Artificial Intelligence for Clinical Trial Design
Stefan Harrer
Abstract
Artificial intelligence (AI) technologies have advanced to a level of maturity that allows them to be employed under real-life conditions to assist human decision-makers. AI has the potential to transform key steps of clinical trial design from study preparation to execution towards improving trial success rates, thus lowering the pharma R&D burden. Suboptimal patient cohort selection and recruiting techniques, paired with the inability to monitor patients effectively during trials, are two of the main causes for high trial failure rates: only one of 10 compounds entering a clinical trial reaches the market. This session will explain in layman's terms some of the foundations of AI methodology, such as Machine Learning and Deep Learning, highlighting how recent advances can be applied at specific stages of the clinical trial design process to improve cohort composition, patient recruitment, medication compliance and patient retention. A special focus will be given to describing how patients in neurology trials could be monitored more efficiently through Digital Disease Diaries, which use wearable devices, machine learning at the edge and cloud technology to automatically detect and log disease episodes and patient adherence to trial protocols. Like all technical revolutions, this comes with challenges and risks, both technical and regulatory. In particular, we will discuss scalability, data encryption and patient privacy.