Artificial Intelligence is continuously changing the landscape of pharmaceutical sciences by solving major issues related to traditional drug discovery and development practices like high cost, long duration and low success rate. This review presents an encompassing overview of Artificial Intelligence applications from drug design and development to delivery in the pharmaceutical pipeline, following a systematic review of recent literature (2020-2025) from major scientific databases followed by thematic analysis and quality assessment. Artificial intelligence techniques (such as machine learning, deep learning, and big data analytics) have significantly improved the drug discovery process because they enable quick screening of enormous molecular datasets, precise prediction of pharmacodynamic interactions, and effective lead optimization. Artificial Intelligence also helps to develop personalized medicine that integrates genomics, proteomics, and clinical data to create custom-tailored therapies for patients. According to the review, creating novel pharmacological indications for already-approved medications can be done quickly and affordably through artificial intelligence-based drug repurposing. The report also suggests how Artificial Intelligence is being implemented in drug delivery systems, pharmacovigilance, clinical trials, healthcare services, etc. to improve patient outcomes and efficiency. Such Artificial Intelligence has a huge potential with great possibilities; however, there are many challenges to its implementation. For instance, bias in data, lack of transparency, regulatory challenges, concerns over data privacy and security, etc. Such challenges highlight the need for strong governance frameworks as well as the need for explainable Artificial Intelligence. Overall, Artificial Intelligence is evolving into an engine of innovation in pharmaceuticals- creating a future of more efficient, accurate, and personalized healthcare solutions. It also illuminates important research gaps and future directions for sustainable integration of these technologies in the healthcare system.
Rajoriya et al. (Fri,) studied this question.