Recently, Signant hosted a virtual event exploring topics in clinical data management. Introducing the concept of data aggregation underpinning Signant’s Clinical Data Hub solution, a group of panelists explored how this approach differs from traditional strategies and offers researchers new opportunities to reveal better insights while making the process of data management more efficient.
Our Chief Operating Officer and clinical data management expert, Jason Martin, kicked off the event by explaining how researchers today are compelled to capture more data from more sources, and outlined the trends driving this increase. He surveyed the audience via an interactive poll which confirmed that they too have observed the trend, with most respondents indicating that their studies involve anywhere from six to fifteen different data sources.
Challenges in Clinical Data Management: The Four Vs
Jan Breemans, Signant’s Senior Analytics Director, expounded on the challenges in clinical data management. He explained how the increasing volume, variety, velocity, and veracity of data generated in today’s research results in longer and more resource-intensive data management cycles.
Data Aggregation via Data Lake Architecture
To set the stage for the next topic, Jason conducted another audience poll to understand attendees’ experiences when bringing clinical data together. Christine Dinger, Senior Product Director at ThoughtSphere, used the resulting word cloud as a springboard into a discussion about data lake architecture, explaining how it creates downstream efficiencies that improve backend workflows.
She displayed graphics to illustrate how, traditionally, data from all sources are routed into a data warehouse where they are then transformed, loaded, stored, transferred, ingested, and transformed again before they can be used for analysis.
In contrast, data lake architecture, she continued, “allows for aggregation and transformation to be performed once across all data mediums, and in a unified and scalable way”. When coupled with machine learning and artificial intelligence algorithms, she added, Clinical Data Hub gets more accurate and more robust with each data source and study loaded into it.
Layering in Analytics
In the final segment, Signant’s Gael Houille, Senior Director, Technical Services, reiterated that intelligent data aggregation reimagines how researchers can use data in clinical trials by offering a more efficient way to organize and store data for risk-based monitoring as well as downstream reviews and analysis.
He introduced examples of analytics tools that can be applied to visualize and interpret data including Signant’s Blinded Data Analytics, Outcome Analytics, and Study Oversight solutions. These tools offer proactive data management, providing a means to “engage with data in a meaningful way such as drawing insights, predicting outcomes, and making important decisions about resource allocation, for instance”.
The event concluded with a final audience poll, a moderated question and answer session, and a summary of key points.
To explore those and hear more about each topic, you can view the recording as well as connect with our data management experts.