Artificial Intelligence in Pharmaceutics: Current Applications, Methodological Challenges, and Translational Potential—A Review

Background: Artificial intelligence (AI), designed to emulate human cognitive processes, has rapidly become an integral component of contemporary pharmaceutical research. Advances in machine learning (ML) and deep learning (DL) have significantly enhanced efficiency across the drug development pipeline, including target identification, formulation design, and drug delivery optimization. Objective: This systematic review aims to synthesize recent evidence on the application of AI in pharmaceutical technology and drug delivery design, with particular emphasis on drug discovery, dosage form optimization, manufacturing processes, and pharmacokinetic/ pharmacodynamic (PK/PD) modeling. Methodology: A systematic literature review was conducted in accordance with PRISMA 2020 guidelines. Peer-reviewed studies examining AI-driven approaches in pharmaceutics were identified, screened, and analyzed, focusing on their methodological frameworks, applications, and reported outcomes. Results: AI-based systems enabled the analysis of large-scale genomic, proteomic, and chemical datasets, facilitating the identification of disease-relevant biomarkers and potential drug candidates. Modeling and simulation approaches improved preclinical predictions of pharmacokinetics, pharmacodynamics, and toxicity, supporting candidate prioritization and experimental design. Applications were particularly prominent in antitumor drug discovery, formulation optimization, manufacturing process enhancement, and PK/PD modeling. Despite these advances, significant challenges persist, including data bias, limited model interpretability, insufficient external validation, and regulatory uncertainty. Conclusion: AI offers substantial opportunities for automation, precision, and innovation in pharmaceutical sciences. However, addressing methodological limitations, improving transparency, and establishing ethically guided and regulatory-compliant AI frameworks are essential for successful clinical translation. Continued interdisciplinary collaboration will be critical to the safe and effective integration of AI into pharmaceutical technology and drug delivery systems. Keywords: Artificial Intelligence, Deep Learning, Drug Discovery, Drug Delivery Systems, Machine Learning, Pharmaceutical Technology, Pharmacokinetics, Pharmacodynamics.