Use of Scoring Functions for Clinical Trial Optimization
Next week’s PSI Conference will feature Dr. Yannis Jemiai speaking on the use of Scoring Functions in the re-imagined approach to trial optimization using quantitative decision frameworks. These Scoring Functions enable trial sponsors to rank clinical trial designs by performance characteristics ranging from statistical power to sample size, trial duration and even estimated clinical trial costs.
Here we provide an overview of how Scoring Functions can be implemented for enhanced clinical trial selection.
What is a scoring function?
When clinical trial sponsors aim to optimize trial selection, their decision reflects the needs and preferences of multiple stakeholders. Some members of a leadership committee might prioritize trial duration, others trial costs. While most people are committed to powering a study adequately, the question of whether to increase upfront investments for marginal gains in power might also be subject to debate.
A scoring function is a mathematical tool that enables leadership teams to assign weights to features of a clinical trial based on how well they satisfy a number of performance characteristics. These weights then assign a score to each clinical trial design, and leadership teams can quickly determine those designs which best satisfy various priorities.
Why use a scoring function?
Traditionally discussions about priorities and tradeoffs occurred through in person deliberations. Such a method might have worked when only a small handful of design options were under consideration. This is no longer the case.
Advances in cloud-computing mean that far more design options are available to sponsors than there ever were before. Cytel’s Solara can simulate hundreds of thousands of designs in a matter of minutes. The option of deliberating on the benefits of each design is no longer feasible.
A scoring function provides sponsors with an objective way to determine preferences and then quickly rank options. Arguably, by setting priorities before seeing available options, the process of clinical trial selection becomes even more objective.
How to build a scoring function?
Scoring functions are complex mathematical tools, and need to be created with precise algorithms that can evaluate numerous simulations. Solara provides tools to enable sponsors to select their priorities for preference characteristics, and will then build a scoring function for you to apply to Solara-simulated trial designs.
Click below to learn more about Yannis’ talk at PSI.
About the Author of Blog:
Dr. Esha Senchaudhuri is a research and communications specialist, committed to helping scholars and scientists translate their research findings to public and private sector executives. At Cytel Esha leads content strategy and content production across the company's five business units. She received a doctorate from the London School of Economics in philosophy, and is a former early-career policy fellow of the American Academy of Arts and Sciences. She has taught medical ethics at the Harvard School of Public Health (TH Chan School), and sits on the Steering Committee of the Eastern Division of the Society for Women in Philosophy which is responsible for awarding the Distinguished Woman Philosopher Award.