Artificial Intelligence for Clinical Trial Facilitation, Lessons for Inflammatory Bowel Disease: A Scoping Review

Despite major advances in many fields of science and technology, pharmaceutical research and development continues to be inefficient across multiple diseases. Inflammatory bowel disease (IBD) trials are also subject to high failure rates. The aim of this review was to give an overview of the available literature on the use of artificial intelligence (AI) for clinical trial facilitation across a variety of medical specialties before trying to best position AI in IBD clinical trials.

A scoping review was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) scoping reviews guidelines. The search strategy was performed using PubMed and combined the terms linked to "AI" and "clinical trials." We included studies assessing the use of AI in transforming the key steps of the drug development process and clinical trials. Studies evaluating the use of AI for clinical purposes were excluded.

In total, 80 articles were included. The rapid development of AI has great potential to transform the process of clinical development of new drugs in IBD, from screening of candidate molecules to study conception and execution, thereby enhancing trial efficiency. By improving the quality of trial design and facilitating patient selection, AI could help to decrease sample sizes and costs. AI may help to prescreen patients to facilitate-and possibly automate-trial enrollment. AI techniques could also help in patient monitoring by making adherence control more accurate, facilitating endpoint detection and real-time analysis.

Notwithstanding the ethical, regulatory, and practical limitations, incorporation of AI into clinical trials may accelerate and improve quality of drug development in IBD.