Current state-of-the-art in multi-scale modeling in nano-cancer drug delivery: role of AI and machine learning

Nanomedicine has transformed cancer therapy by enabling targeted drug delivery through nanoparticle-based systems. However, challenges such as inefficient tumor accumulation, poor tissue penetration, and limited cellular uptake hinder therapeutic efficacy. This review explores computational modeling approaches to optimize nanodrug delivery, focusing on multi-scale and stochastic frameworks. Mathematical models have been developed to simulate nanoparticle transport across systemic, tissue, and cellular levels, addressing key processes such as transvascular extravasation, interstitial distribution, and drug release. Additionally, studies integrating artificial intelligence (AI) and machine learning (ML) into in silico models have demonstrated improved predictive accuracy, optimized patient-specific treatments, and refined nanoparticle design. Computational tools for simulating nanoparticle transport, model validation strategies, and the challenges of merging AI with traditional modeling paradigms are discussed. Furthermore, environmental and manufacturing sustainability concerns in nanomedicine production are addressed. By bridging gaps in current research, this work provides a comprehensive overview of computational methodologies, emphasizing their potential to advance precision oncology and accelerate the clinical translation of AI-driven nano-cancer drug delivery systems.