“There is always the risk that interim analyses might occur after the Sufficient Information Threshold has been reached. Bayesian methods alleviate some of this risk.”
The question of when a clinical trial has achieved enough data to determine its success or futility is critical. The Sufficient Information Threshold describes this conceptual point: that is, when all information relevant to the study has been collected, allowing decision-makers to answer questions about the efficiency, ethical quality, and effectiveness of a clinical study. Myriad scientific, rational, and ethical reasons indicate stopping patient enrollment after this threshold is reached: it is unnecessary, it wastes resources, and it can expose patients to subpar treatments.
It is important to approximate this threshold as quickly as possible, but how? Cytel’s East Bayes® cloud-powered software can provide important insights using Bayesian methodologies, providing the continuous learning needed to make decisions about the future of a clinical trial.
“Sufficient Information Threshold for Effective Bayesian Applications: The Effective, Efficient, and Ethical Way Forward,” by Pantelis Vlachos, Kyle Wathen, and Yannis Jemiai, discusses the uses of Bayesian predictive probability across the clinical development journey, in particular approximating the Sufficient Information Threshold and how it can be used for strategic clinical trial design.
Click below to access the full position paper and to learn more about:
- The Sufficient Information Threshold and the Sufficient Efficacy Information Threshold
- Bayesian predictive probability methods
- Unplanned early stopping in early phase clinical trials
- Bayesian methods in late-phase clinical trials
The Weekend Read series features complimentary publications on a variety of topics on clinical trial design and data science. Subscribe to our weekly newsletter below and never miss a post!
Read more from Perspectives on Enquiry and Evidence:
Sorry no results please clear the filters and try again
Dynamic Bayesian Borrowing to Bolster Limited Sample Sizes in Rare Indications
Embracing Innovation: Exploring the Design of Umbrella and Basket Trials
Bayesian Adaptive Clinical Trial Designs: INLA vs. MCMC
