The use of Artificial Intelligence Algorithms in drug development and clinical trials: A scoping review

Background: Artificial Intelligence (AI) is transforming drug development and clinical trials, helping researchers find new treatments faster and personalize care for patients. By automating tasks like molecule screening and predicting treatment outcomes, AI addresses critical challenges in modern medicine. Objectives: This review explores how AI is being used in drug development and clinical trials, focusing on its benefits, limitations, and potential to improve healthcare outcomes. Methods: A scoping review based on Arksey and O'Malley's, 2005 framework was conducted, analyzing 1,956 studies from PubMed, Web of Science, IEEE Xplore, and Scopus. Ten studies were selected for in-depth analysis. Results: Common AI techniques include Support Vector Machines, Neural Networks, and Random Forests, applied in tasks such as identifying new drug uses, predicting antibiotic resistance, and streamlining clinical trials. While AI has shown great promise, challenges like inconsistent data quality and difficulties in clinical validation remain. Conclusions: AI offers exciting opportunities to improve healthcare by making drug development and clinical trials more efficient. However, overcoming barriers like data integration and methodological standardization is essential to ensure these tools benefit diverse populations, especially in settings like Brazil, where genetic diversity and health inequalities pose unique challenges.