Floating Gastroretentive Drug Delivery Technologies

Abstract

Floating gastroretentive drug delivery technologies have emerged as an effective strategy for improving the oral bioavailability of drugs exhibiting narrow absorption windows or preferential gastric absorption. Despite continuous progress in formulation science, the prediction of floating behavior and in vivo gastric retention remains largely dependent on empirical experimentation, increasing development time and cost. This study identifies a significant research gap in the integration of artificial intelligence with formulation optimization for floating gastroretentive systems. A novel AI-assisted predictive framework is proposed to estimate gastric retention efficiency and drug release performance simultaneously using formulation composition and physicochemical descriptors. The framework combines explainable machine learning with formulation-specific feature engineering to support personalized dosage design. Recent advances in pharmaceutical informatics, digital twins, and computational formulation science are incorporated to establish an intelligent optimization strategy. The proposed research aims to reduce formulation iterations while improving prediction reliability across diverse drug candidates. The findings are expected to accelerate the development of nextgeneration gastroretentive dosage forms suitable for precision medicine and AI-enabled pharmaceutical manufacturing