Maximize the predictive strength of Citeline Predict: Study Feasibility by integrating your data alongside Informa’s.
Citeline’s gold-standard, granular drug, trial, site, investigator, and patient proximity data sets were used to train the ML models in the initial version of Study Feasibility. While this is an excellent starting point for a predictive analytic, the best ML models will have a strong foundation of relevant data combined from multiple sources in addition to Citeline’s data. To make the most out of Study Feasibility and to refine its predictive power, the ML models can be powered by trial operational metrics, site and investigator performance/quality data, activation timelines, real world data, and more — in addition to Citeline’s data. ICON plc. partnered with us to do exactly this — incorporating their clinical trial activation, cycle time, performance, and quality data alongside ours (see press release for more details). Combining complementary data sets and expertise from Citeline and ICON tightened feasibility predictions, improved feasibility analysis workflows, and will help ICON users to:
Shorten the time to first patient in
Minimize overall enrollment durations
Select a higher percentage of sites that enroll patients
The predictions and capabilities in Study Feasibility will also help to reduce cost and manual effort in the clinical trial planning process for feasibility teams. Platform users can quickly see the impact of specific trial elements on predicted enrollment timelines and optimize projected enrollment of patients accordingly.
In addition, feasibility predictions can be made for new trial designs that may not have a perfect match in historical data. This allows for exploration of innovative, experimental trial designs and locations without the risk of wasting resources or investing in non-performing sites.
This value will be further amplified by incorporating your data into the data foundation used to train the ML models.