Clinical trial feasibility is a fundamental contributor to the overall success of a development program. However, selecting the right countries, sites and investigators and starting up as quickly as possible remains a challenge, leading to greatly variable performance and inaccurate predictions for important trial milestones.
Current approaches can best be described as a blend of art and science, requiring time-intensive data analysis, deep contextual understanding, and a healthy slice of good fortune to meet enrollment targets.
Citeline Study Feasibility is a predictive analytic solution that instantly delivers insights to improve clinical trial decisions and cycle times, by combining Informa Pharma Intelligence's expertly curated, indexed, and enriched clinical data sets with machine learning algorithms. The highly intelligent machine learning engine in Citeline Study Feasibility dynamically forecasts enrollment predictions at the site, country, and overall trial level so users can:
Plan for optimal trial participation
Accelerate speed to first patient in
Reduce the chance of investing in non-performing sites
The platform employs a combination of human and artificial intelligence to deliver predictive insights across three key aspects of feasibility – site allocation, site scoring, and enrollment duration, including probability of enrollment success. These guide and support decisions around which countries to enter for a clinical trial, how many sites are required, and which sites are most recommended based on a given study protocol.
“This is another exciting step forward in the use of data and technology to accelerate clinical trial cycle times. The Study Feasibility platform will help many CROs cater to the unique recruitment challenges of each study across a variety of therapy areas.”
Ruth Lalor, VP, Data & Applied Analytics, ICON plc.
Considering the model’s computational power, these predictive analytics can all be achieved at considerable speed and scale, enabling reduction in the time between protocol finalization, site selection, first site initiation, and first patient in.
In addition, by generating visual analyses of these feasibility scenarios, Citeline Study Feasibility makes it easy to understand what elements of a trial design are having a positive or negative impact on enrollment durations, so trial operators can compare various scenarios and share with colleagues to collaborate.
Watch this video to learn more!
Citeline Study Feasibility
The core machine learning engine in Citeline Study Feasibility is based on gradient boosted decision trees that are trained on Informa’s data and proprietary engineered features. Predictions are made stable by reducing the impact of variability and local overfitting through multiple regression models.
Users can see what trial design elements are having a positive or negative impact on predictions and refine their plans accordingly. The end result is a single platform in which feasibility scenarios can be instantly modeled, optimized, compared, and shared with explain-ability and transparency to an 80% confidence interval.
For each scenario, Citeline Study Feasibility provides a probability of enrollment success. This describes the probability that the trial will successfully enroll the target patient accrual, within the target enrollment duration, given the inputted parameters. Reflecting the uncertainty around probabilities, the resulting predicted enrollment duration can also be viewed within a 20–80% confidence interval. These probabilities are derived from Informa's proprietary enrollment prediction algorithm, which has demonstrated clear superiority over conventional prediction methods.
“It is understanding that risk and what impact you are going to have on study progress if you don’t act because of the risk. An 80% probability of success may or may not feel comfortable, but if you change the protocol footprint, the country strategy, you could make it much more deliverable.”
Director, Strategic Feasibility, Top 5 CRO
Clinical trials are notoriously subject to external factors that lead to variable enrollment rates. Designing a trial in such a way that minimizes the degree of variability is equally as important as targeting an overall reduction in cycle times - something that Citeline Study Feasibility makes great strides toward. In this way, sponsors can balance the allocation of resources more efficiently both for an individual trial and across a wider R&D program.
Does your organization use machine learning to support trial feasibility analyses?
- Not today, but plan to