Supervised Machine Learning Algorithms for Evaluation of Solid Lipid Nanoparticle (SLNs) and particle size

Solid lipid nanoparticles (SLNs) are pharmaceutical delivery systems that have advantages such as controlled drug release, high loading capacity and long term stability. Particle size and size distribution are two important criteria of SLNs. These factors affect drug release rate, bio-distribution, mucoadhesion, cellular uptake of water and buffer exchange to the interior of the nanoparticles, protein diffusion and cancer therapy. In this study formulation and development of SLNs using high speed homogenization technique have been evaluated. Main emphasis of the work is to study whether the effect of mixing time and formulation ingredients on particle size can be modeled. For this purpose different machine learning algorithms have been applied. The results present that particle size of SLNs can be best estimated by decision tree based methods, but function fitting methods like Linear Regression and Ridge Regression also perform well.