Artificial Neural Networks (ANN) for Polymeric Nanoparticle Properties Prediction Based on PLGA for Drug Delivery

There is a complex relationship between the properties of Poly (Lactic-Co-Glycolic Acid) (PLGA) and its Nanoparticle (NP) synthesis parameters that affect its performance as a drug delivery system. In the current study because of the complexity of the data, artificial neural networks were used to predict the impact of input variables on the performance, including NP size, Encapsulation Efficiency (E.E.%), and Drug Loading (D.L.%). In the current study, over 180 data gathered from literarture via data minig method. The effective parameters can be classified into two main groups: intrinsic polymer properties and parameters associated with the synthesis process. The individual effects of each of these parameters, their combination as third set, and finally target parameters have also been added to them as 4th set are thoroughly examined. The results revealed that considering all parameters as 4th set provides higher accuracy (R2 = 0.93) in NP size prediction. At the same time, E.E. % and D.L. % are primarily influenced by synthesis parameters (R2 = 0.96) and polymer intrinsic properties (R2 = 0.92), respectively. Sensitivity analysis for the effect of each parameter has revealed that presence of PEG in the formulation, NPs size, and synthesis method are the most effective parameters in prediction of NPs size,  E.E. % and D.L. %, respectively.