By Clinical Informatics News Staff

December 18, 2015 | UCB has selected the Sinequa Big Data Search & Analytics Platform for use with its clinical trial file share. Using the Sinequa Platform, UCB is able to more effectively find data sets needed to answer questions arising in the lifecycle of drug development.

Over the past 15 years, UCB has amassed more than 20TB of data which is currently growing at a rate of 30% a year. Datasets include more than a million SAS data sets with billions of data rows as well as SAS program code, ASCII, Microsoft Office and PDF files. With the number of file types and volume of content, search and discovery was a mounting challenge. As a result, UCB’s business objectives required a reduction of the time and cost by implementing an enterprise search capability that permits analysts and programmers to quickly locate relevant clinical data files.

To achieve this objective, UCB selected Sinequa. This easy to implement platform enables UCB to easily find data faster, making the processing of requests easier and much more efficient.  For example, with a simple query, statisticians and/or data managers can easily find data relevant for their current study/analysis and more quickly discover the link to and background of the original study, any of the related data or documents that exist to support the study. Even more, it helps to find data about the study that researchers may not have known about previously. This can reduce the time needed for additional searches or new analyses by orders of magnitude and helps UCB to respond quickly to questions by regulatory authorities as well as possibly answering new questions concerning the use of a drug in specific populations. 

“SAS data sets comprise as much as 70% of our clinical development file content. No other company we evaluated could handle SAS data sets like Sinequa,” said Todd Culverwell, Director, Trial Master File and Clinical Repositories, UCB, in a press release. “We can simply search for a key phrase and be directed right away to a row in a SAS data set. We can also use any number of 900 SAS clinical dataset variables and ask for results within a value range for each of these variables. In some cases what once took weeks, can be easily be produced within a day or two.”

“Sinequa is simply great technology,” said Oliver Thoennessen, Senior Manager Global IT Drug Development, UCB in the same statement. “We immediately saw its benefit watching it perform something we didn’t know was possible. It makes an exponential difference for our organization. We were also impressed with the number of smart connectors available out-of-the-box and Sinequa’s unique ability to develop new ones.”