Artificial neural networks modelling the prednisolone nanoprecipitation in microfluidic reactors

• Published in: European journal of pharmaceutical sciences Vol. 37; no. 3; pp. 514 - 522
• Main Authors: Ali, Hany S.M., Blagden, Nicholas, York, Peter, Amani, Amir, Brook, Toni
• Format: Journal Article
• Language: English
• Published: Kindlington Elsevier B.V 28-06-2009; Elsevier
• Subjects: Algorithms; Anti-Inflammatory Agents - chemistry; Artificial Intelligence; Artificial neural networks; Biological and medical sciences; General pharmacology; Medical sciences; Microfluidic Analytical Techniques; Microfluidics; Modelling; Models, Chemical; Models, Statistical; Nanoprecipitation; Neural Networks (Computer); Particle Size; Pharmaceutical technology. Pharmaceutical industry; Pharmacology. Drug treatments; Prednisolone; Prednisolone - chemistry; Solubility; Modelling; Nanoprecipitation; Microfluidics; Prednisolone; Artificial neural networks; Antineoplastic agent; Corticosteroid; Pharmaceutical technology; Antiinflammatory agent; Neural network; Modeling; Adrenal hormone; Immunosuppressive agent
• ISSN: 0928-0987; 1879-0720
• DOI: 10.1016/j.ejps.2009.04.007

This study employs artificial neural networks (ANNs) to create a model to identify relationships between variables affecting drug nanoprecipitation using microfluidic reactors. The input variables examined were saturation levels of prednisolone, solvent and antisolvent flow rates, microreactor inlet angles and internal diameters, while particle size was the single output. ANNs software was used to analyse a set of data obtained by random selection of the variables. The developed model was then assessed using a separate set of validation data and provided good agreement with the observed results. The antisolvent flow rate was found to have the dominant role on determining final particle size.