Machine learning enabled multiscale model for nanoparticle margination and physiology based pharmacokinetics

Abstract

This study presents a multiscale modeling framework for simulating and predicting the behavior and biodistribution of nanoparticles ($\mathrm{NPs}$), focusing on applications such as targeted drug delivery. The framework encompasses two coupled models: (1) a DeepONet-enabled Fokker–Planck equation to model the NP drift–diffusion in the red-blood cell-free layer (RBCFL) that predicts NP margination and concentration profiles taking hematocrit and vessel radius as inputs, built on top of a hemorheological model of shear-induced blood flow and (2) a physiologically based pharmacokinetic (PBPK) model that uses the predicted concentration profiles in microvasculature to inform the biodistribution of NPs across different organ in the body.