RETRACTED: Exploring the applications of formulation-based drug development strategies in neurological disorders using artificial intelligence and machine learning approaches

The study of artificial intelligence (AI), a multidimensional field, empowers machines with the ability to understand, reason, learn, and perform tasks autonomously. As a pivotal branch of computer science, AI excels in analyzing complex medical data and uncovering significant relationships for diverse diagnostic purposes. In neurology, innovative AI techniques have revolutionized diagnostics, management, and outcome prediction, opening new avenues for tackling neurological disorders. AI encompasses two key subsets: machine learning (ML) and deep learning (DL), which have gained immense popularity for predicting bioactivity, toxicology, physical and chemical properties, formulation quality, and drug-target interactions. The complexity of neurological diseases (ND) presents unique challenges in developing treatments for the central nervous system (CNS), given obstacles like the blood-brain barrier and high medication attrition rates. However, AI algorithms, leveraging vast datasets, efficiently analyze, interpret, and predict unknown facts, significantly accelerating CNS drug discovery. Deep learning architectures have furthered our understanding of AI's potential to address complex CNS disease issues, transforming the drug development landscape. This review delves into AI, ML, and their applications in advancing CNS drug and formulation development. It provides comprehensive, up-to-date insights on AI/ML advancements in neurology, emphasizing nanoparticle-based drug delivery systems. Additionally, the review covers ML algorithms' roles in de novo drug design, structure-based drug design, ligand-based drug design, absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction, and drug repurposing. Despite notable progress, significant challenges remain in enhancing AI's practical application in neurology. Overcoming these hurdles requires compiling extensive data and developing interpretable AI systems, paving the way for groundbreaking advancements in CNS drug development.