Artificial neural networks modelling the prednisolone nanoprecipitation in microfluidic reactors

Area of Science:

• Pharmaceutical Science
• Chemical Engineering
• Materials Science

Background:

• Drug nanoprecipitation is a critical process for formulating nanoparticles with enhanced bioavailability.
• Microfluidic reactors offer precise control over reaction conditions for nanoparticle synthesis.
• Understanding the interplay of process parameters is essential for reproducible drug nanoparticle production.

Purpose of the Study:

• To develop a predictive model for drug nanoprecipitation using artificial neural networks (ANNs).
• To identify key variables influencing particle size during prednisolone nanoprecipitation in microfluidic systems.
• To elucidate the dominant factors controlling nanoparticle characteristics.

Main Methods:

• Utilized artificial neural networks (ANNs) to model the complex relationships between input variables and particle size.
• Investigated input variables including prednisolone saturation, solvent/antisolvent flow rates, and microreactor geometry (inlet angles, internal diameters).
• Validated the developed ANN model using a separate dataset to ensure predictive accuracy.

Main Results:

• The ANN model accurately predicted particle size based on the selected input variables.
• Antisolvent flow rate was identified as the most influential parameter affecting final particle size.
• The model demonstrated good agreement between predicted and observed results.

Conclusions:

• Artificial neural networks provide a powerful tool for modeling and optimizing drug nanoprecipitation processes.
• Precise control over antisolvent flow rate is paramount for achieving desired particle sizes in microfluidic drug formulation.
• This study offers valuable insights for the rational design of nanoparticle drug delivery systems.