigated using response surface model (RSM), partial least squares method (PLS) and artificial neural network of multilayer perceptron (MLP). The morphological study of the granules was also investigated using a scanning electron microscope. The results showed that X1, X3, and X5 significantly affected the properties of granule. The RSM, PLS and MLP models were found to be useful statistical analysis tools for a better mechanistic understanding of granulation. The statistical analysis results showed that the RSM model had a better ability to fit the quality attributes of granules compared to the PLS and MLP models. Understanding the effect of process parameters on granule properties provides the basis for modulating the granulation parameters and optimizing the product performance at the early development stage of pharmaceutical products.