Issue link: https://read.uberflip.com/i/1187868
Modernizing Clinical Trials: Digital Technologies and the Cloud 4 Published by FiercePharma allowing them to iterate faster and more frequently. Powered by machine learning, real-time scenario planning helps to facilitate smar ter trial planning by enabling researchers to determine the most optimal sites, countries and/or protocol combinations. "Jus t by eliminating poor per for ming sites, trial teams have the potential to reduce their trial cost by 20%. And by making data-driven decisions that are significantly more accurate, we can plan and execute clinical trials faster, leading to hundreds of thousands in cost savings for ever y month saved in a trial," Ari Yacobi, Chief Data Scientist at Knowledgent, said. To accomplish this type of predic tive power large amounts of data needs to be securely stored and quickly shared, a benefit of utilizing a cloud-based plat form. The ITP application leverages the secure storage capacity of AWS, as well as other AWS services, to clean, aggregate and integrate the data and ensure that data scientists have the ability to quer y it. The use of the highly scalable cloud-based computational power and advanced machine learning algorithms on AWS Cloud can help pharma companies to efficiently and effectively predict and plan clinical trial design and recruitment, decreasing overall clinical trial timelines. UTILIZING HISTORICAL CLINICAL TRIAL PATIENT DATA TO INFORM CLINICAL DEVELOPMENT Computational power and AI/ML is only one par t of the puzzle, though. These resources can only yield meaningful insights when turned on extensive, timely and accurate data, and when informed by a thorough understanding of the natural history of a disease. Pharma companies have looked to their prior experience, medical literature and emerging real-world data (RWD) to meet this need. However, none of t hes e res ources are per fec t. Published literature is static and covers just a few data element s about one trial at a time. RWD is far more voluminous but c an be under mined by differences between patient populations, unsystematic data collec tion and a limited geographic coverage. Finally, the sponsor's own historical clinical trial data is inherently limited to the scope of its earlier studies and is laborious to standardize for meta-analysis. All of these shor tcomings hinder researchers' ability to make data-driven decisions. Recognizing the need for fit-for-purpose data address these challenges, Medidata has made available a pool