Abstract
Clinical trials are crucial for drug development, but they require significant time and financial resources. Additionally, uncertainties may arise during these trials concerning their results due to concerns surrounding effectiveness, safety, or the enrollment of participants. If robust AI (artificial intelligence) models exist that can accurately forecast clinical trial results, it would effectively prevent potential failures in such trials and also speed up the drug discovery process. Consequently, more resources could be allocated towards potentially successful trials, ultimately enhancing the suc-cess rate of new drug development. This article systematically reviews the research works on the three main scenar-ios of AI affecting clinical trial outcomes. Clinical text embedding, complex trial relations and trial prediction methods. Then, the challenges and opportunities of predicting clinical trial outcomes is discussed in real-world applications.