During the development of a pharmaceutical formulation, a powerful tool is needed to extract the key points from the complicated process parameters and material attributes. Artificial neural networks (ANNs), a promising and more flexible modeling technique, can address real intricate questions in a high parallelism and distributed pattern in the manner of biological neural networks. The data mined and analyzing based on ANNs have the ability to replace hundreds of trial and error experiments. ANNs have been used for data analysis by pharmaceutics researchers since the 1990s and it has now become a research method in pharmaceutical science. This review focuses on the latest application progress of ANNs in the prediction, characterization and optimization of pharmaceutical formulation to provide a reference for the further interdisciplinary study of pharmaceutics and ANNs.

Poly(lactic-glycolic acid) (PLGA) is a biocompatible bio-scaffold material, but its own hydrophobic and electrically neutral surface limits its application as a cell scaffold. Polymer materials, mimics ECM materials, and organic material have often been used as coating materials for PLGA cell scaffolds to improve the poor cell adhesion of PLGA and enhance tissue adaptation. These coating materials can be modified on the PLGA surface via simple physical or chemical methods, and coating multiple materials can simultaneously confer different functions to the PLGA scaffold; not only does this ensure stronger cell adhesion but it also modulates cell behavior and function. This approach to coating could facilitate the production of more PLGA-based cell scaffolds. This review focuses on the PLGA surface-modified materials, methods, and applications, and will provide guidance for PLGA surface modification.

Thorough understanding and accurate prediction of in vivo drug release are essential for developing long‐acting microsphere systems. However, the fate of microspheres after prolonged tissue residence and the regulatory role of physiological factors remain unclear, hindering elucidation of release mechanisms. Herein, the dynamic evolution of microsphere depots and associated microenvironmental changes were studied. Beyond poly(lactic‐co‐glycolic acid) (PLGA) and API effects, microsphere depot behavior is partly regulated by conserved biological processes, with skeletal muscle and subcutaneous tissue employing distinct adaptive strategies to restore homeostasis. Using these insights, we developed the in vivo release predictive models (IVRPMs) that establish a true IVIVC for naltrexone PLGA microspheres. The IVRPMs demonstrated broad applicability across microspheres with different APIs and PLGA types, and showed promising translational potential in beagle and human studies. This study shifts the research paradigm from “material‐dominated release” to “organism‐material coevolution”, addressing a key question in depot formulation fate.