Data Driven and Mechanistic Modelling of PLGA Nanoparticle Formation in Hydrodynamic Flow-Focusing Microfluidics

Abstract

Microfluidic devices offer precise control over polymeric nanoparticles (NPs) synthesis. However, rational design of process optimization to obtain a target NPs sizes remains challenging because the relationship between operating parameters, mixing dynamics, and particle formation are not very linear Here, we integrate mechanistic analysis, statistical design of experiments (DoE), and machine learning (ML) to develop predictive and inverse-design frameworks for the synthesis of poly(lactic-co-glycolic acid) (PLGA) NPs. The effects of flow rate ratio (FRR), PLGA concentration, and microchannel width were systematically investigated using hydrodynamic flow-focusing (HFF) microfluidic devices.Mixing time analysis demonstrated that NPs size is primarily governed by solvent to antisolvent mixing, with equivalent mixing times producing comparable particle sizes despite different combinations of FRR and channel width. A Box Behnken DoE yielded a highly predictive quadratic model (R² = 0.9979), identifying microchannel width as the dominant design variable, followed by PLGA concentration and FRR. Eight machine learning algorithms were subsequently developed and evaluated, with Gradient Boosting achieving the highest predictive accuracy (test R² = 0.9900, RMSE = 2.65 nm).Finally, inverse design experiments were performed for target NPs sizes of 80, 120, and 160 nm using DoE and a selected sub-set of ML models. Process conditions predicted by the developed models were implemented experimentally, and the Gradient Boosting model produced NP sizes in closest agreement with the preassigned targets, outperforming both the DoE and other ML models. This combined mechanistic and data driven framework enables reliable prediction and inverse design of PLGA nanoparticle synthesis and provides a practical strategy for intelligent, on-demand microfluidic manufacturing of polymeric nanomedicines.