Application of Artificial Neural Network to Determine Optimum Formulation Development and in Vitro Characterization of Methylene Blue and Galantamine Loaded Polymeric Nanoparticles for the Treatment of Alzheimer's Disease

Abstract

Alzheimer's disease is a major neurodegenerative disorder characterized by complex pathophysiology and currently lacks a curative treatment. This study aims to develop and characterize methylene blue and galantamine co-loaded PLGA nanoparticles, surface-modified with poloxamer 188 and GSH, to increase blood residence time and improve brain-targeted delivery. The nanoparticles were prepared using the double emulsion solvent evaporation method, and their physicochemical properties were characterized by TEM, FT-IR, DSC, XRD, and C-13 NMR. Artificial neural network modeling was used to optimize the formulation parameters, including PLGA %, PVA %, and sonication time, for predicting particle size and encapsulation efficiencies of methylene blue and galantamine. Results showed that the optimized nanoparticles had particle sizes <200 nm, appropriate zeta potential, and high encapsulation efficiencies. DSC, FT-IR, XRD, and NMR analyses confirmed the absence of crystalline peaks for methylene blue and galantamine, indicating successful encapsulation. Artificial neural network models demonstrated high predictive accuracy, serving as a valuable tool for formulation optimization. This dual-drug, surface-modified nanoparticle approach offers promising potential for multi-target therapy in Alzheimer's disease.