DIA – Digital Technology in Clinical Trials

Session 1 Track B: Data Principles & Solution Patterns to Unlock our Data Wealth

Clinical Trials generate enormous tombs of data. EDC generates many gigabytes of data for each trial. Verbose auditing increase datasets by 10x. Wearables and other sensors increase datasets (again) by 10x to 100x. RWE datasets are only bounded by the potential candidate pool of all people with their health records digitized. How are we to deal with our data explosion? From the fable “The Miser and his Gold”, how do we ensure our data is “a wealth we use” as wealth not used is the same as wealth that does not exist. This session will discuss maintaining data principles, embracing proven big data patterns, and leveraging the benefits of cloudification with cost vigilance to achieve the data agility our clinical trials demand.

Learning Objective :

• Propose a set of data principles to guide big data strategy
• Describe big data solution patterns
• Defend that successful DataOPS requires cloudification with cost vigilance