Nanoprecipitation is a simple and fast method to produce polymeric nanoparticles (Np); however, most applications require filtration or another separation technique to isolate the nanosuspension from aggregates or polydisperse particle production. In order to avoid variability introduced by these additional steps, we report here a systematic study of the process to yield monomodal and uniform Np production with the nanoprecipitation method. To further identify key variables and their interactions, we used artificial neural networks (ANN) to investigate the multiple variables which influence the process. In this work, a polymethacrylate derivative was used for Np (NpERS) and a database with several formulations and conditions was developed for the ANN model. The resulting ANN model had a high predictability (> 70%) for NpERS characteristics measured (mean size, PDI, zeta potential, and number of particle populations). Moreover, the model identified production variables leading to polymer supersaturation, such as mixing time and turbulence, as key in achieving monomodal and uniform NpERS in one production step. Polymer concentration and type of solvent, modifiers of polymer diffusion and supersaturation, were also shown to control NpERS characteristics. The ANN study allowed the identification of key variables and their interactions and resulted in a predictive model to study the NpERS production by nanoprecipitation. In turn, we have achieved an optimized method to yield uniform NpERS which could pave way for polymeric nanoparticle production methods with potential in biological and drug delivery applications.
Keywords: Artificial neural networks; Homogeneous nanoparticles; Mixing time; Nanoparticle production; Nanoprecipitation; Polymeric nanoparticles.